Skip to content

hassan-mohiddin/freeflow / .deprecated/skill-tooling-pre-rewrite/skill-eval/evaluate-skill/fixtures/v3-legacy/accepted-bundle/evidence/reference/inputs/skill

write-skill

Verified

Use when creating, rewriting, tightening, or reviewing an agent skill's instructions, trigger description, structure, examples, or bundled resources.

Write Skill

Use Anthropic/Claude skill-creator guidance as the structure and progressive-disclosure authority when available. Do not copy it into this skill.

Use concise, behavior-shaping wording. Prefer sharp rules, concrete triggers, and stop conditions over explanation or filler.

Job

Write the smallest skill that changes behavior.

Start with one SKILL.md. Add other files only when the skill would fail without them.

Direct /write-skill, "production-ready", "complete", or "add examples/references/scripts if useful" does not override the smallest-skill default or the repo's skill-file rules.

Do not add references, examples, README files, changelogs, or metadata when a compact SKILL.md can hold the behavior.

Do not add helper scripts for commands the agent can run directly, such as git log, git diff, search, formatting, or line counts. Scripts are for repeated deterministic work that would be risky or wasteful to retype.

Treat the repo's line budget as a best practice, not a hard cap. If none exists, aim to keep SKILL.md under 100 lines for normal skills. Let deep skills exceed it when the active rules, examples, or structure clearly earn their place.

Description First

The description controls activation. Make it specific enough to route the skill without making it broad enough to hijack unrelated work.

Use:

  • What the skill does.
  • When to use it.
  • Concrete trigger situations.

Avoid:

  • Generic helper language.
  • Marketing copy.
  • Long taxonomies.
  • Claims about quality.

Wording Discipline

Every sentence should either route, constrain, stop, or guide behavior.

Prefer sharp rules over explanations. Prefer one good example over a paragraph.

Small wording changes can alter agent behavior. Change one pressure point at a time when possible.

Use direct verbs:

  • Inspect.
  • Stop.
  • Ask.
  • Do not edit.
  • Verify.
  • Report.

Avoid vague verbs:

  • Consider.
  • Ensure.
  • Leverage.
  • Try to.
  • Be mindful.

Placement Discipline

Order rules by behavioral priority, not topic neatness.

Put hard stop conditions before normal workflow details.

Put source-of-truth, user-owned decision, safety, and verification rules above convenience rules.

Do not hide the real constraint in a later caveat.

Revision Rule

Do not add prose because the skill "could be clearer." Add or move wording because an eval, user failure, or concrete pressure case showed a behavior gap.

When improving a skill after a failure:

  1. Name the failed behavior.
  2. Find the sentence that should have prevented it.
  3. Tighten wording or placement.
  4. Keep unrelated sections still.
  5. Re-run the smallest relevant eval.
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 470kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall