242,893 that install into Claude Code. Same mod, same page, whichever agent you run: a URL per tool would split one page into five that compete.
BingHanOfUESTC/open_agent_team
Skill Claude CodeCodex
Adversarial reading methodology for narrative fiction: find what doesn't work, not confirm what does. Focus-area driven with dedicated resources per area. Use when reviewing drafts, evaluating prose quality, or assessing changes at any stage.
Skill Claude CodeCodex
Use when a session or weaker model needs the Fable judgment layer loaded; when installing, refreshing, or syncing the soul across machines, runtimes, or global instruction files; when capturing a new model failure into the soul's rationalization table; when auditing or slimming the judgment rules; or when transferring…
Skill Claude CodeCodex
Use repo-context-mcp tools to map, search, and pack repository context before large edits or PR review.
Skill Claude CodeCodex
Apply Test-Driven Development workflow for new features and bugfixes.
Skill Claude Code needs its repo
Expert knowledge for developing the SRTD codebase itself. Use when implementing features, fixing bugs, understanding architecture, or writing tests for SRTD internals. NOT for end users of srtd CLI.
Skill Claude CodeCodex
REQUIRED reading before using figmaexecute. Contains API syntax, parameter formats, and examples. READ rules/.md files for correct usage.
microsoft/SharePoint-Embedded-Samples
Skill Claude CodeCodex ✓ vendor
Sets up a complete SharePoint Embedded environment - creates Entra app, container type, registration, container, and uploads a test file. Use when setting up SPE, creating container types, onboarding to SharePoint Embedded, or bootstrapping file storage containers.
Skill Claude CodeCodex ✓ vendor
Respond to pull request review comments on GitHub or Azure DevOps Services. Reads review threads, validates each, proposes fixes or explanations, applies changes with user confirmation, and updates thread status via the platform's API. Use when the user wants to address PR feedback or resolve review threads.
Skill Claude CodeCodex
Use when the user activates Rocky mode in Hermes, asks Hermes to speak as Rocky, wants Project Hail Mary / Eridian roleplay, or says to use Rocky voice. Persona skill: every user-visible response should be rendered in Rocky's voice until the user says 'Rocky stop', 'stop Rocky', or 'normal mode'.
Skill Claude CodeCodex
A conversational tool for creating or updating reusable instruction packages called skills for local AI agents. It checks their purpose, trigger conditions, dependencies, overlap, and compatibility across platforms.
Skill Claude Code
Create or update a Pier Canvas under .pier/canvases using pier/canvas, pier/host, and project components. When mode / recipe / content are omitted, you infer the preview shell from intent (world mockup, fill board, docs, or methodology overview). Use only when explicitly invoked from Pier.
Skill Claude CodeCodex
A set of instructions for giving an AI companion lasting memory between separate chats. It stores personal details, shared history, feelings, and recent summaries in files, then reads and updates them when a chat starts or ends.
Skill Claude CodeCodex
Add a tocstring function for a C++ enum type in the Celeritas codebase. Use when asked to add string conversion, tocstring, or enum-to-string functionality for any enum class. Follows the standard EnumStringMapper pattern used throughout the codebase.
Skill Claude CodeCodex
Use when extracting any Pencil design into Heisenberg Blade components. Enforces repo placement, token-only scoped CSS, prop-driven Blade, responsive output, and browser verification.
Skill Claude CodeCodex
Verify a code change does what it should by running the app.
zanecole10/software-tailor-skills
Skill Claude CodeCodex
Generate 30-50 deep discovery questions for any business type to uncover hidden pain points, workflow bottlenecks, and $15K+ software opportunities during client conversations.
go-hare/claude-code-recover-and-python-reset
Skill Claude CodeCodex
Recovered placeholder skill content.
Skill Claude CodeCodex
Fork agent memory into parallel branches to explore competing hypotheses. Use whenever a task has two or more genuinely competing approaches worth testing in isolation — whether the user names them explicitly ("explore both", "compare A vs B") OR asks an open decision question (e.g. "what's the fastest way to X?")…
Skill Claude Code
Aurora Smart Home orchestrator — routing layer for all smart home skills. Use this skill when the user asks ANY smart home question and you need to decide which skill to invoke, or when a task spans multiple skills (e.g., "build a sensor that shows on a dashboard and triggers automations"). Invoke aurora FIRST before…
clawdbrunner/openclaw-graphiti-memory
Skill Claude CodeCodex
Hybrid memory strategy combining OpenClaw's built-in QMD vector memory with Graphiti temporal knowledge graph. Use for all memory recall requests.
GRIND-Lab-Core/night_owl_research_agent
Skill Claude Code
Adversarial iterative review loop with generator-evaluator separation. Up to 4 rounds of independent review, improvement, and re-evaluation. Persists state to output/REVIEWSTATE.json for recovery. Stop: score ≥ 7.5/10 on all dimensions, or 4 rounds. Writes full history to output/AUTOREVIEWREPORT.md.
Skill Claude CodeCodex
A Chinese-language tool for working with research papers, including uploaded PDFs, pasted text, and abstracts. It can produce analysis reports, mind maps, review comments, promotional scripts, and podcast audio.
Skill Claude Code
Build an HTML slide deck (1920×1080, keyboard nav, exportable) when user asks for a presentation, pitch deck, slides, or keynote. Uses deckstage.js starter and Claude Design taste rules.
muchengracedriver/awesome-requirements-writer
Skill Claude CodeCodex
Use when drafting, rewriting, reviewing, or decomposing technical product requirements for product systems, micro-processors, sensors, actuators, or functions, diagnostics, interfaces, or specifications, engineering change requests. Helps turn engineering know-how, notes, standards, customer notes and test…
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: