project-init
Skill0 starsChanged 2 months agoMITView on GitHub
Bootstrap Superpowers agent workflow in a project — docs/superpowers folders, mandatory skills (brainstorming, writing-plans, semantic-version, caveman-commit, dont-forget, recap, automate-before-manual, dont-be-lazy, validate-before-share, finish-with-dev-server, ask-before-architecture, diagrams-mermaid, ui-change-e2e), slash commands, AGENTS.md gates. Use when user invokes /init or asks to initialize agent conventions in a new or legacy repo.
43 other projects use a version of this.
Adopted by
Most recently taken up by
- emadabdulrahim/claude-skillstheir own version, first seen Nov 16, 2026
- tjst-t/claude-skillstheir own version, first seen Nov 16, 2026
- mridun-gupta/project-init.skillstheir own version, first seen Nov 15, 2026
- veraetogrex-portfolio/solo-sddtheir own version, first seen Nov 15, 2026
- CT-masato-hino/claude-code-project-packtheir own version, first seen Nov 15, 2026
- AlexZio00/sovereign-skillstheir own version, first seen Nov 14, 2026
Used with
Projects with it also use harness-audit, workflow and 3 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.
sattva2020Skillharness-audit
Audits a codebase for "AI-agent harness" maturity across six layers (context engineering, tools & MCP, memory & state, tests & evals, observability, guardrails & approvals). Scores each layer, flags AGENTS.md/CLAUDE.md drift, gives prioritized fixes. Use for "audit harness", "оцени харнес", "check agent readiness", "is this project agent-ready", "проверь готовность к AI-агентам".
Also in 3 projects that use this
VercelSkillworkflow
Creates durable, resumable workflows using Vercel's Workflow SDK. Use when building workflows that need to survive restarts, pause for external events, retry on failure, or coordinate multi-step operations over time. Triggers on mentions of "workflow", "durable functions", "resumable", "workflow sdk", "queue", "event", "push", "subscribe", or step-based orchestration.
Also in 3 projects that use this
MicrosoftSkillrelease
Use ONLY when the user explicitly asks to cut/publish a Huabu desktop release or tag a version. Performs an outward action — bumps the version in apps/desktop/package.json, commits + annotated-tags vX.Y.Z, and pushes the branch + tag. That tag push auto-builds the macOS/Windows installers and publishes a GitHub Release. Provides `status`, `bump`, `tag-push`, and a one-command `run` (bump → tag-push).
Also in 4 projects that use this
MicrosoftSkillhandoff
Compact the current conversation into a handoff document for another agent to pick up.
Also in 3 projects that use this
GoogleSkillcode-review
Adversarial systems, concurrency, memory-model, and architecture code review protocol. Use this skill whenever asked to review code, PRs, diffs, or branches in Filament.
Also in 3 projects that use this
Other versions43 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 43
- bkywksj/knowledge-base★ 346same name
- zephyrwang6/myskill★ 339same name
- AlexZio00/sovereign-skills★ 158same name
- claude-world/director-mode-lite★ 80same name
- agencia-conversion/agentic-seo-skills★ 51same name
- u9401066/pubmed-search-mcp★ 28same name
- mathruffian-dot/cross-device-agent-skills★ 27same name
- ecodelearn/template-claude-code-open★ 25same name
- peter-tu-zynkr/zynkr-skill-builder★ 21same name
- SpaceZephyr/allSkills★ 14same name
33 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 repository26 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .cursor/rules/automate-before-manual.mdcCursor rule
- .cursor/rules/finish-task-dev-server.mdcCursor rule
- brainstormingSkill
- caveman-commitSkill
- find-skillsSkill
- semantic-versionSkill
- systematic-debuggingSkill
- verification-before-completionSkill
- writing-plansSkill
- ask-before-architectureSkill
- automate-before-manualSkill
- caveman-commitSkill
- diagrams-mermaidSkill
- dont-be-lazySkill
- dont-forgetSkill
- find-jobSkill
- finish-with-dev-serverSkill
- google-calendar-mcpSkill
- init-fmzSkill
- instagram-chrome-postSkill
- recapSkill
- semantic-versionSkill
- skills-sh-maintainerSkill
- ui-change-e2eSkill
- validate-before-shareSkill
The file
We split this skill into the rules it gives an agent
6 rules. 0 are common, 1 is distinctive, and 5 are very specific to this project.
0
Common
Most of the 22 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
5
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 64
Read README.md, AGENTS.md, package.json, docs/stack.md.
- Distinctive: line 68
Create if missing (never delete existing specs/plans):
- Very specific: line 80
Run the sync script (installs all current farukzahra/agent-skills packages, including any newly added skills):
- Very specific: line 125
Create docs/release-history.json at 0.1.0 if missing.
