Loading...
Loading...
Found 10,427 Skills
Pylon MCP tools for pushing plans, code reviews, and pulling human feedback. Use this skill when interacting with the Pylon AI-to-human review bridge.
Create a new feature/bug track with spec and implementation plan. Interactive interview generates requirements spec, then phased TDD plan. Use when starting work on a new feature, bug fix, or chore.
Structured Autonomy Planning Prompt
从内容到成品PPTX的端到端演示文稿制作，含AI插画生成和18种设计风格。当用户提到"做PPT"、"做幻灯片"、"演示文稿"、"Keynote"、"slides"时使用。
Create a new plugin for Claude Code marketplace with validation, ADR, and release automation. TRIGGERS - create plugin, new plugin, scaffold plugin, add plugin, plugin-dev create.
Assists in creating, modifying, viewing or managing GitHub Pull Request (PR). Automatically analyzes branch commits and change content, generates compliant Traditional Chinese PR titles and descriptions. Use cases include: (1) Create a new PR from the current branch, (2) Modify the title, description, reviewers or labels of an existing PR, (3) Check the PR status of the branch (open, merged, closed), (4) Need to automatically aggregate multiple changes to generate a summary. Applicable to scenarios with requests such as "create PR", "create pull request", "help me open a PR", "modify PR content". Operations are executed via GitHub CLI (gh).
Universal context reviewer: delegates arbitrary context (plans, decisions, documents, architecture proposals) to external agents (Codex + Gemini) for independent review with debate protocol. Context always passed via files.
The human project owner and final authority. Does not write code or run tools -- resolves tie-breaks, approves or denies major decisions, and unblocks deadlocks.
Multi-agent review of implementation plans. Use after creating a plan but before implementing, especially for complex or risky changes.
Senior Agile Facilitator & Delivery Architect for 2026. Specialized in AI-enhanced Scrum orchestration, automated ticket management, and high-velocity sprint coordination. Expert in utilizing LLMs to synthesize daily updates, detect blockers before they arise, and maintain a high-integrity backlog across GitHub Issues, Jira, and linear.
Auto-fix CodeRabbit review comments - get CodeRabbit review comments from GitHub and fix them interactively or in batch
Bind addressable evidence IDs from `papers/evidence_bank.jsonl` to each subsection (H3), producing `outline/evidence_bindings.jsonl`. **Trigger**: evidence binder, evidence plan, section->evidence mapping, 证据绑定, evidence_id. **Use when**: `papers/evidence_bank.jsonl` exists and you want writer/auditor to use section-scoped evidence items (WebWeaver-style memory bank). **Skip if**: you are not doing evidence-first section-by-section writing. **Network**: none. **Guardrail**: NO PROSE; do not invent evidence; only select from the existing evidence bank.