task-bootstrap
Skill2 starsChanged 22 days agoNo licenceView on GitHub
Use when the user explicitly calls "/task-bootstrap", says "開新任務", or asks to "bootstrap a task". First hands off to a repo-local *task-bootstrap if the repo has one; otherwise runs session-start, then creates a branch and a git worktree for the new task (main, baseline or task mode), copies .env and a few local files, and shows the plan before changing anything. Runs only when the user calls it explicitly.
- Reads credentials
- Commits and pushes
In this repository55 other files it gives its agents.
- global/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- global/CLAUDE.mdCLAUDE.md
- activity-loggerSkill
- ai-weekly-insightSkill
- arxiv-digestSkill
- assumption-extractorSkill
- brainstormingSkill
- claude-workflow-designerSkill
- codebase-auditSkill
- code-review-claudeSkill
- code-review-codexSkill
- code-review-geminiSkill
- code-story-tellerSkill
- completion-gateSkill
- control-returnSkill
- critical-researchSkill
- deai-voice-rewriteSkill
- deep-readingSkill
- git-status-tuiSkill
- handoffSkill
- interactive-presentation-generatorSkill
- lessonSkill
- md-translateSkill
- micro-poc-validatorSkill
- narrative-auditorSkill
- newsletter-digestSkill
- pptx-to-mdSkill
- presentation-plannerSkill
- pr-review-assistantSkill
- qa-to-notesSkill
- report-generatorSkill
- repo-syncSkill
- research-cross-validatorSkill
- research-synthesisSkill
- review-convergence-gateSkill
- role-orchestratorSkill
- role-pmSkill
- role-rdSkill
- secure-ai-development-gateSkill
- sepiaSkill
- session-preferencesSkill
- session-startSkill
- skill-auditorSkill
- skill-routerSkill
- skill-syncSkill
- spec-gap-finderSkill
- tech-feasibilitySkill
- technical-proposal-reviewSkill
- tech-research-pipelineSkill
- ui-design-analyzerSkill
- understand-fileSkill
- understand-functionSkill
- understand-repoSkill
- work-log-analyzerSkill
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.