Split gitea skill into main file and reference documentation.
Main SKILL.md now focuses on core commands (154 lines, down from 201),
with setup/auth and CI/Actions moved to reference files.
Co-Authored-By: Claude Code <noreply@anthropic.com>
Remove top-level model override to allow per-skill/agent model configuration.
Reorder sections for consistency.
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
Claude Code has unified commands into skills with the user-invocable
frontmatter field. This migration:
- Converts 20 commands to skills with user-invocable: true
- Consolidates docs into single writing-capabilities.md
- Rewrites capability-writing skill for unified model
- Updates CLAUDE.md, Makefile, and other references
- Removes commands/ directory
Skills now have two types:
- user-invocable: true - workflows users trigger with /name
- user-invocable: false - background knowledge auto-loaded
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Resolves issue #86 by having the spawn-issues orchestrator create worktrees
upfront and pass the worktree paths to agents, instead of having agents
create their own worktrees in sibling directories outside the sandbox.
Changes:
- spawn-issues orchestrator creates all worktrees before spawning agents
- issue-worker, pr-fixer, code-reviewer accept optional WORKTREE_PATH
- When WORKTREE_PATH is provided, agents work directly in that directory
- Backward compatible: agents still support creating their own worktrees
if WORKTREE_PATH is not provided
- Orchestrator handles all worktree cleanup after agents complete
- Eliminates permission denied errors from agents trying to access
sibling worktree directories
This ensures agents operate within their sandbox while still being able to
work with isolated git worktrees for parallel implementation.
Closes#86
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Set explicit model preferences to optimize for speed vs capability:
- haiku: 11 commands, 2 agents (issue-worker, pr-fixer), 10 skills
Fast execution for straightforward tasks
- sonnet: 4 commands (groom, improve, plan-issues, review-pr),
1 agent (code-reviewer)
Better judgment for analysis and review tasks
- opus: 2 commands (arch-refine-issue, arch-review-repo),
1 agent (software-architect)
Deep reasoning for architectural analysis
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add linter detection logic that checks for common linter config files
(ESLint, Ruff, Flake8, Pylint, golangci-lint, Clippy, RuboCop)
- Add instructions to run linter on changed files only
- Add "Lint Issues" section to review output format
- Clearly distinguish lint issues from logic/security issues
- Document that lint issues alone should not block PRs
Closes#25
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Introduces a new command that guides users through creating capabilities
for the architecture repository. The command analyzes user descriptions,
recommends appropriate component combinations (skill, command, agent),
gathers necessary information, generates files from templates, and presents
them for approval before creation.
Closes#75
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add model: sonnet to issue-worker agent (balanced for implementation)
- Add model: sonnet to pr-fixer agent (balanced for feedback iteration)
- Add model: haiku to /dashboard command (read-only display)
- Add model: haiku to /roadmap command (read-only categorization)
- Document rationale for each model selection in frontmatter comments
Closes#72
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Creates a lighter-weight PR creation flow for when you're already on a
branch with commits. Features:
- Auto-generates title from branch name or commits
- Auto-generates description summarizing changes
- Links to related issue if branch name contains issue number
- Triggers code-reviewer agent after PR creation
Closes#19
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add new section to display recent workflow runs from tea actions runs
- Show status indicators: [SUCCESS], [FAILURE], [RUNNING], [PENDING]
- Highlight failed runs with bold formatting for visibility
- Gracefully handle repos without CI configured
- Include example output format for clarity
Closes#20
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The planning process previously jumped directly from understanding a feature
to breaking it down into issues. This led to proposing issues without first
understanding the user's actual workflow and where the gaps are.
Added a discovery phase that requires walking through:
- Who is the specific user
- What is their goal
- Step-by-step workflow to reach the goal
- What exists today
- Where the workflow breaks or has gaps
- What's the MVP
Issues are now derived from workflow gaps rather than guessing.
Closes#29
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add streamlined commit workflow that analyzes staged changes and
generates conventional commit messages (feat:, fix:, etc.) with
user approval before committing.
