hassan-mohiddin/freeflow / .deprecated/skill-tooling-pre-rewrite/skill-eval/evaluate-skill/fixtures/v3-legacy/accepted-bundle/evidence/candidate/inputs/skill
write-skill
VerifiedCreate or revise agent skills. Use when defining a skill's trigger description, active instructions, stop conditions, structure, examples, references, scripts, or readiness status.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 4.2 KB |
| references/activation-boundaries.md | markdown | 864 B |
| references/agent-first-instructions.md | markdown | 1012 B |
| references/development-loop.md | markdown | 974 B |
| references/progressive-disclosure.md | markdown | 842 B |
references/development-loop.md
View on GitHub# Skill Development Loop
## Draft
- Define purpose, trigger, non-goals, and failure pressure.
- Write the smallest candidate.
- Label it Draft or Unverified.
- Static validation may prove structure, not behavior.
## Iterate
- Preserve one strong failure or reuse an adequate case unchanged.
- Compare the exact old/no-skill control with the candidate under the same prompt, fixture, tools, host, and model settings.
- Grade objective artifacts before prose.
- Change one measured pressure point.
- Re-run the whole fixed case after the measured change; bootstrap does not reuse partial control evidence.
## Production-Ready
Require evidence relevant to the declared support:
- positive activation and near-miss non-trigger behavior;
- high-value pressure regressions;
- artifact outcomes where files or commands matter;
- honest unsupported labels for unavailable host or multi-turn evidence.
The owner decides promotion when evidence and residual gaps are visible.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| 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: 471k | Updated | Claude CodeCodex | Verified | Install |
| 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: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| 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 available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |