菜单
这个仓库中的 skills
SkillsMP 已收集 DojoGenesis/plugins 中的 352 个 Skill。打开任一 Skill 可查看来源和详情。
DojoGenesis/plugins已展示 40 / 352 个已收集 Skill。
Breaks a learning goal into chunked sessions with comprehension gates before advancing. Use when: 'help me learn X step by step', 'I want to understand this deeply not quickly', 'teach me this properly', 'I keep forgetting what I just read', 'I feel…
原文语言：英语
Produces an Exploration Brief rating a project GREEN/YELLOW/RED for collaboration fit, with architecture snapshot, resonance map, and ranked entry points. Use when: 'explore this project', 'assess this codebase', 'should we collaborate on this', 'onboard me…
原文语言：英语
Produces a Research Brief (deep mode) or Landscape Map (wide mode) document synthesizing findings into actionable recommendations. Use when: 'research this topic deeply', 'map the landscape of X', 'investigate and synthesize', 'do a wide scan of the…
原文语言：英语
Produces a unified Synthesis Document organized by themes with cross-source evidence, contradictions surfaced, and concrete recommendations. Use when: 'synthesize these research files', 'find patterns across these sources', 'consolidate my notes into…
原文语言：英语
Produces a Retrospective Document with structured reflection (what went well, what was hard, what to change) and seeds for the memory garden. Use when: 'do a retrospective', 'what did we learn from this sprint', 'reflect on this release', 'harvest the…
原文语言：英语
5-layer code analysis (AST, Call Graph, CFG, DFG, PDG) that yields 95% token savings over raw file reads. Use when: 'systematically understand an unfamiliar codebase', 'analyze code structure with minimal tokens', 'map call graphs and data flow', 'find dead…
原文语言：英语
Produces a numbered Architecture Decision Record with context analysis, route comparison, decision rationale, consequences, and propagation checklist. Use when: 'write an ADR', 'architectural decision', 'record a decision', 'ADR for'.
原文语言：英语
Bootstrap project structure from proven templates: phases, tracks, decisions, artifacts, commissions directories with README stubs and initial ADR-000 template.
原文语言：英语
Produces a typeset PDF artifact from any source file — code, Markdown, HTML, chat JSON, or structured Dojo files (specs, ADRs, skills). Use when: "export this to PDF", "generate a PDF of this file", "make a PDF from this".
原文语言：英语
Configure Pretext typography settings for PDF export — font stacks, sizing, line height, page geometry, and disposition-driven typography mapping. Use when defaults need tuning for specific content types or audiences.
原文语言：英语
Produces a signed distribution manifest and CAS-packaged skill set by orchestrating the full community-to-Dojo pipeline: shallow-clone repos, scan for compatibility, normalize frontmatter in parallel batches of 10, package via dojo CLI, and emit manifest.json…
原文语言：英语
Produces a documented directory structure plan — tree layout diagram, naming convention decision, and organizational philosophy — applying patterns such as feature-domain grouping, temporal prefixes for dated artifacts, numbered directories for ordered…
原文语言：英语
Builds production-ready remote MCP servers on Cloudflare Workers with typed tools, OAuth authentication, and Wrangler deployment. Use when: "build MCP server on Cloudflare", "remote MCP", "deploy MCP to Workers", "MCP OAuth authentication", "expose tools via…
原文语言：英语
Scaffolds production-ready MCP servers from OpenAPI specs with schema validation, named tool definitions, and versioning strategy. Use when: "build MCP server from API", "create tool server from OpenAPI", "expose REST API to LLM agent", "scaffold MCP from…
原文语言：英语
Produces an enriched SKILL.md with all six Dojo SkillRegistry.IsValid() fields populated — name, description, tier, agents, tool_dependencies, and trigger phrases — inferred from the existing body without rewriting it. Use when: "normalize this skill", "make…
原文语言：英语
Produces a complete SKILL.md by extracting and formalizing a workflow that has been executed at least twice, converting implicit procedural knowledge into installable, agent-executable instructions. Use when: "turn this process into a skill", "standardize…
原文语言：英语
Produces a compatibility catalog — skill-scan-report.md and skill-scan-catalog.json — classifying every SKILL.md in one or more GitHub repos or local paths as ready, normalizable, or incompatible, so you know exactly what normalization work lies ahead before…
原文语言：英语
Produces a complete SKILL.md packaged as a .skill file ready for CAS distribution. Use when: "create a new skill", "write a skill", "build a skill for this workflow", "turn this into a skill", "upgrade this to a skill".
原文语言：英语
Produces a maintained skills directory with updated names, unified terminology, repaired cross-references, and a git commit documenting every change and what was preserved. Use when: "update these skill names", "refactor the skills directory", "clean up skill…
原文语言：英语
Produces a quantified current-state report (test count, aria markers, error boundaries, storage usage, dependencies) used to anchor specifications in measured reality rather than assumptions. Use when: 'audit the codebase before speccing', 'ground this spec…
原文语言：英语
Produces a phased, file-grounded action plan from 1-2 uploaded documents (specs, meeting notes, design docs, or code files) with concrete deliverables and binary success criteria per phase. Use when: 'create a plan from this spec', 'plan the refactoring from…
原文语言：英语
Produces a backend-grounded frontend specification document covering API contracts, integration guide, auth flows, and updated track prompts. Use when 'spec the frontend for this API', 'write frontend spec from backend', or 'ground the UI in this existing…
原文语言：英语
Spec-to-fix pipeline: audit a codebase against its specification, classify gaps by severity, fix in parallel, track in GAPS.md registry. Use when a spec exists but implementation completeness is unknown.
原文语言：英语
Produces a self-contained implementation prompt document with objective, context grounding, numbered requirements, file manifest, binary success criteria, constraints, and backend grounding — ready for autonomous agent execution. Use when 'write an…
原文语言：英语
Produces a routing decision and delegated output by analyzing uploaded files and user intent, then dispatching to the correct specialized skill (context-ingestion, research-synthesis, or release-specification). Use when: 'create a plan from these files',…
原文语言：英语
Produces a gap inventory and Track 0 remediation commit that closes mismatches between implementation prompts and actual codebase state, ensuring parallel tracks start from a clean, type-safe foundation. Use when: 'commission these tracks', 'run Track 0…
原文语言：英语
Produces a completed pre-implementation checklist appended to a specification document, confirming vision clarity, technical readiness, implementation plan completeness, and Track 0 codebase alignment before any agent is commissioned. Use when: 'verify the…
原文语言：英语
Produces a production-ready release specification document (Full or Lean format) including current-state audit, technical architecture with code examples, implementation plan, and risk assessment. Use when 'write a release spec', 'create a release…
原文语言：英语
Produces a suite of coordinated, self-contained implementation prompts and a master integration contract table from a set of interconnected specs. Use when 'convert specs to prompts', 'ready to commission these specs', or 'coordinate these parallel tracks…
原文语言：英语
Produces a format-calibrated specification document — Full (5,000-15,000 words, all sections), Lean (1,000-3,000 words, agent-ready), or Minimal (delta + code examples) — matched to the scope and audience of the request. Use when: 'write a spec for this…
原文语言：英语
Produces a structured Zenflow commission document (Objective, Context & Grounding with pattern files, step-by-step Requirements, File Manifest, binary Success Criteria, and explicit Constraints) from a finalized spec, saved to prompts/vX.X.X/. Use when:…
原文语言：英语
Adversarial code review that breaks the self-review monoculture. Use when you want a genuinely critical review of recent changes, before merging a PR, or when you suspect Claude is being too agreeable about code quality. Forces perspective shifts through…
原文语言：英语
Produces a follow-up scout document that reframes the original question based on what feedback revealed (a reframe = a new strategic lens that changes which problem is worth solving). Use when: 'scout this again with fresh eyes', 'the first scout raised…
原文语言：英语
Produces a feature-to-surface mapping table, handoff design, and business model for a product spanning multiple platforms (desktop, mobile, web, CLI, etc.), where each surface has a distinct role rather than duplicating the others. Use when: "we need a…
原文语言：英语
Produces a reframed product positioning — a before/after statement that replaces a keep-or-kill decision with a complementary role for the product — plus a set of strategic routes that leverage that role. Use when: "should we deprecate X now that we have Y",…
原文语言：英语
Produces a complete set of phase-by-phase artifacts for a development cycle — scout document, backend grounding doc, parallel track specifications, implementation prompts, and a post-cycle reflection — by orchestrating the other strategic-thinking skills in…
原文语言：英语
Produces an aggregated markdown performance report from stored trace data — tool call metrics, token usage, cost, bottlenecks, and numbered recommendations. Use when: "session cost report", "what ran this week", "why did this spike", "end-of-sprint…
原文语言：英语
Produces a structured APPROVE / WARN / BLOCK decision by checking remaining token budget across query, session, and monthly tiers before an expensive operation runs. Use when: "is this operation within budget", "pre-flight check before web search", "budget…
原文语言：英语
Produces a verified build/test status report and auto-fixed modules by sweeping all Go modules in a workspace. Use when: "run a sweep", "check all builds", "nightly sweep", "fix all failing modules", "workspace health check".
原文语言：英语
Produces a committed audit log file enumerating documentation drift — inaccuracies, broken links, missing sections, and outdated information — with severity ratings and action taken. Use when: "docs seem out of date", "audit the documentation", "is the README…
原文语言：英语