ccoalm/ccl-skills / skills/skill-extraction-workflow
skill-extraction-workflow
Flagged复盘 / 沉淀 / 总结经验 / 补进技能 / 技能缺陷 / 流程优化 / would other teammates hit this / will we forget next time / teamwide recurrence / extract skill / post-mortem / 深度 review·审计技能仓库 / 对标外部技能包找 gap(benchmark superpowers·gstack 等) / 核查全局安装点(~/.config/opencode 等)旧快照是否遮蔽本仓技能 / 本仓(ccl-skills 等共享技能仓)OpenCode 项目配置·命令治理 → turn reusable lessons into durable CCL skills.
references/analysis-parse-fix-test-challenge-replay.md
View on GitHub# Replay Validation Runbook
Use replay when validating whether a reusable extraction rule really works on a task shape similar to the one that produced it.
## When to Use
- A retrospective, bug hunt, or review follow-up produced a reusable workflow rule.
- The rule is meant to generalize beyond one incident or one repository.
- The new rule needs a pressure test before being treated as durable guidance.
## Replay Goal
Drive the task shape through the workflow as explicit stages:
1. analysis
2. parse / decompose
3. fix
4. test / verification
5. challenge
6. replay
Replay succeeds only if the workflow also keeps the four outputs separate:
- project-level fix
- test / verification evidence
- challenge findings
- reusable workflow lesson
## Replay Inputs
- The original task shape or a close analog
- The proposed workflow rule
- The validation and challenge checks that close the extraction
## Acceptance Criteria
- The problem is decomposed before extraction, not folded into analysis.
- The test/verification evidence is distinct from the fix.
- The challenge result is distinct from the validation result.
- The reusable lesson is general enough to survive a second task with the same shape.
## Failure Modes
- Treating replay as a prose-only example instead of an actual validation step.
- Reusing a one-off evidence bundle as durable skill content.
- Collapsing parse/decompose back into analysis.
- Declaring the lesson landed before replay confirms the workflow still produces the expected outputs.
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 |