9,876 tagged LLM, measured the same way as everything else here.
Browse within: agent 502chatgpt 227agents 211cli 169ml 133bun 129javascript 124agentic-ai 122openai 118agent-framework 116deep-learning 107foundation-models 98agentskills 90cortex 90
Skill Claude CodeCodex
Repo-local Sage eval-gauge / hill-climbing Phase-0 toolkit. Use when an operator, Claude Code, or Codex needs to measure Sage capability with a GROUND-TRUTHED gauge (not substring eval scores), run the Gate Experiment (does the eval track reality?), compare bare-model vs harness, get the noise floor /…
Skill Claude CodeCodex
Hmem write protocol — picks prefix (L/E/D/P/N/R/I/H…), tree location, and tags, and detects duplicates before persisting. Use before any writememory or appendmemory call (skipping it creates duplicates and misplaced entries), or when the user says 'remember this', 'save this', 'log this', or invokes /hmem-write.
Skill Codex
Use when calling any OneTool pack tool via onetool/ot triggers or the MCP run tool — pack map with aliases, call syntax, kwarg-prefix and alias forgiveness, discovery, a greppable index of every command, recovery from disconnected servers, and large-result handling.
Skill Claude CodeCodex
This skill should be used when the user asks to "debug without print", "debug", "observe running code", "add metric", "inspect variables at runtime", "see what a variable is", or mentions "detrix", "agent mode", "eBPF", "logpoint", "dynamic metrics", "debugpy", "observe code". Debugger for agents.
cnkang/nginx-markdown-for-agents
Skill Codex
Route and validate harness maintenance work for nginx-markdown-for-agents. Use when changing AGENTS.md, docs/harness, tools/harness, Makefile, or CI harness wiring. Also use it when you need spec resolution, risk-pack routing, or phased verification commands.
Skill Claude CodeCodex
Comprehensive Zephyr I2C subsystem expertise for Inter-Integrated Circuit bus communication. Use when: (1) Configuring I2C controllers or devices via devicetree or Kconfig, (2) Implementing synchronous I2C transfers with i2ctransfer/i2cread/i2cwrite, (3) Using register access helpers like…
Skill Claude Code
Harvest real, citable achievements from the user's git history, PRs, and work documents, and turn the confirmed ones into STAR stories. Use when the user wants to mine their repos or work artifacts for accomplishments, can't remember what they achieved, or wants to build their story bank from evidence instead of…
Skill Claude CodeCodex
How to use Memento — a local-first MCP memory layer for AI assistants — to remember and recall durable knowledge about the user, their preferences, conventions, decisions, and projects across sessions. Trigger this skill whenever the user has Memento connected and any of the following happens, even when the user does…
openitu/itu-t-recommendation-reviewer
Skill Claude CodeCodex
Review draft ITU-T Recommendations (and ITU-T | ISO/IEC common texts) for compliance with the ITU-T Author's Guide, presentation rules, and quality checklist before submission for consent/determination/approval. Use this skill whenever the user asks to review, check, audit, proofread, or improve a draft ITU-T…
Skill Claude CodeCodex
A Russian-language guide for MemoHood, a conversation-memory plugin with tools for searching, recalling, capturing, pinning, and managing remembered facts.
Skill Codex
Use for Ariadne MCP-backed Kubernetes state questions: translate operational questions into Cypher, repair graphquery failures, and decide when graphschema or graphhealth is needed. Best for live or snapshot-backed graph data about resource relationships; do not use for codebase-only tasks or generic Kubernetes…
Skill Claude CodeCodex
This skill should be used when the user asks to "test my specs", "validate my design docs", "find gaps in my architecture", "stress-test the spec", "vibe test", "pressure test the docs", or mentions spec validation before implementation begins.
Skill Claude CodeCodex
Confirm or refute a vulnerability candidate against a live target with a deterministic probe, respecting authorization and scope. Use when a SAST or LLM review flags a possible injection or SSRF, when triaging a finding before filing a bug or shipping a fix, or when a verification result turns out wrong.
Skill Claude CodeCodex
Use when working on the Hecate operator UI in ui/. Keeps frontend work aligned with Hecate's operator-console workflows, runtime-debugging focus, and React/Vite stack.
Skill Claude CodeCodex
Create low-fidelity, text-based wireframes using the Markdown-UI Domain Specific Language (DSL).
Skill Claude CodeCodex
Use when drafting a post-event follow-up message to someone met at a conference.
Skill Claude CodeCodex
This skill should be used when the user asks for a code review of a change — a pull request, merge request, branch, commit range, working-tree change, or pasted diff — covering correctness, security, performance, structure, and repository-specific rules. Trigger on phrases like "review this PR", "review this MR"…
Skill Claude CodeCodex
A Russian-language skill for searching a local knowledge base built from documents and other sources such as web pages, YouTube, audio, and Obsidian notes.
Skill Claude CodeCodex
Delegate tasks to other agents in the team by creating real PaperClip child issues. Covers single-agent delegation and multi-agent coordination, with failure handling and idempotency. Trigger phrases: any task outside your direct capabilities (email/calendar/drive) that should be routed to Coder, Infrastructure…
Skill Claude Code
An English-to-Chinese translation and polishing guide. It produces natural Chinese translations, and can also provide English and Chinese text side by side.
Skill Claude CodeCodex
Use when the user asks to scan a repo for AI/LLM security issues, wants to know "is this skill safe?" before installing an Agent Skill, needs to "scan my MCP config" or check an MCP server before trusting it, asks about prompt injection / tool poisoning / RAG poisoning risk in their code, or is about to install any…
Skill Claude CodeCodex
Access the persistent memory database (PostgreSQL claudememory) for long-term context across Claude Code sessions. Triggers on "what do I know about", "memory lookup", "recall", "memory db", "what did we decide about", "similar conversations", "lookup context", "/memory". Provides semantic search, SQL queries and the…
Skill Claude CodeCodex needs its repo
Analyze authorized video content from a local video file, a public direct HTTP(S) video URL, or—with --allow-platform—a single public video on a platform page (e.g. Bilibili/YouTube watch links, fetched via yt-dlp without login or cookies). Use this skill whenever the user asks to read, understand, summarize…
xaviviro/Opendata.cat-MCP-Server
Skill Claude CodeCodex
Useu quan calgui respondre una pregunta amb dades obertes catalanes (15 portals — Generalitat, Barcelona, Diba, AOC, Reus, Girona, FGC, Idescat, Renfe, INE, REE, CNMC, CORA, Catalònica) amb les eines del servidor MCP opendata.cat (searchdatasets, getdatasetinfo, listdatasetfields, querydataset, relateddatasets).…
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: