القائمة
Use when creating, regenerating, or auditing a repository-specific development harness, contract system, risk router, evidence gate, or project workflow policy.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
Use when designing, changing, or debugging backend server code (REST, Node.js/TypeScript, Go), especially endpoints, response envelopes, pagination, migrations, queries, auth, password hashing, secrets, or deploys; also for N+1 queries, races, IDOR, SSRF/injection, goroutine leaks, unhandled rejections, event-loop blocking, graceful shutdown, or production-only migration failures.
Use when designing, changing, or debugging backend server code (REST, Node.js/TypeScript, Go), especially endpoints, response envelopes, pagination, migrations, queries, auth, password hashing, secrets, or deploys; also for N+1 queries, races, IDOR, SSRF/injection, goroutine leaks, unhandled rejections, event-loop blocking, graceful shutdown, or production-only migration failures.
Use when a feature or refactor changes public contracts, schemas, shared integration points, cross-layer data flow, release behavior, or other high-risk architecture decisions.
Use when designing or debugging high-concurrency Go services, especially worker pools, backpressure, bounded channels, errgroup/WaitGroup, rate limits, load shedding, circuit breakers, GOMAXPROCS, or connection pools; also for load-time OOM, rising goroutines, lock contention, p99 spikes, retry storms, pprof, singleflight, semaphore, or production-only collapse.
Use when writing a git commit message, Japanese UI copy or app strings (ボタン/エラーメッセージ等の文言), code review comments, or a completion report, especially when tone, formality, verbosity, or review phrasing is uncertain.
Use when creating, regenerating, or auditing a repository-specific development harness, contract system, risk router, evidence gate, or project workflow policy.
استنادا إلى تصنيف SOC المهني
| name | harness-writing |
| description | Use when creating, regenerating, or auditing a repository-specific development harness, contract system, risk router, evidence gate, or project workflow policy. |
🌐 English version · 繁體中文（正本 / canonical）
Harness 是唯一的 orchestration kernel：狀態轉移靠風險路由與 claim→evidence 閘門；profile 選擇所需狀態；adapter 描述環境能力；契約保存專案判準；domain playbook 提供階段內技術方法。
不變核心不重造，專案參數不杜撰。檔案數只能當輔助訊號；主要依可逆性、爆炸半徑、歧義、外部副作用與可驗證性路由。
完整讀 harness-core-template.md 並填完所有 {{SLOT}}。以下不變量不得默刪：
candidate → active → hardened → deprecated 生命週期。覺得某項不適用時，在生成報告列出理由交給使用者裁決。
參數先寫成 JSON，再用 scripts/render_harness.py --template harness-core-template.md --config <config.json> --output <target-repo> 產生三個 artifact。renderer 只保證欄位完整、slot 全數解析與不覆寫既有檔案；參數真實性仍必須由探勘證據證明。
active；必須附來源與測驗／檢查。candidate，不可因一次觀察直接生效。candidate 只有在再次觀察、使用者明確裁決或明確事故證據下升 active；能低成本機械化再升 hardened。.claude/skills/harness/SKILL.md、references/pipelines.md 與 docs/contracts/README.md。feature-flow 等 process skill 作為 profile／階段策略，不建立第二狀態機。docs/plans/<slug>/；既有路徑可保留相容入口，但必須指定單一 canonical source。rg '\{\{[^}]+\}\}' .claude/skills/harness docs/contracts；任何殘留 slot 都阻擋交付。harness-core-template.md：生成前全文讀取；不可只靠本檔摘要自行重建。references/evaluation-protocol.md：換模型、校準路由或評估流程成本／成效時讀。references/evaluation-scenarios.json：行為 gate 的 canonical scenario ID／★ mapping。references/test-scenarios.md：換模型、修改 risk router／evidence／契約生命週期後，以 fresh session 回歸。scripts/render_harness.py：驗證 slot 並安全產生三個 canonical artifact。scripts/evaluate_runs.py：驗證 JSONL 行為紀錄、彙總成效指標並執行 gate。