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/agent-first-instructions.md
View on GitHub# Agent-First Instructions
Write the instruction the executing agent needs at the moment of choice.
## Strong Rules
A useful rule names:
- the trigger or pressure;
- the required or forbidden action;
- the evidence or stop condition.
Prefer:
> If the existing eval already preserves the failure and criteria, reuse it unchanged. Do not mutate evidence to prove process order.
Over:
> Ensure the evaluation workflow remains efficient and aligned with best practices.
## Placement
Order by behavioral priority:
1. user authority and source truth;
2. destructive or irreversible stops;
3. evidence and verification requirements;
4. normal execution;
5. convenience and style.
A late caveat rarely defeats an early command. Move the real constraint to where the agent first chooses.
## Editing From Failure
- Name the failed behavior.
- Find the sentence that should have prevented it.
- Sharpen or move that sentence before adding sections.
- Keep unrelated rules stable.
- Re-test the same pressure.
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 |