golden-path-validation
Skill1 starsChanged 2 months agoNo licenceView on GitHub
驗證一份 setup 指引 / runbook / onboarding / bootstrap 是否「陌生人每次照做都能完整重現」的方法：派無前置知識的冷讀代理人、在可拋棄乾淨環境實際照指引執行，抓文件 fact-check 放過、只有實機跑才現形的硬編假設 / 環境漂移 / verifier 自己的 bug。五階段：完整性稽核 → 自動化 verify → 冷讀代理人實機執行 → 乾淨環境 re-verify → 發現回收。觸發詞：驗證 setup 指引、runbook 驗證、onboarding 測試、bootstrap 測試、golden path / paved road 驗證、每次照做都能重現、冷讀測試、cold-read、陌生人照做、實機執行驗證、setup guide validation、原生非模擬、verifier 也要被驗。Trigger when validating that a follow-along setup/onboarding/bootstrap guide actually works for a newcomer, via cold-read agents executing it in disposable clean environments.
In this repository75 other files it gives its agents.
- 5w1h-decisionSkill
- agent-teamSkill
- asd-ste100Skill
- blank-slate-reviewSkill
- branch-worktree-guardianSkill
- broken-link-checkSkill
- bulk-evaluateSkill
- business-analysisSkill
- business-researchSkill
- case-first-module-workflowSkill
- cc-release-impact-reviewSkill
- chrome-extension-mcp-debugSkill
- cognitive-load-assessmentSkill
- component-contract-designSkill
- compositional-writingSkill
- content-extension-evaluationSkill
- continuous-learningSkill
- dart-comment-traceabilitySkill
- dart-domain-modelingSkill
- dart-provider-architectureSkill
- dart-style-guardianSkill
- dart-test-async-guardianSkill
- data-extractionSkill
- decision-tree-helperSkill
- design-decision-frameworkSkill
- dispatch-strategy-reviewSkill
- doc-flowSkill
- docSkill
- error-patternSkill
- event-flow-arbitration-designSkill
- evidence-driven-bugfixSkill
- foundation-designSkill
- framework-issueSkill
- frontend-with-playwrightSkill
- impeccableSkill
- knowledge-cardsSkill
- linux-install-debugSkill
- lsp-firstSkill
- mermaid-asciiSkill
- methodology-writingSkill
- migration-playbook-methodologySkill
- multi-round-reviewSkill
- multi-session-orchestrationSkill
- neurodivergent-outputSkill
- observability-stackSkill
- parallel-evaluationSkill
- pre-fix-evalSkill
- project-analysisSkill
- project-initSkill
- requirement-protocolSkill
- saas-tech-selectionSkill
- scope-confirmationSkill
- search-tools-guideSkill
- skill-design-guideSkill
- skill-syncSkill
- specSkill
- startup-checkSkill
- strategic-compactSkill
- system-designSkill
- system-misjudgmentSkill
- The first 60 shown.
The file
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.