init
Skill0 starsChanged 2 months agoMITView on GitHub
在一個專案裡初始化 Agent SDLC 流程——訪談設定、探測 GitHub Project 的 GraphQL ID、產生設定檔與治理文件。新專案要採用這套流程時的第一步。
137 other projects use a version of this.
Adopted by
Most recently taken up by
- naderelewa/Product-to-Prodtheir own version, first seen Nov 8, 2026
- ShahriarBijoy/show-me-howtheir own version, first seen Nov 8, 2026
- MMACABRE/SKILLStheir own version, first seen Nov 8, 2026
- BSSE23047/nauraiz-devtheir own version, first seen Nov 8, 2026
- edwinidrus/dragonhoardtheir own version, first seen Nov 8, 2026
- NilsHellwig/acl-paper-skillstheir own version, first seen Nov 8, 2026
Used with
Projects with it also use daily-arxiv, exp-eval and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
LambenthanSkilldaily-arxiv
每日从 arXiv 拉取新论文,过滤相关性,auto-ingest 高优先级论文,检测 SOTA 更新
Also in 5 projects that use this
LambenthanSkillexp-eval
实验判决门:Review LLM 独立评判实验结果 → 4 种判决路径 → 自动更新 claims confidence、ideas status、graph edges
Also in 5 projects that use this
skyllwtSkillexp-pilot-eval
Pilot result evaluation — read pilot results, apply success criteria, update idea page (pilot_result, failure_reason if failed), generate PILOT_VERDICT_REPORT. Called by /ideate Phase 5 after /exp-pilot-run.
Also in 4 projects that use this
skyllwtSkillexp-pilot-run
Pilot experiment execution — read Pilot Spec YAML, write pilot code, run experiment(Confirm with the user before operation and require the applicant to conduct manual inspection), return results. Called by /ideate Phase 5. Does NOT modify wiki pages or judge pass/fail.
Also in 4 projects that use this
gaebalaiSkillcodex-system
PROACTIVELY consult Codex CLI, your highly capable supporter with exceptional reasoning and task completion abilities. Codex is a trusted expert you should ALWAYS consult BEFORE making decisions on: design choices, implementation approaches, debugging strategies, refactoring plans, or any non-trivial problem. When uncertain, consult Codex. Don't hesitate - Codex provides better analysis. Explicit triggers: "think deeper", "analyze", "second opinion", "consult codex".
Also in 3 projects that use this
- +6 more from Lambenthan
- +1 more from skyllwt
Other versions137 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 137
- microsoft/vscode★ 195ksame name
- mcollina/skills★ 2ksame name
- skyllwt/OmegaWiki★ 1.7ksame name
- DAIR-AutoResearch/AutoSci★ 1.7ksame name
- PKU-DAIR/AutoSci★ 1.7ksame name
- skyllwt/AutoSci★ 1.7ksame name
- TokenRollAI/cc-plugin★ 483same name
- pipecat-ai/gradient-bang★ 420same name
- AlexPEClub/ai-coding-starter-kit★ 382same name
- dannysmith/tauri-template★ 312same name
127 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository13 other files it gives its agents.
