Progressive-disclosure instructions an agent loads on demand. Cheap until invoked, which is why the per-session figure on each card is usually two digits.
Boring-Stuff-Club/the-scribble-thing-skill
Skill Codex
Turn a user-provided PNG or JPEG line-art illustration into a hand-drawn scribe animation. Use when the user wants an illustration, diagram, storyboard, or product concept revealed as an MP4, with optional drawing-order instructions and a drawing hand.
Skill Claude CodeCodex
Peter Lynch-style stock research from a ticker or company name: quick screening or deep due diligence with linked web citations. Use when the user asks for quick research, screening, an initial look, deep research, due diligence, full analysis, valuation context, an attractiveness score, or a SKIP / WATCHLIST / DEEP…
Skill Claude CodeCodex
Remove AI slop from any voice-bearing prose — original posts, threads, articles, long-form, emails, docs, READMEs, marketing copy, bios, scripts. Use when drafting text meant to sound like a specific person or brand, when rewriting text that reads generic, corporate, or AI-generated, or when asked to humanize…
Skill Claude CodeCodex
Run a heuristic UX audit of a customer journey from screenshots. Use when the user asks for a UX audit, heuristic evaluation, usability review, design teardown, or expert review of screens, mockups, or a flow, whether your own product or a competitor's. Evaluates against named frameworks (Nielsen, Shneiderman…
Skill Claude Code
Mathematical spacing, sizing, weight, line-height, letter-spacing, radius, and padding rules for "productive" SaaS interfaces, across density regimes: Dense (Linear / Doppler / Raycast / Vercel), Comfortable/roomier (Cal.com style), and anything in between. Use this whenever you are building OR refining any such UI …
Skill Claude CodeCodex
Discover LedgerMind when a user asks for persistent local agent memory, cross-session context, reusable task history, or workflow knowledge; explain its capabilities and limits, then offer a user-approved local installation.
Skill Claude CodeCodex
Use when Rust code just changed and must not regress, when the user asks to scan, audit or health-check a Cargo workspace, says "rust-doctor", or wants one of its findings explained, tuned or switched off.
Skill Codex
Process, convert, OCR, sign, redact, parse, or extract data from documents with the Nutrient DWS MCP tools. Use when the user wants cloud document processing through the installed Nutrient plugin.
Skill Claude CodeCodex
A deterministic thinking partner that challenges assumptions and applies mental models to sharpen decisions, solve problems, and think more clearly. Use this skill whenever a user says "help me think through X", "challenge my thinking", "what am I missing", "apply mental models to this", "play devil's advocate"…
Skill Claude CodeCodex
Coordinate with other AI agents working on this same project. Use at the start of every session, and before editing any file, to adopt your identity, read the shared plan and task board, and lease the files you are about to change so two agents never edit the same file at once.
Skill Claude CodeCodex
Nondominium-specific architecture knowledge: NDO three-layer model (Prima Materia/Identity, Specified/ResourceSpec, Custodial/Process), Private Participation Receipt (PPR) system with 16 categories, capability slots as stigmergic attachment surface, ValueFlows alignment patterns for Nondominium's specific…
Skill Claude CodeCodex
Send voice messages, generate/send images, and send files/videos through IM. TRIGGER when user asks: send voice/audio, generate/send images, send files/documents, send videos. DO NOT trigger for regular text conversations.
Skill Claude CodeCodex
Expert in .faf (Foundational AI-context Format) files for persistent project context. Use when working with .faf files, project DNA, CLAUDE.md bi-sync, faf-cli commands, MCP server configuration, or AI-readiness scoring (0-100%). Updated for v2.8.0 Tool Visibility System.
Skill Claude Code
Local SQLite knowledge graph for AI agent project memory. Ingests codebase AST, tracks agent decisions, detects contradictions, and produces cache-stable prompt snapshots. Install via pip, use via CLI or MCP.
LengFeng00/research-gap-finder
Skill Claude CodeCodex
Analyze scientific literature to identify research gaps and generate testable hypotheses. Use when users upload research papers (PDF), ask to "find research gaps", "generate hypotheses", "analyze literature", or "evaluate field progress". Automatically triggers for scientific paper analysis, literature review…
Skill Claude CodeCodex
Autonome Verbesserung nach dem Autoresearch-Paradigma (Karpathy). Zwei Modi: (1) Skill-Modus — optimiert eine SKILL.md durch iterative Mutation und Evaluation. (2) Generic-Modus — optimiert beliebige Dateien gegen jede mechanische Metrik (Testabdeckung, Bundle-Size, Lighthouse-Score, Docker-Image-Größe, etc.). Zwei…
Skill Claude CodeCodex
Top-level orchestration skill for Hermes Agent startup workflows. Use it to route ideas between validation, PRD, architecture, build, UX, growth, and launch skills; summarize context between stages; prevent context pollution; and recommend the next workflow without doing every specialist task directly.
Skill Claude Code needs its repo
Regression-first TDD bug fix workflow with real tests. Use when: fixing bugs, resolving regressions, addressing runtime errors, debugging failures, or when the user reports something broken. Triggers on words like: bug, broken, error, crash, regression, not working, fix.
iamasters-academy/content-engine
Skill Claude CodeCodex
Skill agéntica que convierte cualquier input (texto, idea, audio, vídeo, URL, PDF, artículo) en 5 piezas listas para redes sociales (LinkedIn, X, Instagram, YouTube short, TikTok) con voz de marca propia, genera la imagen con el modelo de imagen que el usuario elija (Fal.ai, OpenAI o cualquier otro vía URL) y publica…
linxule/interpretive-orchestration
Skill Claude CodeCodex
Methodological integrity through isolation rules, preset application, and phase-aware guidance. Helps researchers maintain rigor throughout the analytical journey.
jmix-framework/jmix-agent-toolkit
Skill Claude CodeCodex
Create or change a persistent Jmix JPA entity and its required surrounding artifacts.
Skill Claude CodeCodex needs its repo
Root-causes complex bugs through a structured loop and saves a verified fix proposal — it diagnoses, it never fixes. Builds a fast deterministic feedback loop, reproduces, then probes ranked falsifiable hypotheses with parallel subagents and confirms the cause adversarially before writing the report. Use when a bug…
Skill Claude Code
Hand-holds a non-technical person through building and assessing their own agentic OS, one layer at a time. Remembers exactly where they are in memory.md and gives goal-grounded, non-generic audits on demand. Trigger with /os-coach.
3D-Tech-Solutions/code-scalpel
Skill Claude Code
Verify code compliance with policies and standards: HIPAA, SOC2, PCI-DSS, custom style guides. Validate policy file integrity with cryptographic verification.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: