Authoring Fan-Agent Skills (in-repo)

Overview

There are two places a SKILL.md can live:

1. User-local: ~/.fan/skills/<maybe-category>/<name>/SKILL.md — personal, not shared. Created via skill_manage(action='create').
2. In-repo (this skill is about this case): /home/bb/fan-agent/skills/<category>/<name>/SKILL.md — committed, shipped with the package. Use write_file + git add. skill_manage(action='create') does NOT target this tree.

When to Use

• User asks you to add a skill "in this branch / repo / commit"
• You're committing a reusable workflow that should ship with fan-agent
• You're editing an existing skill under /home/bb/fan-agent/skills/ (use patch for small edits, write_file for rewrites; skill_manage still works for patch on in-repo skills, but not for create)

Required Frontmatter

Source of truth: tools/skill_manager_tool.py::_validate_frontmatter. Hard requirements:

• Starts with --- as the first bytes (no leading blank line).
• Closes with \n---\n before the body.
• Parses as a YAML mapping.
• name field present.
• description field present, ≤ 1024 chars (MAX_DESCRIPTION_LENGTH).
• Non-empty body after the closing ---.

Peer-matched shape used by every skill under skills/software-development/:

---
name: my-skill-name               # lowercase, hyphens, ≤64 chars (MAX_NAME_LENGTH)
description: Use when <trigger>. <one-line behavior>.
version: 1.0.0
author: Fan Agent
license: MIT
metadata:
  fan:
    tags: [short, descriptive, tags]
    related_skills: [other-skill, another-skill]
---

version / author / license / metadata are NOT enforced by the validator, but every peer has them — omit and your skill sticks out.

Size Limits

• Description: ≤ 1024 chars (enforced).
• Full SKILL.md: ≤ 100,000 chars (enforced as MAX_SKILL_CONTENT_CHARS, ~36k tokens).
• Peer skills in software-development/ sit at 8-14k chars. Aim for that range. If you're pushing past 20k, split into references/*.md and reference them from SKILL.md.

Peer-Matched Structure

Writing Quality Principles

A skill should make the Agent's process predictably better. Apply these checks:

1. Name the behavior change. Remove lines that do not alter what the Agent does.
2. Load context progressively. Keep triggers and always-needed steps here; move bulky or branch-specific material into linked references/, templates/, or scripts/.
3. Give every ordered step a completion criterion. Prefer checkable and exhaustive criteria over “be thorough.”
4. Co-locate each rule. Keep its definition, caveats, examples, and verification together.
5. Use compact leading concepts. “Tight loop,” “tracer bullet,” “root cause,” and “regression test” anchor behavior better than repeated generic prose.
6. Prune sediment. Replace old wording instead of layering duplicates; delete no-op advice such as “be careful.”
7. Prevent premature completion. Sharpen the current step's done condition before adding more phases.

Watch for duplication, stale sediment, always-visible sprawl, no-op prose, and steps that allow the Agent to move on before the work is genuinely complete.

Every in-repo skill follows roughly:

# <Title>

## Overview
One or two paragraphs: what and why.

## When to Use
- Bulleted triggers
- "Don't use for:" counter-triggers

## <Topic sections specific to the skill>
- Quick-reference tables are common
- Code blocks with exact commands
- Fan-specific recipes (tests via scripts/run_tests.sh, desktop paths, etc.)

## Common Pitfalls
Numbered list of mistakes and their fixes.

## Verification Checklist
- [ ] Checkbox list of post-action verifications

## One-Shot Recipes (optional)
Named scenarios → concrete command sequences.

Not every section is mandatory, but Overview + When to Use + actionable body + pitfalls are the minimum for the skill to feel like a peer.

Directory Placement

skills/<category>/<skill-name>/SKILL.md

Categories currently in repo (confirm with ls skills/): autonomous-ai-agents, creative, data-science, devops, dogfood, email, gaming, github, leisure, mcp, media, mlops/*, note-taking, productivity, red-teaming, research, smart-home, social-media, software-development.

Pick the closest existing category. Don't invent new top-level categories casually.

Workflow

1. Survey peers in the target category:

   ls skills/<category>/
   

   Read 2-3 peer SKILL.md files to match tone and structure.
2. Check validator constraints in tools/skill_manager_tool.py if unsure.
3. Draft with write_file to skills/<category>/<name>/SKILL.md.
4. Validate locally:

   import yaml, re, pathlib
   content = pathlib.Path("skills/<category>/<name>/SKILL.md").read_text()
   assert content.startswith("---")
   m = re.search(r'\n---\s*\n', content[3:])
   fm = yaml.safe_load(content[3:m.start()+3])
   assert "name" in fm and "description" in fm
   assert len(fm["description"]) <= 1024
   assert len(content) <= 100_000
   

5. Git add + commit on the active branch.
6. Note: the CURRENT session's skill loader is cached — skill_view / skills_list will not see the new skill until a new session. This is expected, not a bug.

Cross-Referencing Other Skills

metadata.fan.related_skills unions both trees (skills/ in-repo and ~/.fan/skills/) at load time. You CAN reference a user-local skill from an in-repo skill, but it won't resolve for other users who clone the repo fresh. Prefer referencing only in-repo skills from in-repo skills. If a frequently-referenced skill lives only in ~/.fan/skills/, consider promoting it to the repo.

Editing Existing In-Repo Skills

• Small fix (typo, added pitfall, tightened trigger): skill_manage(action='patch', name=..., old_string=..., new_string=...) works fine on in-repo skills.
• Major rewrite: write_file the whole SKILL.md. skill_manage(action='edit') also works but requires supplying the full new content.
• Adding supporting files: write_file to skills/<category>/<name>/references/<file>.md, templates/<file>, or scripts/<file>. skill_manage(action='write_file') also works and enforces the references/templates/scripts/assets subdir allowlist.
• Always commit the edit — in-repo skills are source, not runtime state.

Common Pitfalls

1. Using skill_manage(action='create') for an in-repo skill. It writes to ~/.fan/skills/, not the repo tree. Use write_file for in-repo creation.

2. Leading whitespace before ---. The validator checks content.startswith("---"); any leading blank line or BOM fails validation.

3. Description too generic. Peer descriptions start with "Use when ..." and describe the trigger class, not the one task. "Use when debugging X" > "Debug X".

4. Forgetting the author/license/metadata block. Not validator-enforced, but every peer has it; omitting makes the skill look half-finished.

5. Writing a skill that duplicates a peer. Before creating, ls skills/<category>/ and open 2-3 peers. Prefer extending an existing skill to creating a narrow sibling.

6. Expecting the current session to see the new skill. It won't. The skill loader is initialized at session start. Verify in a fresh session or via skill_view using the exact path.

7. Letting skills accumulate sediment. When adding a rule, remove the wording it replaces.

8. Writing no-op prose. Replace “be careful” or “use best practices” with a checkable completion criterion.

9. Linking to skills that don't exist in-repo. related_skills: [some-user-local-skill] works for you but breaks for other clones. Prefer only in-repo links.

Verification Checklist

• File is at skills/<category>/<name>/SKILL.md (not in ~/.fan/skills/)
• Frontmatter starts at byte 0 with ---, closes with \n---\n
• name, description, version, author, license, metadata.fan.{tags, related_skills} all present
• Name ≤ 64 chars, lowercase + hyphens
• Description ≤ 1024 chars and starts with "Use when ..."
• Total file ≤ 100,000 chars (aim for 8-15k)
• Structure: # Title → ## Overview → ## When to Use → body → ## Common Pitfalls → ## Verification Checklist
• Ordered steps have checkable completion criteria
• Description is trigger-focused and does not duplicate the body
• Branch-specific or bulky material is progressively disclosed
• Duplicate, stale, and no-op prose removed
• related_skills references resolve in-repo (or are explicitly OK to be user-local)
• git add skills/<category>/<name>/ && git commit completed on the intended branch