- codebase-designSkill
- domain-modelingSkill
- grillingSkill
- grill-with-docsSkill
- implementSkill
- planSkill
- retroSkill
- shipSkill
- specSkill
- sprint-reviewSkill
- tddSkill
- ticket-checkSkill
- two-axis-reviewSkill
The file
Files
/sdlc:init — 專案初始化
把這套流程接進目前的專案。跑完之後,其餘所有 /sdlc:* skills 都從
docs/agents/sdlc.md 讀參數,不需要再問任何設定。
已經有 docs/agents/sdlc.md 的專案:改成「更新模式」——讀出現值、
只問要改的部分,不要整份重來。
1. 訪談(一次問完,用表格呈現預設值)
先探測能自己查到的,查得到的不要問:
gh repo view --json nameWithOwner --jq .nameWithOwner # 程式碼 repo
gh project list --owner @me --format json # 既有的 Project 板
ls CLAUDE.md CONTEXT.md docs/adr docs/agents 2>/dev/null # 已有的結構
git worktree list # 是否已用 worktree驗證指令用專案型態推測預設值(*.csproj → dotnet build/dotnet test;
package.json → npm test/npm run build;Makefile → make test……),
列出來讓使用者確認或修改。
然後問(每題附建議值):
- 批准者是誰?(名字或稱呼——Research Review、Plan Review、Done 的擁有者)
- Issue 開在哪個 repo?(可以和程式碼不同 repo;跨 repo 時所有
gh指令都要帶--repo) - 用哪個 GitHub Project 板? 既有的(列出來選)或新建一個
- 要不要 Epic 容器 issue?(多條產品線共用一個板時建議要)
- 用不用 worktree 流程?(多 session 平行開發才需要)
- 有沒有變異測試/契約檢查/本機部署驗證?(沒有就標「無」,DOD 會少那幾條—— 但要在設定檔留一行「無,補上時回來改」)
- 有沒有對外承諾(合約、SLA、給客戶的確認單)? 有 → 建
docs/obligations.md義務對照表,sprint-review 會必查 - 文件語言?(issue、spec、comment 用的語言)
2. 探測或建立 Project 板的 GraphQL ID
用既有的板:
# Project ID
gh project list --owner <owner> --format json --jq '.projects[] | "\(.number) \(.title) \(.id)"'
# Status 欄位與選項 ID(一次拿全)
gh api graphql -f query='query {
node(id: "<PROJECT_ID>") {
... on ProjectV2 {
field(name: "Status") {
... on ProjectV2SingleSelectField {
id
options { id name }
}
}
}
}
}'新建板:gh project create --owner <owner> --title "<名稱>",然後用 GraphQL
把 Status 欄位的選項改成十個階段(updateProjectV2SingleSelectField):
Todo、1.Research、1.Research Review、3.Plan、3.Plan Review、
4.Execute、4.Execute Review、5.Review、Final Review、Done。
改完再跑上面的查詢拿選項 ID。
⚠️ 拿到 ID 之後要實測一次才寫進設定檔:開一張測試 issue、走完
「開票三步驟」(見模板)、確認 Status 真的變了、再關掉刪掉。
ID 抄錯的症狀是 GraphQL 回 Could not resolve to a node——
在 init 當場撞到,比在第一張正式票撞到便宜得多。
3. 產生檔案
模板在本 skill 目錄的 templates/(用 plugin 安裝路徑下的實際檔案,逐一讀入後替換 {{...}} 佔位):
| 模板 | 寫到專案的哪裡 | 條件 |
sdlc.config.md | docs/agents/sdlc.md | 一律 |
dod.md | docs/agents/dod.md | 一律(依第 1 步答案增刪 B 段條目) |
CLAUDE-governance.md | 附加到專案 CLAUDE.md 結尾(沒有就新建) | 一律;已有同名段落就更新該段 |
adr-template.md | docs/adr/template.md | docs/adr/ 不存在才建 |
CONTEXT.md | CONTEXT.md | 不存在才建 |
另建空目錄:docs/sprints/(放 sprint-review 與 retro 的紀錄)。
不要覆蓋任何已存在的內容——CLAUDE.md 用附加、其他檔案存在就跳過並回報。
4. 收尾
- 把產生的檔案清單列給使用者
- 印出快速上手:
一張 story 的完整生命週期:
(討論需求)→ /sdlc:spec <issue> ← 定 AC,設 1.Research Review,等批准
批准後 → /sdlc:plan <issue> ← 拆 task,設 3.Plan Review,等批准
批准後 → 建票 → /sdlc:ticket-check <issue> ← 金魚閘門
過了 → /sdlc:implement ← 寫程式(TDD)
每張 task → /sdlc:ship <task> ← 驗證→commit→合併→CI→comment→自動接下一張
全部完成 → 自動推進到 Final Review,等批准者給 Done
Sprint 邊界:/sdlc:sprint-review → /sdlc:retro(順序固定)
原則背景:sdlc plugin 的 docs/PRINCIPLES.md- 建議使用者 commit 這批新檔案(訊息:
chore: 採用 Agent SDLC 流程)—— 但不要自己 commit,這是他的專案的第一個流程決定,該由他按下去。
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.