Closes#18
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Creates a skill that teaches how to design and create capabilities
(skill + command + agent combinations) for the architecture repository.
Includes:
- Component templates for skills, commands, and agents
- Decision tree and matrix for when to use each component
- Model selection guidance (haiku/sonnet/opus)
- Naming conventions and anti-patterns to avoid
- References to detailed documentation in docs/
- Checklists for creating each component type
Closes#74
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add Architecture Beliefs section to manifesto with outcome-focused beliefs:
auditability, business language in code, independent evolution, explicit over implicit
- Create software-architecture.md as human-readable documentation
- Enhance software-architecture skill with beliefs→patterns mapping (DDD, Event
Sourcing, event-driven communication) and auto-trigger description
- Update work-issue command to reference skill and check project architecture
- Update issue-worker agent with software-architecture skill
- Add Architecture section template to vision-management skill
The skill is now auto-triggered when implementing, reviewing, or planning
architectural work. Project-level architecture choices go in vision.md.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The code reviewer prompt was minimal and didn't specify worktree setup,
causing parallel reviewers to interfere with each other by checking out
different branches in the same directory.
Changes:
- Add worktree setup/cleanup to code reviewer prompt (like issue-worker/fixer)
- Add branch tracking to issue state
- Add note about passing branch name to reviewers
- Expand reviewer prompt with full review process
This ensures each reviewer works in isolation at:
../<repo>-review-<pr-number>
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Creates a new command that refines issues with architectural perspective
by spawning the software-architect agent to analyze the codebase before
proposing implementation guidance. The command:
- Fetches issue details and spawns software-architect agent
- Analyzes existing patterns and affected components
- Identifies architectural concerns and dependencies
- Proposes refined description with technical notes
- Allows user to apply, edit, or skip the refinement
Closes#59
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add software architecture review as a standard part of PR review process:
- Reference software-architecture skill for patterns and checklists
- Spawn software-architect agent for architectural analysis
- Add checks for pattern consistency, dependency direction, breaking changes,
module boundaries, and error handling
- Structure review output with separate Code Review and Architecture Review
sections
Closes#60
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Creates a new command that spawns the software-architect agent to perform
comprehensive architecture audits. The command analyzes directory structure,
package organization, patterns, anti-patterns, dependencies, and test coverage,
then presents prioritized recommendations with a health score.
Closes#58
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Replace polling loop with task-notification based orchestration.
Background tasks send notifications when complete - no need to poll.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Create the software-architect agent that performs deep architectural
analysis on codebases. The agent:
- References software-architecture skill for patterns and checklists
- Supports three analysis types: repo-audit, issue-refine, pr-review
- Analyzes codebase structure and patterns
- Applies architectural review checklists from the skill
- Identifies anti-patterns (god packages, circular deps, etc.)
- Generates prioritized recommendations (P0-P3)
- Returns structured ARCHITECT_ANALYSIS_RESULT for calling commands
Closes#57
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Creates the foundational skill that encodes software architecture
best practices, review checklists, and patterns for Go and generic
architecture guidance.
Closes#56
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Each issue flows independently through: implement → review → fix → review
- Don't wait for all workers before starting reviews
- Print status update as each step completes
- Poll loop checks all tasks, advances each issue independently
- State machine: implementing → reviewing → fixing → approved/failed
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
spawn-issues now orchestrates the full workflow:
- Phase 1: Spawn issue-workers in parallel, wait for completion
- Phase 2: Review loop - spawn code-reviewer, if needs work spawn pr-fixer
- Phase 3: Report final status
issue-worker simplified:
- Removed Task tool and review loop
- Just implements, creates PR, cleans up
- Returns structured result for orchestrator to parse
Benefits:
- Better visibility into progress
- Reuses pr-fixer agent
- Clean separation of concerns
- Orchestrator controls review cycle
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The inline prompt in spawn-issues.md was missing the review loop
that was added to issue-worker/agent.md. Now includes:
- Step 7: Spawn code-reviewer synchronously, fix and re-review if needed
- Step 9: Concise final summary output
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add Task tool to spawn code-reviewer synchronously
- Add review loop: fix issues and re-review until approved (max 3 iterations)
- Add final summary format for cleaner output to spawning process
- Reviewer works in same worktree, cleanup only after review completes
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Background agents need skills specified in frontmatter rather than
using @ syntax which may not expand for Task-spawned agents.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
New command that spawns background agents to work on multiple
issues simultaneously, each in an isolated git worktree.
