Recently added
Plugins grouped by the day they were added to the directory, newest first.
Aug 30, 2026
- cr0stars
GitHub workflow commands and audits for cr-calleja-software projects, configured per-project via .claude/project.md
Claude Code1 skill - mutantkit0stars
Run and interpret MutantKit mutation testing for Swift and Apple-platform projects: check readiness, plan, run, inspect survivors, and gate CI on real test-suite strength rather than line coverage.
CodexClaude Code1 skill - trade-study-analysis1stars
Systematic trade study using DAU 9-Step Process
Claude Code1 skill - streaming-output1stars
Stream long-form content to markdown files with resume capability and context preservation
Claude Code1 skill - streaming-output-mcp1stars
Stream structured content to persistent SQLite storage with automatic session break recovery. Supports multi-format export (Markdown, HTML, JSON, YAML, CSV, Text) and document templates. Core principle: The content IS the state.
Claude Code1 skill1 MCP server - speckit-generator1stars
Project-focused specification and task management with PLANS taxonomy, ADR-style architecture decisions, SMART acceptance criteria, SEAMS-enhanced clarification, tech-specific designer agents, anti-pattern detection (50 patterns across 5 tech stacks), 4-level verification (stub detection + wiring checks), execution orchestration (deviation rules, checkpoint taxonomy, auth gates, session continuity), specialized analysis agents, git checkpoints, mandatory approval gates, and session-memory hooks. Outputs to speckit/ directory.
Claude Code3 skills - specification-refiner1stars
Systematic analysis and refinement of specifications with SEAMS framework, sequential clarification questioning, and multi-phase workflow
Claude Code1 skill - skill-tester1stars
Deep test, analyze, and audit Claude skills. Use this skill whenever the user wants to test a skill's behavior, analyze how it uses the Claude API, inspect inputs/outputs from scripts, or run security and code review audits against skill scripts. Trigger on: "test my skill", "analyze this skill", "audit skill scripts", "review skill for security issues", "what does this skill actually do when it runs", "inspect API calls from skill", "run a skill through its paces", "check my skill for bugs or vulnerabilities". Also trigger when the user shows you a SKILL.md and asks you to evaluate, critique, or stress-test it.
Claude Code1 skill Research and opportunity investigation for protocols
Claude Code1 skill- requirements-dev1stars
Transform concept development artifacts into INCOSE-compliant formal requirements. AI-assisted requirements development with hybrid quality checking (16 deterministic + 9 semantic INCOSE GtWR v4 rules), verification planning, bidirectional traceability, gap analysis against concept architecture, assumption lifecycle management, and ReqIF export. Organized around functional blocks from concept development. Includes cross-cutting notes registry, need/requirement split workflow, gap discovery agent, assumption tracker, 5 specialized agents (quality-checker, tpm-researcher, skeptic, gap-analyst, document-writer), 16 scripts, 10 commands, and hooks for automatic state updates. Use when developing requirements, formalizing needs, writing specifications, building traceability, analyzing coverage gaps, managing assumptions, or preparing for systems engineering reviews.
Claude Code1 skill - rcca-master1stars
Orchestrate complete Root Cause and Corrective Action (RCCA) investigations using the 8D methodology. Guides team formation (D1) with domain-specific recommendations, problem definition (D2), containment (D3), root cause analysis (D4) with integrated tool selection (5 Whys, Fishbone, Pareto, Kepner-Tregoe, FTA), corrective action (D5-D6), prevention (D7), and closure (D8). Use when conducting RCCA, 8D, root cause analysis, corrective action, failure investigation, nonconformance analysis, quality problems, or customer complaints.
Claude Code1 skill - problem-definition1stars
Guide RCCA/8D problem definition using 5W2H and IS/IS NOT analysis. Transforms scattered failure data into precise, measurable problem statements that bound investigation scope without embedding cause or solution. Use when defining problems for root cause analysis, writing D2 sections of 8D reports, analyzing nonconformances, investigating failures, or when user mentions problem definition, problem statement, RCCA, 8D, failure analysis, or corrective action.
Claude Code1 skill - plugin-creator1stars
Automatically generate Claude plugins from user prompts. Supports plugin creation, documentation, and testing. Use when needing to create a new plugin or when user mentions "plugin", "Claude plugin", "plugin creation", or "plugin development".
Claude Code1 skill - pareto-analysis1stars
Conduct Pareto Analysis (80/20 Rule) to identify the vital few causes driving the majority of problems. Guides data collection, category definition, chart creation, cumulative percentage calculation, and prioritization. Generates professional Pareto charts (SVG) and HTML reports with quality scoring. Use when prioritizing defects, complaints, failures, or improvement opportunities; when user mentions "Pareto", "80/20 rule", "vital few", "trivial many", "prioritization", or needs to identify which factors contribute most to a problem.
Claude Code1 skill - kepner-tregoe-analysis1stars
Conduct Kepner-Tregoe (KT) Problem Solving and Decision Making (PSDM) analysis using the four rational processes - Situation Appraisal, Problem Analysis, Decision Analysis, and Potential Problem Analysis. Use when performing structured root cause analysis, making complex decisions, evaluating alternatives with weighted criteria, conducting IS/IS NOT specification analysis, anticipating implementation risks, troubleshooting complex issues, or when user mentions "Kepner-Tregoe", "KT method", "IS/IS NOT", "situation appraisal", "decision analysis", "MUSTS and WANTS", "potential problem analysis", or needs systematic problem-solving methodology. Includes specification matrices, decision scoring, quality rubrics, and professional report generation.
Claude Code1 skill - fmea-analysis1stars
Conduct Failure Mode and Effects Analysis (FMEA) for systematic identification and risk assessment of potential failures in designs, processes, or systems. Supports DFMEA (Design), PFMEA (Process), and FMEA-MSR (Monitoring & System Response). Uses AIAG-VDA 7-step methodology with Action Priority (AP) risk assessment replacing traditional RPN. Use when analyzing product designs for potential failures, evaluating manufacturing process risks, conducting proactive risk assessment, preparing for APQP/PPAP submissions, investigating field failures, or when user mentions "FMEA", "failure mode", "DFMEA", "PFMEA", "severity occurrence detection", "RPN", "Action Priority", "design risk analysis", or needs to identify and prioritize potential failure modes with their causes and effects.
Claude Code1 skill - five-whys-analysis1stars
Conduct rigorous 5 Whys root cause analysis with guided questioning, quality scoring, and professional report generation. Use when performing root cause analysis, investigating problems, conducting 5 Whys sessions, troubleshooting recurring issues, or when user mentions "5 whys", "root cause", "why did this happen", "find the cause", or needs to identify underlying causes of defects, failures, or process problems. Includes validation tests, scoring rubric, and countermeasure development.
Claude Code1 skill - fishbone-diagram1stars
Create comprehensive Fishbone (Ishikawa/Cause-and-Effect) diagrams for structured root cause brainstorming. Guides teams through problem definition, category selection (6Ms, 8Ps, 4Ss, or custom), cause identification, sub-cause drilling, prioritization via multi-voting, and 5 Whys integration. Generates visual SVG diagrams and professional HTML reports. Use when brainstorming potential causes, conducting root cause analysis, facilitating quality improvement sessions, analyzing defects or failures, structuring team problem-solving, or when user mentions "fishbone", "Ishikawa", "cause and effect diagram", "6Ms", "cause analysis", or "brainstorming causes".
Claude Code1 skill - fault-tree-analysis1stars
Conduct Fault Tree Analysis (FTA) to systematically identify and analyze causes of system failures using Boolean logic gates. Top-down deductive method for safety and reliability engineering. Use when analyzing system failures, evaluating safety-critical designs, calculating failure probabilities, identifying minimal cut sets, assessing redundancy effectiveness, or when user mentions "fault tree", "FTA", "system failure analysis", "minimal cut sets", "safety analysis", "failure probability", "AND/OR gates", or needs to trace failure pathways from top event to basic events. Supports qualitative structure analysis and quantitative probability calculations.
Claude Code1 skill - documentation-architect1stars
Transform documentation using the Diátaxis framework
Claude Code1 skill - concept-dev1stars
Walk through the NASA Phase A concept development lifecycle: ideation, problem definition, black-box architecture, drill-down with gap analysis, and document generation. Produces concept documents and solution landscape summaries with cited research. Includes 7 specialized agents (ideation, problem analysis, architecture, domain research, gap analysis, skeptic verification, document writing), 6 scripts (session management, source/assumption tracking, web research with crawl4ai), 9 commands, hooks for automatic state updates, and tiered research tool detection. Use when developing a concept, exploring a new idea, brainstorming a system concept, running Phase A, creating a concept document, or conducting feasibility studies.
Claude Code1 skill - harborview-qa0stars
Readiness triage, story maturing, and exploratory test charters for the Harborview delivery team. Teaching plugin for the Beekeeper Lab series Out of the Tab.
Claude Code3 skills - compass0stars
AI-guided development workflow with per-project Obsidian-compatible knowledge vaults. Provides structured spec → research → plan → build → test → validate methodology. Run /compass:setup to set up a project.
Claude Code33 skills - portolan0stars
Long-horizon task management for Claude Code — intake alignment, automated orchestration, independent verification
Claude Code4 skills - captain-memo3stars
Cross-AI local memory layer (Claude Code, Codex, Gemini, Cursor) — hybrid search, three summarizer providers, self-hosted embedder. Replaces claude-mem.
Claude Code5 skills1 MCP server - trelio-agent-workspaces1stars
Production integration for private Trelio meetings and regular work, guided setup diagnostics, working-folder onboarding, guarded project and private-skill management, scoped Agent Workspaces, Agent Secrets, live skill catalogs, declarative Remote MCP, and backend-managed signed runtimes.
CodexClaude Code6 skills2 MCP servers - document-rag0stars
Document Intelligence & Hybrid Retrieval MCP: multi-format extraction, structural validation, DuckDB SQL queries, and Qdrant semantic search.
Agent Plugins1 MCP server - technical-writer17stars
House-style technical writing: a core style and truth skill plus specialized skills for design docs, decisions, changelogs, runbooks, tracker issues, and prose review
CodexClaude Code11 skills - level7-dev-loop0stars
One-intent solo development: inspect, implement, test, repair, self-review, and hand off with optional team assurance.
CodexClaude Code12 skills - auto-agent-team0stars
Coordinate native Codex subagents and show DSH-style team state, tasks, dependencies, verification, and review in a live dashboard.
Codex1 MCP server - arxiv-paper-zh1stars
Verify and translate arXiv papers into compilable Chinese editions with paired English and Chinese PDFs.
Codex1 skill - disciplined-coder0stars
Team engineering discipline (SSOT principles) + per-domain design references + runtime LLM verification reviewers + spec/plan & doc review gates, for Codex. Mirrors the Claude Code plugin via shared skills and hook logic.
CodexClaude Code13 skills - codex-master0stars
The Hive plugin for controlling a sleeping Agentinnen fleet through a data-sparse local MCP server. codex-master-mcp and Masterjet remain compatibility aliases.
Codex1 skill1 MCP server - skill-hoonsoo0stars
Read-only live context and grammar review for local documents.
CodexClaude Code1 skill1 MCP server - hoonsoo0stars
Real-time, advice-only document review for human-in-the-loop LLM sessions.
Agent Plugins - skill-hoonsoo0stars
Read-only live context and grammar review for local documents.
CodexClaude Code1 skill1 MCP server - e-comet-skills0stars
MCP tools for e-Comet seller analytics, live Wildberries data, Ozon Seller promotion reports, and explicit-consent issue reporting.
CodexClaude Code1 MCP server - engram0stars
Persistent memory with canonical root-turn checkpoint activation and Stop verification for Codex.
Codex1 MCP server - engram0stars
Persistent memory for AI coding agents. Survives across sessions and compactions.
Claude Code1 MCP server - tend-ci-runner39stars
Tend's internal CI skills — reviews PRs, triages issues, fixes CI, sweeps repos for improvements. Loaded by tend's GitHub Action; not for general manual use.
CodexClaude Code22 skills - install-tend39stars
Set up and diagnose Tend, an autonomous junior maintainer for GitHub repositories.
CodexClaude Code2 skills - vouchington-workflow0stars
Portable implementation, dependency automation, planning, publishing, issue, retrospective, event-driven CI, stacked-PR, and PR workflow skills for Codex and Claude.
CodexClaude CodeAgent Plugins19 skills - vouchington-testing0stars
Portable testing guidance for common runners and application stacks.
CodexClaude CodeAgent Plugins8 skills - vouchington-database0stars
Portable PostgreSQL schema and performance guidance.
