llm-tools skills

479 tagged llm-tools, measured the same way as everything else here.

Browse within: ai-coding 175api-integrations 163event-driven 163github-webhooks 163mcp-server 159agent 90bioinformatics 80LLM 64claude-plugins 62claude-code-plugin 52ai-tools 51agents 48skills 46agent-harness 44

phoenix-intent

49

All-The-Vibes/ATV-Phoenix

Skill Claude CodeCodex

Decompose a high-level vague intent into N concrete /goal instances (≤5), each with its own phoenixsense acceptance check, proven complete via composite phoenixaccept (all N sawred AND greenafterred AND currentlygreen). Use when a task is multi-faceted (build + integrate + configure + notify) with independent or…

not rated 5 5d ago A 119 tokens original MIT

live-audit

50

Grinv/steam-games-mcp

Skill Claude CodeCodex

Audit steam-games-mcp — build/test/lint gate, live MCP tool edge-case sweep (input validation, SteamID64/vanity/appid edge cases, key-gating), and source-level code review. Use when asked to test/audit the published or just-fixed steam-games-mcp package, hunt for bugs/edge cases, or repeat "the same kind of testing as…

not rated 4 16d ago A 83 tokens original MIT

musicbrainz

51

SteveGrosbois/tidal-cli

Skill Claude CodeCodex

Interroge l'API publique MusicBrainz pour récupérer des métadonnées musicales fiables : recherche d'artistes, discographies complètes (release-groups : albums, EPs, singles, lives, compilations), détails de releases (labels, formats, dates, pays), recordings, œuvres, relations entre entités (membres de groupe…

not rated 4 1mo ago A 177 tokens

WinterDDo/paul-graham-skills

Skill Claude CodeCodex

Apply when an attempt at a task has failed, when Claude is debugging, when a previous answer did not work, when iterating on a solution that is not converging, or when the user reports that the last response missed the mark. Critical trigger: any moment where the temptation is to retry the same approach with cosmetic…

not rated 4 4mo ago A 93 tokens

nesift

53

scottgl9/nesift

Skill Claude CodeCodex

Token-efficient web research for AI agents. Fetches, indexes, and queries web content locally via hybrid BM25 + embeddings, returning only the chunks that fit a token budget. Replaces raw webfetch for any task involving more than one source. Use when the user asks you to research, compare, summarize, or fact-check…

not rated 4 3mo ago A 83 tokens GPL-2.0

steam

54

Sarg338/steam-mcp

Skill Claude CodeCodex

Query Steam for a user's library, playtime, achievements, friends, groups, and inventory, plus any game's store details, reviews, community tags, prices, sales, and live player counts — and higher-level help like game recommendations, "is this worth buying", and planning a co-op night. Read-only, bring-your-own-key.…

not rated 4 +1 1mo ago A 102 tokens

deep-research

56

B143KC47/deep-research-skill

Skill Codex

Use when the answer needs verified evidence across multiple sources - deep research, literature review, paper review, GitHub/project due diligence, claim verification, fact-checking, current or version-sensitive information, counterevidence search, cited reports, or checking local files against the web. Do not use for…

not rated 2 2mo ago A 83 tokens original MIT

gleanin

57

pcx-wave/glean

Skill Claude CodeCodex

Rules distilled from past session friction (errors, edit loops, corrections), analyzed by a stronger model and applied to guide future work. Regenerated from glean/artifacts/ plus an index of trigger-loaded protocols from GLEANPROTOCOLDIRS by sync.sh — load every session via CLAUDE.md.

not rated 2 1mo ago A 62 tokens original MIT

prd-decomposer

58

Sixz-AI/prd-workflow

Skill Claude CodeCodex needs its repo

Triggers when: user mentions "PRD", "requirements", "break down requirements", "split PRD", or provides a long feature document. Use this skill to first clarify ambiguous requirements, confirm business logic and boundaries, and then decompose the finalized PRD into atomic frontend tasks focusing purely on BUSINESS…

not rated 2 4mo ago A 71 tokens original MIT

toolcapsule

59

RainSunMe/toolcapsule

Skill Claude Code

Use when: turning MCP servers into lazy Agent Skills, calling MCP tools with inline JSON or local files, or looking up MCP tool schemas on demand.