- commands/spawn-issues.md: Entry point, parses args, spawns agents
- agents/issue-worker/agent.md: Autonomous agent that implements
a single issue (worktree setup, implement, PR, cleanup)
Worktrees are automatically cleaned up after PR creation.
Branch remains on remote for follow-up work if needed.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Adds guidance to prefer vertical slices (user-visible value) over
horizontal slices (technical layers) when planning and writing issues.
roadmap-planning skill:
- New "Vertical vs Horizontal Slices" section
- Demo test: "Can a user demo/test this independently?"
- Good vs bad examples table
- When horizontal slices are acceptable
issue-writing skill:
- New "Vertical Slices" section
- Demo test guidance
- Good vs bad issue titles table
- User-focused issue framing examples
Closes#31
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Skills are knowledge modules referenced by commands, not
directly invoked by users. Added user-invocable: false to:
- backlog-grooming (used by /groom)
- claude-md-writing (used by /update-claude-md)
- code-review (used by /review-pr)
- issue-writing (used by /create-issue)
- roadmap-planning (used by /plan-issues)
- vision-management (used by /vision, /manifesto)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Updates or creates CLAUDE.md with:
- Organization context section (links to manifesto, repos.md, vision)
- Current project structure from filesystem scan
- Architecture patterns inferred or asked
Preserves existing custom content, shows diff before writing.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Create claude-md-writing skill with best practices for CLAUDE.md files
- Create repos.md registry of all repos with status (Active/Planned/Splitting)
- Update /create-repo to include organization context section
- Update repo-conventions to reference new skill
Each repo's CLAUDE.md now links to manifesto, repos.md, and vision.md
so Claude always understands the bigger picture.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Skill documents standard repo structure, naming conventions,
open vs proprietary guidance, and CI/CD patterns.
Command scaffolds new repos with vision.md, CLAUDE.md, Makefile,
CI workflow, and .gitignore - all linked to the architecture repo.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Software should run well on modest hardware. ARM64-native where possible.
Bloated software is a sign of poor engineering.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Product repos find the manifesto at ../architecture/manifesto.md.
This allows the architecture repo to be a sibling of product repos.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Rebuild vision.md to trace personas, jobs, and principles back to manifesto
- Improve /vision command with inheritance guidance and templates
- Update vision-management skill with explicit inheritance rules and formats
Product visions now explicitly extend (not duplicate) organization manifesto.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Shift from developer-centric personas (solo dev, small team) to the actual
mission: empowering domain experts to create software without coding.
- Who We Serve: Domain experts, Agencies, Organizations (small → enterprise)
- Added "Empowering Domain Experts" beliefs section
- Integrated "build in public" into Who We Are
- Updated non-goals to align with new focus
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Updated all internal references for the rename:
- CLAUDE.md: New purpose statement, updated structure, added manifesto info
- README.md: Updated title, clone URL, folder structure
- commands/retro.md: Changed flowmade-one/ai to flowmade-one/architecture
The actual Gitea rename should be done after merging this PR.
Closes#44🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Restructured skill to clearly distinguish:
- Manifesto: Organization-level (architecture repo)
- Vision: Product-level (product repos)
Key additions:
- Architecture table showing all three levels with commands
- Manifesto section with structure, when to update, creation steps
- Vision section clarified as product-level extending manifesto
- Relationship diagram showing inheritance model
- Example of persona inheritance (org → product)
- Continuous improvement loop including retro → encoding flow
- Quick reference table for common questions
Closes#43🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Changed the retro flow to:
1. Retro (any repo) → Issue (architecture repo)
2. Later: Encode issue into learning file + skill/command/agent
Key changes:
- Retro now only creates issues, not learning files
- Learning files are created when the issue is worked on
- All issues go to architecture repo regardless of source repo
- Added "When the Issue is Worked On" section for encoding guidance
- Clearer separation between capturing insights and encoding them
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Clarifies /vision is for product-level vision, distinct from /manifesto
which handles organization-level vision.
Changes:
- Added architecture table showing org vs product vs goals levels
- Process now checks for manifesto first for org context
- Output format includes Organization Context section
- Guidelines clarify when to use /manifesto vs /vision
- Product personas/jobs extend (not duplicate) org-level ones
Closes#41🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Adds new command to view and manage the organization-level manifesto.
Distinct from /vision which handles product-level vision.
Features:
- Guides manifesto creation if none exists
- Displays formatted summary of existing manifesto
- References vision-management skill
- Clear output format for all sections
Closes#40🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Adds learnings folder for capturing insights from retros and daily work.
Learnings serve as historical record, governance reference, and encoding
source for skills/commands/agents.
README includes:
- Purpose explanation (historical + governance + encoding)
- Learning template with all sections
- Encoding process and destination guide
- Periodic review guidance
- Naming conventions
Closes#39🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Defines the foundational organization-level vision:
- Who We Are: Small, focused AI-native builders
- Personas: Solo developer, Small team, Agency/Consultancy
- Jobs to Be Done: Ship fast, maintain quality, stay in flow
- Beliefs: AI-augmented development, quality without ceremony, sustainable pace
- Guiding Principles: Encode don't document, small teams big leverage, etc.
- Non-Goals: Enterprise compliance, every platform, replacing judgment
Closes#38🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The vision system now guides defining WHO we build for and WHAT they're
trying to achieve before jumping into goals and issues.
Updated vision-management skill:
- New vision.md structure with Personas and Jobs to Be Done sections
- Guidance for defining good personas (specific, characterized, limited)
- Guidance for jobs to be done (outcome-focused, in their voice, pain-aware)
- Milestones now tied to personas and jobs with structured descriptions
- Issue alignment checks persona/job fit before milestone fit
Updated vision command:
- Guides through persona and JTBD definition when creating vision
- Output format shows personas and jobs prominently
- Guidelines emphasize traceability to personas
Updated plan-issues command:
- Identifies persona and job before breaking down work
- Plan presentation includes For/Job/Supports context
- Flags misalignment with persona/job, not just goals
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Updated skills and commands to identify and formally link issue
dependencies using tea CLI:
Skills updated:
- issue-writing: Document deps in description + link with tea CLI
- backlog-grooming: Check for formal dependency links in checklist
- roadmap-planning: Link dependencies after creating issues
Commands updated:
- create-issue: Ask about and link dependencies for new issues
- plan-issues: Create in dependency order, link with tea issues deps add
- groom: Check dependency status, suggest missing links
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Updated work-issue and review-pr commands to use --comments flag,
ensuring discussion context is available when working on issues or
reviewing pull requests.
Closes#32🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Refactored the vision system to separate concerns:
- vision.md remains the stable "north star" philosophy document
- Gitea milestones now track goals with automatic progress via issue counts
- Updated /vision, /retro, and /create-issue commands to auto-assign milestones
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Transforms the product-manager from a reactive backlog manager into a
vision-driven system with continuous improvement capabilities.
New components:
- vision-management skill: How to create, maintain, and evolve product vision
- /vision command: View, create, or update product vision (syncs to Gitea)
- /improve command: Identify gaps between vision goals and backlog
Enhanced existing components:
- product-manager agent: Now vision-aware with strategic prioritization
- /retro command: Connects learnings back to vision updates
- /plan-issues command: Shows vision alignment for planned work
The vision lives in two places: vision.md (source of truth) and a Gitea
issue labeled "vision" for integration with the issue workflow.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Document tea pulls merge as the correct merge method
- Add warning against using Gitea API with admin credentials
- Document tea comment as alternative to interactive tea pulls review
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The approval step was failing on self-authored PRs and stopping the
merge flow. Since LGTM verdict already indicates approval, just merge
directly without the separate tea pulls approve command.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The tea CLI doesn't have a command to output PR diff content directly.
The -f diff flag only returns a URL. Updated docs to use tea pulls
checkout followed by git diff main...HEAD.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The skills are already listed in frontmatter (skills: gitea, issue-writing,
backlog-grooming, roadmap-planning), so the "Use the gitea skill"
instruction was unnecessary.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Skills have only ~20% auto-activation rate when referenced by name.
Using @~/.claude/skills/*/SKILL.md guarantees skill content is loaded.
Updated all commands to use file references instead of "Use the X skill".
Updated docs/writing-commands.md with new pattern and examples.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Updated all skill descriptions with proper trigger terms following
the pattern: "What it does. Use when [trigger terms]."
Skills updated:
- code-review: triggers on PR review, code quality, bugs, security
- issue-writing: triggers on creating issues, bug reports, features
- backlog-grooming: triggers on grooming, reviewing issue quality
- roadmap-planning: triggers on planning features, breaking down work
Updated docs/writing-skills.md:
- Added YAML frontmatter requirements section
- Documented required and optional fields
- Added guidance on writing effective descriptions
- Updated "How Skills are Loaded" to reflect model-invoked behavior
- Added note about subagent skill access
- Updated checklist with frontmatter requirements
- Added reference to official documentation
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The description now follows the documented pattern:
1. What it does: specific actions (view, create, manage)
2. When to use: trigger terms users would mention (issues, PRs, tea, gitea)
This helps Claude know when to automatically apply the skill.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The allowed-tools field in skills RESTRICTS which tools can be used,
not grants permission. The tea CLI permissions are already configured
in settings.json via permissions.allow.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
When the gitea skill is active, Claude can now use tea CLI commands
without asking permission. This enables smoother workflow when using
commands like /work-issue that rely on the gitea skill.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Skills require YAML frontmatter with name and description fields
for Claude Code to automatically discover and load them. Added
frontmatter to all five skill files:
- gitea: CLI for issues, PRs, and repository management
- code-review: Guidelines for reviewing code changes
- issue-writing: How to write clear, actionable issues
- backlog-grooming: Review and improve existing issues
- roadmap-planning: Plan features and create issues
Closes#12🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Heredoc syntax causes tea comment to be backgrounded and fail silently.
Updated Comments section to:
- Use quoted strings with literal newlines for multiline comments
- Add warning about avoiding heredoc syntax
Closes#10🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Documents that tea CLI uses --description/-d flag for PR body content,
not --body like the gh CLI. This helps avoid failed commands when
transitioning from gh CLI.
Closes#5🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Allow all tea and git commands without approval prompts.
This enables the code-reviewer agent to post comments
and merge PRs automatically.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add Comments section to gitea skill with examples
- Update code-reviewer agent with explicit tea CLI commands
for posting comments, approving, and merging PRs
Closes#6🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The tea CLI doesn't have a `view` subcommand - use `tea issues <number>`
directly instead of `tea issues view <number>`.
- Fix example in ARCHITECTURE.md
- Add clarifying tip in gitea skill to prevent this common mistake
Closes#2🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Captures learnings from completed AI-assisted work and creates
improvement issues in the AI repo. Creates a feedback loop where
friction points and insights get tracked as actionable issues.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Replace fj CLI with tea CLI across all commands
- Create new gitea skill, remove forgejo skill
- Update all agents to use gitea skill
- Update commands to use skill-based approach (reference skills instead of embedding CLI commands)
- Update all documentation (README, ARCHITECTURE, VISION, writing guides)
- Swap git remotes: origin now points to git.flowmade.one (Gitea)
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add explicit example and warning to prevent agents from misinterpreting
the fj pr view diff command. The correct format is:
fj pr view <number> diff
NOT:
fj pr diff <number>
Closes#25🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
When the code-reviewer agent determines a PR is LGTM with no blocking
issues, it now automatically merges using rebase strategy and deletes
the branch. PRs with "Needs Changes" or "Blocking Issues" verdicts
are left for the user to address.
Closes#23🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Adds checklist item prompting agent authors to make deliberate
model selection choices rather than defaulting to `inherit`.
Positioned after skills list, before capabilities.
Closes#19🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Adds checklist item prompting agent authors to make deliberate
model selection choices rather than defaulting to `inherit`.
Positioned after skills list, before capabilities.
Closes#19🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Both agents now use `sonnet` instead of `inherit`:
- code-reviewer: Sonnet provides good code understanding for
structured review tasks without needing opus-level reasoning
- product-manager: Planning and issue-writing follow patterns
from skills; sonnet handles these well
Each agent includes a comment explaining the model choice.
Closes#18🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Adds a new "Model Selection" section that explains when and why to
choose different Claude models (haiku, sonnet, opus, inherit) for agents.
Includes:
- Model characteristics comparison table
- Decision matrix for agent task types
- Concrete examples with reasoning
- Best practices for model selection
- Guidance on when to use `inherit`
Closes#17🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Adds step 8 to spawn the code-reviewer agent in background after PR creation.
The agent will review the PR diff and post feedback as a comment.
Closes#11🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Update product-manager agent to use official Claude Code format
- Update ARCHITECTURE.md to document frontmatter fields
- Add code-reviewer agent and code-review skill to docs
- Update README.md project structure
This aligns our agent documentation with the official Claude Code
agent format which uses YAML frontmatter for name, description,
model, skills, and tools.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Follow official Claude Code agent format with:
- name, description, model, skills in frontmatter
- System prompt as markdown content
- Streamlined documentation focused on agent behavior
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Shows good vs bad comment styles for each review category:
code quality, bugs, security, style, test coverage, and positive feedback.
Closes#10🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Create specialized agent for automated PR code review that:
- Fetches PR diffs via fj CLI
- Analyzes code for quality, bugs, security, style, and test coverage
- Posts structured review comments to PRs
Includes code-review skill with guidelines for reviewing code changes.
Closes#9🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Create docs/writing-commands.md with comprehensive documentation for
writing new commands:
- File structure (commands/<name>.md with YAML frontmatter)
- Argument handling with $1, $2 placeholders and argument-hint patterns
- How commands invoke skills and spawn agents
- Interactive patterns: approval workflows, choices, input gathering
- Annotated examples from all 7 existing commands
- Naming conventions and best practices
- Submission checklist
Closes#5🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Create docs/writing-agents.md with comprehensive documentation for
writing new agents:
- File structure and naming conventions (agents/<name>/AGENT.md)
- How agents combine multiple skills into focused personas
- Use cases: parallel processing, context isolation, complex workflows,
autonomous exploration
- When to use agents vs direct skill invocation with decision matrix
- Annotated walkthrough of product-manager agent
- Best practices for skill selection, boundaries, and guardrails
Closes#4🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Create docs/writing-skills.md with comprehensive documentation for
writing new skills:
- File structure and naming conventions
- How skills are loaded and referenced by commands/agents
- Best practices for composable, focused content
- Annotated examples from existing skills (forgejo, issue-writing,
backlog-grooming, roadmap-planning)
- Checklist for new skill submissions
Closes#3🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Remove fj pr status (doesn't work reliably)
- Post review summary as comment before merging
- Delete branch after merge with -d flag
- Document all merge options in forgejo skill
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Explains how commands, skills, and agents work together as a
composable AI workflow system. Includes ASCII diagram, component
relationships, data flow examples, and guidance for adding new
components.
Closes#2🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Clarify the three actions available after review:
- Merge (approve by merging)
- Request changes (comment without merging)
- Comment only (discussion)
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The fj CLI doesn't have a `pr review` subcommand. Updated documentation
to reflect actual available commands (pr comment for feedback).
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Covers:
- The problem: inconsistent AI-assisted workflows
- The solution: composable toolkit for Claude Code
- Component types: skills, agents, commands
- Target users: developers using Claude Code with Forgejo
- Guiding principles: encode don't repeat, composability,
approval before action, dogfooding, progressive disclosure
Closes#1🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