- Very specific: line 137
Run without user invoking /init
- Very specific: line 139
Commit or push (/commit-push handles ship)
“Common” is measured: kept by at least 6 in 10 of the 22 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Project init — bootstrap agent workflow
Only when the user invokes /init or asks to initialize this repo — never automatic.
Sets up Superpowers + Faruk mandatory skills in the current project. Does not scaffold apps, commit, or push.
Summary (what init does)
| # | Action |
| 1 | Create docs/superpowers/specs/ and plans/ (+ README) |
| 2 | Install mandatory skills at project scope |
| 3 | Ensure /commit-push, /init, and /recap in .cursor/commands/ |
| 4 | Optional: Cursor rules + docs/release-history.json for web apps |
| 5 | Merge AGENTS.md workflow table (never replace a rich file) |
Mandatory skills to install
Superpowers (obra/superpowers via skills-lock.json)
| Skill | Gate |
brainstorming | No feature code before approved spec |
writing-plans | Plan → docs/superpowers/plans/ |
systematic-debugging | Root cause before bug fixes |
verification-before-completion | Evidence before "done" |
Faruk (farukzahra/agent-skills)
| Skill | Gate |
semantic-version | Version bump only on /commit-push → /sobre |
caveman-commit | Commit messages on /commit-push |
dont-forget | Recurring rules → CI/hooks/codegen, not prose |
recap | Session handoff → HTML recap (/recap) |
automate-before-manual | Try PAT/SSH/API before manual steps (../secrets/) |
dont-be-lazy | User lazy → API/MCP, vault, Cursor browser — agent finishes |
validate-before-share | Verify URLs before sending to user |
finish-with-dev-server | Dev server up, port conflict rules, test URLs |
ask-before-architecture | Ask before stack/architecture choices |
diagrams-mermaid | Mermaid only; validate syntax before show |
ui-change-e2e | E2E on UI create/change/bugfix |
Optional after init
skills-sh-maintainer— onlyagent-skillsrepo
Workflow
1. Inspect
Read README.md, AGENTS.md, package.json, docs/stack.md. Note stack only.
2. Superpowers folders
Create if missing (never delete existing specs/plans):
docs/superpowers/specs/
docs/superpowers/plans/
docs/superpowers/README.mdTemplate README: farukzahra/agent-skills → reference/superpowers/docs-README.md (or local clone path).
3. Install skills
Run the sync script (installs all current farukzahra/agent-skills packages, including any newly added skills):
# From any machine with agent-skills cloned — relative to repo parent:
../agent-skills/scripts/sync-faruk-skills.ps1Or manually:
npx skills experimental_install
npx skills add farukzahra/agent-skills -a cursor -y(-y installs every skill in the package; omit skills-sh-maintainer outside agent-skills repo — the script handles that.)
- No
skills-lock.json→ copyskills-lock.core.jsonfrom agent-skills, thenexperimental_install - Existing full lock →
experimental_installonly; do not overwrite
Stack skills (if missing from lock):
| Signal | Add |
| Next.js | vercel-react-best-practices, frontend-design |
| Vue | vue-best-practices, frontend-design |
| Prisma | prisma-cli, prisma-client-api, prisma-database-setup, prisma-postgres |
| Playwright | playwright-best-practices |
| Fastify | nodejs-backend-patterns |
4. Slash commands
Copy from agent-skills repo if missing:
reference/commands/commit-push.md→.cursor/commands/commit-push.mdreference/commands/init.md→.cursor/commands/init.mdreference/commands/recap.md→.cursor/commands/recap.md
Deploy config: docs/commit-push.json (see reference/commands/deploy-manifest.json).
5. Cursor rules (if .cursor/rules/ empty)
From Faruk Base: automate-before-manual.mdc, finish-task-dev-server.mdc.
6. Release history (web apps)
Create docs/release-history.json at 0.1.0 if missing. Bump only via /commit-push.
7. AGENTS.md
Append workflow table if missing — see reference/agents-snippet.md.
8. Report
List: folders created, skills installed, commands ready (/init, /commit-push, /recap), next step = brainstorming.
Do not
- Run without user invoking
/init - Overwrite lock, specs, or plans without permission
- Commit or push (
/commit-pushhandles ship) - Install
skills-sh-maintaineroutside agent-skills
Paths (Faruk local)
| Item | Path |
| Agent-skills repo | ../agent-skills (sibling of project repos) |
| Secrets vault | ../secrets/ (never absolute paths in skills) |
| Sync all Faruk skills | ../agent-skills/scripts/sync-faruk-skills.ps1 |
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.