not rated 2 11d ago A 34 tokens original MIT

crudcraft

60

GitRavz/CRUDcraft

Skill Claude CodeCodex

Use when building or editing a small database-backed web app in ANY stack — plain PHP, Laravel, or Supabase, on MySQL/MariaDB, PostgreSQL, SQLite, SQL Server, or a hosted DB — scaffolding a project, creating or evolving a database, designing tables or writing SQL, adding login/registration or user roles, building a…

not rated 2 1mo ago A 174 tokens original MIT

axiom-math

61

tufantunc/axiom-advanced-math-mcp

Skill Claude CodeCodex

Use when a task needs mathematics that must be exact rather than estimated — symbolic integration or differentiation, solving equations, factoring, limits, series, matrix algebra, combinatorics, or checking whether a mathematical claim is actually true. Runs a computer algebra system (Giac/Xcas) locally via a CLI, so…

not rated 2 yesterday A 74 tokens GPL-3.0

pgautopilot

62

cyberreinxy/pgautopilot

Skill Claude CodeCodex

Use this skill for ANY PostgreSQL database work through the PGAutoPilot MCP server. Trigger when user asks to: - Explore, query, or manage a PostgreSQL database - Design schemas, tables, or data models for Postgres - Write, optimize, or debug SQL queries - Check database health, performance, or connectivity - Insert…

not rated 2 6d ago A 142 tokens

lyrenth-web-reading

63

lyrenth/lyrenth-mcp

Skill Claude CodeCodex

Read the content of one or many public web pages through Lyrenth, as clean Markdown instead of raw HTML. Use when the user gives a URL to read, summarize, quote, compare or extract from, or when a link needs to be opened to answer a question.

not rated 1 13d ago A 61 tokens original MIT

news

64

CKBrennan/overtone-news-mcp

Skill Claude CodeCodex

Overtone intelligence toolkit. Retrieves contextually analyzed news AND answers emotional/narrative questions across coverage: tone distribution, anger/sadness/fear spike alerts for a topic (pollable), emerging under-reported concepts, topics whose dominant tone is shifting fastest, and hourly/daily tone timeseries…

not rated 1 4mo ago B 98 tokens original MIT

codex-goal-handoff

65

cskwork/codex-goal-handoff

Skill Claude CodeCodex

Prepare a durable specification and handoff for a bounded engineering workflow the user wants Codex to pursue as a persistent goal. Use for Codex goal delegation, not ordinary long-running work or a request merely to save session state.

not rated 1 changed yesterday A 52 tokens original MIT

kleap

66

kleaphq/cli

Skill Claude CodeCodex

Build, edit and publish real websites with Kleap from inside this agent, via the Kleap MCP server. Use when the user wants to create a website or web app, change a site they made on Kleap, connect a domain, or take a site live — especially when they want it actually hosted and online, not just code. Kleap provides the…

not rated 1 1mo ago A 88 tokens original MIT

zig-docs-mcp

67

gbrlpzz/zig-docs-mcp

Skill Claude CodeCodex

Connect Prime Agent to the local zig-docs-mcp MCP server for always-fresh official Zig documentation of the latest release, std-library symbol docs from released sources, curated high-performance lightweight-software guidance, and safe local Zig toolchain auto-update prompts. Use when writing, reviewing, or debugging…

not rated 1 19d ago A 79 tokens original MIT

aisenseapi/aisense-free-public-rest-apis

Skill Claude CodeCodex

Use this skill whenever the user wants to integrate with, call, test, or learn about the free public REST APIs from AI SENSE AS (aisenseapi.com). Triggers include: requests for current time/datetime/timestamp, random numbers, random colors, passwords, UUIDs, GUIDs, Base64/Base58/Base32 encoding or decoding, JWT…

not rated 0 changed yesterday A 294 tokens original MIT

pikasim

71

codebruinc/pikasim-mcp

Skill Claude CodeCodex

Buy mobile connectivity from PikaSim — anonymous eSIM data plans in 190+ countries (from $0.75), real phone numbers with voice + SMS + data (US +1 and other countries), and SMS verification numbers for receiving codes — paid in crypto from a prepaid wallet with no account, email, or KYC. An agent can fully…

not rated 0 1mo ago A 199 tokens original MIT

youtube-transcripts

72

haljishi/vidwords-mcp

Skill Claude CodeCodex

Read and search YouTube videos through VidWords. Use when the user supplies a YouTube URL, a bare 11-character video id, a youtu.be or Shorts link, or a channel handle, and wants any of: the transcript or subtitles (TXT/SRT/VTT), what a video says about a topic, a quote with a citable timestamp, only the words spoken…

not rated 0 18d ago A 111 tokens original MIT

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: