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>
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>
Introduces project README covering the composable component architecture
(commands, skills, agents), quick start guide, available commands, and
example workflows. This complements CLAUDE.md which serves as internal
instructions for the AI.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Move commands, scripts, settings to repo root
- Add Makefile with install/uninstall/status targets
- Symlinks ~/.claude/* to this repo for version control
- Update documentation with setup instructions
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add .claude/ directory for Claude Code configuration
- Add prompts/ for reusable prompt templates
- Add scripts/ for automation scripts
- Add hooks/ for Claude Code hooks
- Add CLAUDE.md with project documentation
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
