Repository
Stanshy/AgentHub agent skills
- skills
- 23
- GitHub stars
- 201
GitHub description: “One person, one software company. Manage 47 AI agents from a single Electron app — with Harness Engineering (Skills + Hooks + FileWatchers) for disciplined, traceable AI workflows.”
- Stars
- 201 (24 forks)
- Licence
- MIT
- Last push
- Apr 2026
- Created
- Mar 2026
- Homepage
- agenthub.stanshy.com
- ai-agents
- ai-workflow
- claude-code
- developer-tools
- electron
- harness-engineering
- open-source
- team-management
- typescript
- vue
Install all skills
npx skills add Stanshy/AgentHubAdd --skill <name> for a single skill and -a <agent> to choose the agent (see the agent guides).
Skills in Stanshy/AgentHub, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | 1.Dev Plan Generate a development plan with task breakdown and section 10 tracking tables | Stanshy/ | 201 | — | ~686 | Automated safety check: Notes | MIT | 6 mo ago |
| 2 | Scan child projects for pitfalls and propose company standard updates | Stanshy/ | 201 | — | ~549 | Automated safety check: Notes | MIT | 6 mo ago |
| 3 | Six-question diagnostic framework for G0 pre-check — validate product direction before development starts | Stanshy/ | 201 | — | ~690 | Automated safety check: Pass | MIT | 6 mo ago |
| 4 | Initialize new project with CLAUDE.md, .knowledge/ structure, company rules, and git | Stanshy/ | 201 | — | ~528 | Automated safety check: Notes | MIT | 6 mo ago |
| 5 | 5.Review L1 internal review with auto-detection, design comparison, and Gate escalation path | Stanshy/ | 201 | — | ~854 | Automated safety check: Notes | MIT | 6 mo ago |
| 6 | 6.Sop Plan L1 計畫模式 SOP — 強制上下文載入 + Plan Mode 評估 + 任務拆解. An agent skill from Stanshy/AgentHub. | Stanshy/ | 201 | — | ~437 | Automated safety check: Notes | MIT | 6 mo ago |
| 7 | L1 Code Review SOP — 強制規範對照 + 審核決策，不得跳過任何 checkpoint. An agent skill from Stanshy/AgentHub. | Stanshy/ | 201 | — | ~522 | Automated safety check: Notes | MIT | 6 mo ago |
| 8 | Mark a task as done after L1 review passes. An agent skill from Stanshy/AgentHub. | Stanshy/ | 201 | — | ~451 | Automated safety check: Notes | MIT | 6 mo ago |
| 9 | Create task breakdown in dev plan section 6 and generate .tasks/ files | Stanshy/ | 201 | — | ~432 | Automated safety check: Notes | MIT | 6 mo ago |
| 10 | Boss dispatches tasks — auto-create .tasks/ files and record in dev-plan | Stanshy/ | 201 | — | ~554 | Automated safety check: Notes | MIT | 6 mo ago |
| 11 | 11.Task Done Mark a task as inreview (pending L1 review) and record in dev plan section 10 | Stanshy/ | 201 | — | ~489 | Automated safety check: Notes | MIT | 6 mo ago |
| 12 | 12.Task Start Mark a task as inprogress when agent begins working. An agent skill from Stanshy/AgentHub. | Stanshy/ | 201 | — | ~412 | Automated safety check: Notes | MIT | 6 mo ago |
| 13 | 13.Gate Record Record a gate review decision in the dev plan section 10. An agent skill from Stanshy/AgentHub. | Stanshy/ | 201 | — | ~317 | Automated safety check: Pass | MIT | 6 mo ago |
| 14 | Periodic Harness health audit based on 7 design principles. An agent skill from Stanshy/AgentHub. | Stanshy/ | 201 | — | ~390 | Automated safety check: Notes | MIT | 6 mo ago |
| 15 | 15.Pm Review PM reviews gate submission with 6-item checklist and recommendation | Stanshy/ | 201 | — | ~259 | Automated safety check: Pass | MIT | 6 mo ago |
| 16 | 16.Pre Deploy Pre-deployment checklist for G5 submission. An agent skill from Stanshy/AgentHub. | Stanshy/ | 201 | — | ~297 | Automated safety check: Notes | MIT | 6 mo ago |
| 17 | 17.Sop Deploy 部署 SOP — 強制品質 checklist + pre-deploy 確認，不得跳過任何 checkpoint. An agent skill from Stanshy/AgentHub. | Stanshy/ | 201 | — | ~292 | Automated safety check: Notes | MIT | 6 mo ago |
| 18 | 18.Sop Execute L2 任務執行 SOP — 強制規範載入 + 驗收確認，不得跳過任何 checkpoint. An agent skill from Stanshy/AgentHub. | Stanshy/ | 201 | — | ~410 | Automated safety check: Notes | MIT | 6 mo ago |
| 19 | 19.Sprint Close Merge sprint branch to base branch, tag release, and clean up branches | Stanshy/ | 201 | — | ~305 | Automated safety check: Notes | MIT | 6 mo ago |
| 20 | Generate a sprint proposal document with scope, risks, and G0 checklist | Stanshy/ | 201 | — | ~202 | Automated safety check: Pass | MIT | 6 mo ago |
| 21 | 21.Task Status Update task status and append event log in .tasks/ file. An agent skill from Stanshy/AgentHub. | Stanshy/ | 201 | — | ~382 | Automated safety check: Pass | MIT | 6 mo ago |
| 22 | Record a pitfall or lesson learned in the postmortem log. An agent skill from Stanshy/AgentHub. | Stanshy/ | 201 | — | ~183 | Automated safety check: Pass | MIT | 6 mo ago |
| 23 | 23.Sprint Retro Generate sprint retrospective by analyzing section 10 data. An agent skill from Stanshy/AgentHub. | Stanshy/ | 201 | — | ~160 | Automated safety check: Pass | MIT | 6 mo ago |
Questions, answered from the data.
What is the best skill in Stanshy/AgentHub?
Dev Plan from Stanshy/AgentHub ranks first of the 23 skills in Stanshy/AgentHub listed here, with the highest score: its repository has 201 GitHub stars, its SKILL.md loads about 686 tokens and it has informational notes only in the automated safety check. Next come Knowledge Feedback and Product Diagnosis.
Are the skills in Stanshy/AgentHub official?
None yet. All 23 skills in Stanshy/AgentHub listed here come from community repositories; a skill counts as official when the product's own GitHub organization publishes it.
How do I install all skills from Stanshy/AgentHub?
Run npx skills add Stanshy/AgentHub in your project: the open-source skills CLI installs the repository's skills into your coding agent's skills folder. To install a single skill, open its page here for the exact command.
How are these skills ranked?
By Skill Navigator score, which combines the GitHub stars of the skill's repository (shared across that repo's skills and discounted for large collections), how many other GitHub owners carry a copy of the skill, and automated SKILL.md quality checks, minus penalties for safety-check warnings and for each further skill from the same repository. Skills that fail the safety check are not listed.