CodexClaude CodeAgent Plugins2 skills - security-triage0stars
Repository-neutral Codex Security finding triage.
CodexClaude CodeAgent Plugins1 skill - vwf1stars
Highly opinionated Product → Blueprint → Plan → Execute workflow for solo developers or small teams — enforced workspace structure with a selectable stack-template menu checked by /vwf:doctor, a flow-first blueprint (entities as data contracts, OpenAPI + JSON-Schema artifacts) with whole-product coherence review, chained dependency plans, an autonomous execute with review/security/acceptance/UX subagents behind one final merge gate that stamps blueprint implementation state, post-deploy verify with production release freezing + API backward-compat enforcement, feedback intake, and mempalace-backed memory.
Claude Code28 skills2 MCP servers - typescript1stars
The TypeScript language plugin — one plugin per toolchain, this one owning the Node/TS ecosystem and so covering both `typescript` and `javascript`. A `typescript` router skill (lean SKILL.md routing to on-demand references: the coding standards baseline, Vitest testing, the build pipeline for single-package and monorepo) plus an `effect` router skill for Effect-TS doctrine, `package-json`, `pnpm`, `tsconfig`, `lint-format`, and the TypeScript/JavaScript language server. Its stack adapter retired in Wave C: all twelve TypeScript templates are stackgen bundles now, so this plugin offers no menu.
Claude Code6 skills - stackgen1stars
The principles-driven stack materializer — implements the vwf stack-adapter contract with a dispatch rule: a technology a shipped pack covers is copied from the pack; anything uncovered is generated (Context7 research → vwf's principles catalog → the stackgen-skill-reviewer gate). Both paths land directly in the repo's committed .claude/ tree — skills, agents, hooks and rules only, structured per a closed kind vocabulary, recorded in a lockfile — editable and plugin-independent for collaborators. Re-sync is explicit and diffed, never silent. Waves A–C landed 21 packs and 19 bundles across seven kinds; Wave D adds the eighth kind, deploy-target, whose container-image pack is the curated answer the container-generic bundle used to generate, assets/artifact-doctrine.md — the host rules deciding whether a generated skill, agent or hook is valid at all — and the ninth kind, design-tool, whose three packs land vwf's design adapters at fixed names in the repo's own .claude/. Two tool axes (design, cicd) let a pack be reached by the config token that selects it, which is what rescued a CI pack no menu could offer. The secrets-manager category then landed on the backing axis behind assets/contracts/secrets.md, where the whole decision is where the secret lives and what onboarding a teammate costs — and where devtools' Doppler doctrine went.
Claude Code3 skills - gcp1stars
Google Cloud stack plugin for vwf — the judgment layer an SDK reference cannot give you: which service to pick and when it stops being the answer, how each one bills and the traps that multiply it, which services have local emulators (and where they lie), and least-privilege IAM shapes. Covers the full Firebase suite plus Cloud SQL, AlloyDB, Memorystore, Bigtable, BigQuery, Pub/Sub, Cloud Tasks, Scheduler, Eventarc, Workflows, Cloud Storage, Cloud Run, GKE, Artifact Registry, Cloud Deploy, Cloud Armor, VPC, DNS, Load Balancing, CDN, KMS, Backup & DR, reCAPTCHA Enterprise and Vertex AI. Observability is OpenTelemetry only — GCP services appear as OTLP sinks, never as vendor SDKs. Implements the vwf stack-adapter contract.
Claude Code5 skills - flutter1stars
Opinionated Flutter plugin — a `dart` router skill (lean SKILL.md routing to on-demand references: GetX, a Firebase suite of auth/analytics/app-check/crashlytics/messaging/storage, and feature areas of architecture, state, navigation, theming, layouts, animations, performance, maps, webview, webrtc, revenuecat, image handling, http/json, concurrency, caching, testing, flavors, app-size, coverage, build) and a `swift` router skill (Swift, SwiftUI, Xcode), plus `kotlin`, `pubspec`, `analysis-options`, and `internationalization`, and bundled Dart, Kotlin & Swift (SourceKit) language servers. Its stack adapter retired in Wave C — `dart-flutter` is a stackgen bundle now, and the app-framework pack carries the Dart/Kotlin/Swift judgment. Self-contained — no cross-marketplace dependencies.
Claude Code6 skills