Menu
Skills in this repository
SkillsMP has collected 722 skills from Sheshiyer/skill-clusters. Open a skill to review its source and details.
Sheshiyer/skill-clustersShowing 40 of 722 collected skills.
Analyze a GitHub repo's issue/PR/code state, produce a status report, and propose or execute the next wave of work with parallel agents. USE WHEN asked 'where is this repo now?', to summarize issues and decide what's next, to run the next wave, or for ongoing…
Upgraded planning protocol for large-scale delivery plans: interactive discovery, 80-task default granularity, phase→wave→swarm orchestration, and dispatch-aware GitHub synchronization. USE WHEN you need a production-grade, heavily parallelized execution plan…
Dispatches Claude Code Task subagents to run prompts from a vault plan note. Tracer-first execution, time-budgeted work, calibrated review rigor. Use when the user says "execute the plan", "run group A", "dispatch", or is ready to run prompts from a…
First-run walkthrough for Conducty. Confirms vault location, seeds indexes if missing, ingests the user's primary project via [[conducty-context]], and produces a tiny scoped first plan so the user sees the cycle end-to-end. Use when the user says "set up…
Quality gate between parallelization groups. Verifies every prompt at its assigned review level, computes health metrics, detects systemic failures, updates hill charts. Use when a group finishes, the user says "checkpoint" or "verify group", or between…
Standalone post-implementation code review across a whole branch or PR. Goes beyond the in-cycle spec/quality reviewers (which check single prompts) to assess the diff holistically — security, correctness, perf, idioms, dead code, hidden coupling, test depth.…
Ingest a project directory into the Obsidian vault as a linked context sub-graph — Architecture, Conventions, Invariants, Hotspots, Tests, Glossary, plus per-bounded-context module notes. Tracks refresh deltas over time, flags stale context, and feeds prompt…
Leverage-point analysis for failed prompts. Determines whether the fix belongs at the plan, prompt, or code level before generating any fix. Use when a prompt fails verification, a checkpoint catches an issue, fix attempts aren't working, or the user says…
Multi-persona decision analysis through structured dialectic. Six software-engineering archetypes debate a question to uncover the Design Truth. Use when the user says "analyze this decision", "dialectic", "decision analysis", "think this through", "debate…
End-of-plan improvement kata. Extracts lessons from the just-finished plan, identifies experiments, and shapes the next plan's approach. USE WHEN [[conducty-review]] has just completed, or the user says "what did we learn", "improve the process",…
Conducty's context engine lives in an Obsidian vault. This skill defines the vault layout, naming, linking, and index conventions every other Conducty skill must follow when reading or writing notes. Use when reading/writing any plan, design, context,…
Batch planning of AI prompts. Loads vault context (latest plan, latest improvement, project context, failure patterns, metrics), sets appetite, generates time-budgeted prompts with tracer markers and calibrated review levels. Use when the user says "plan",…
End-of-plan review sweep. Audits the plan's executed prompts, records verdicts with evidence, extracts failure patterns, computes velocity metrics, prepares carry-forward intelligence. Use when the user says "review", "audit", "review this plan", or at the…
Defines appetite, scope, no-go zones, and design before any prompts are written. Use when a goal is Medium or High complexity, requirements are unclear, scope needs bounding, or the user says "shape", "design", "brainstorm", "think through".
Pre-merge / pre-deploy gate. Runs the full ship-readiness battery — lint, typecheck, test suite, secrets scan, dependency-vulnerability check, [[conducty-code-review]] verdict — and writes a `Ship Reports/Ship Report YYYY-MM-DD HHmm.md` note with a…
Establishes the Conducty orchestration system — its philosophy, ten engineering-grounded principles, ubiquitous language, and per-plan cycle. USE WHEN starting any session before invoking other Conducty skills, or the user says "what is Conducty", "explain…
Test-driven development at orchestrator (verification-first planning) and implementer (red-green-refactor) levels. Use when implementing any feature/bugfix, when writing tests, when the plan specifies TDD, or when the user says "TDD", "red-green-refactor",…
Caveman-style compression for conducty orchestration artifacts — subagent prompt text, plan note prompt blocks, prompt log entries, checkpoint notes. Cuts token waste in the orchestration layer where "prompt quality is leverage" already demands tight…
Vault hygiene audit — finds orphaned notes, broken wikilinks, stale context, never-consumed designs, missing index entries, and unused improvement experiments. Writes a `Vault Audit YYYY-MM-DD HHmm.md` report. Use when the user says "vault audit", "vault…
The evidence gate. Run the verification command via Bash, read the output, then make the claim. USE WHEN about to mark ANY prompt complete, before any "done" / "passed" claim, or the user asks to verify, confirm, or prove a result.
Git worktree lifecycle for parallel prompt execution. Creates isolated worktrees per prompt, verifies baselines, merges after checkpoint, cleans up. Use when a parallelization group has 2+ prompts targeting the same repo, or the user says "worktree",…
Biopython is a comprehensive set of freely available Python tools for biological computation — sequence manipulation, file I/O, database access, structural bioinformatics, and phylogenetics. USE WHEN parsing FASTA/GenBank or other bio file formats, querying…
Give agents persistent structural memory of a codebase — navigate dependencies, track public APIs, and understand why connections exist without re-reading the whole repo. USE WHEN building an agent that must reason over a large codebase's structure or…
Route a database/data task to the right skill among the data-layer specialists — PostgreSQL, MySQL/MariaDB, the Prisma ORM, Redis, ClickHouse analytics, cross-engine migrations, and high-throughput ingestion/ETL. USE WHEN a user is designing, querying,…
Guide for building reliable, fault-tolerant Go applications with DBOS durable workflows. Use when adding DBOS to existing Go code, creating workflows and steps, or using queues for concurrency control.
Guide for building reliable, fault-tolerant Python applications with DBOS durable workflows. Use when adding DBOS to existing Python code, creating workflows and steps, or using queues for concurrency control.
Guide for building reliable, fault-tolerant TypeScript applications with DBOS durable workflows. Use when adding DBOS to existing TypeScript code, creating workflows and steps, or using queues for concurrency control.
Route a document task to the right skill among the documents specialists — office formats (DOCX/PDF/PPTX/XLSX), docs sites, changelogs, OCR extraction, natural-language PDF edits, NotebookLM, and diagram authoring. USE WHEN a user wants to create, edit,…
Route an SEO/growth task to the right skill among 8 search specialists — intent research, content briefs, site architecture, schema/structured data, programmatic pages at scale, technical audits, AI-search (AEO/GEO) optimization, and Google's official…
Standalone Google Gemini image-generation CLI (gemini-3-pro-image-preview) for UI placeholders, documentation illustrations, icons, and design assets, driven by a stdlib Python script with no MCP server. USE WHEN you want to generate an image from a text…
Route a media-generation task to the right tool among 11 specialists — image generation (GPT Image 2, Nano Banana 2, OpenAI Images), image enhancement, image-to-3D, AI video direction, FFmpeg processing, frame extraction, and GIF search/authoring. USE WHEN a…
Expert patterns for Neon serverless Postgres — branching, connection pooling, and Prisma/Drizzle integration. USE WHEN running Postgres on Neon, setting up per-PR/preview DB branches, or wiring the serverless driver/pooler from a serverless or edge app.
NetworkX is a Python package for creating, manipulating, and analyzing complex networks and graphs. USE WHEN modeling graph/network data, running graph algorithms (shortest path, centrality, community detection), or analyzing relationships and connectivity in…
Generate an absurdly thorough README.md by deeply exploring a codebase first — tech stack, getting-started, architecture, env vars, scripts, testing, deployment, and troubleshooting. USE WHEN a user asks to write, create, or update a README or document a…
Generate marketing-quality, true-retina (2x) app screenshots with Playwright — discover routes/features from the codebase, handle login, and capture each view. USE WHEN a user wants screenshots for Product Hunt, social media, a landing page, or documentation.
Generate SEO-optimized competitor comparison and alternatives pages — X vs Y layouts, alternatives-to-X pages, feature matrices, Product/ItemList schema, and conversion-optimized CTAs. USE WHEN a user wants a comparison page, vs page, alternatives page,…
Content quality and E-E-A-T analysis with AI-citation (GEO) readiness scoring — readability, thin-content risk, keyword and structure checks, and helpful-content alignment. USE WHEN a user wants a content quality review, E-E-A-T audit, readability check,…
Use DataForSEO for live SERPs, keyword metrics, backlinks, competitor analysis, on-page checks, and AI-visibility data via its MCP server. USE WHEN a user needs real, live SEO data (rankings, volumes, backlinks, LLM mentions) rather than static best-practice…
Hreflang and international SEO audit, validation, and generation — self-referencing/return tags, x-default, ISO language/region code validation, and HTML/header/sitemap output. USE WHEN a user mentions hreflang, i18n SEO, international SEO, multi-language,…
Generate SEO-focused images — OG/social cards, blog heroes, schema ImageObject assets, product visuals, and infographics — with per-use-case aspect ratio, resolution, and a post-gen SEO checklist (alt text, WebP, schema). USE WHEN image generation is part of…