Skills

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.

session

1297

axoviq-ai/synthadoc

Skill Claude CodeCodex

Extract conversation turns from AI session history files (.jsonl).

not rated 1.2k +29 yesterday A SkillSpector: warn 14 tokens AGPL-3.0

speckit-clarify

1298

Azure/GPT-RAG

Skill Claude Code ✓ vendor

Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.

not rated 1.2k +3 today A 34 tokens original MIT

benchmark

1299

soniqo/speech-swift

Skill Claude Code needs its repo

Run performance + quality benchmarks. ASR reports WER, RTF, process memory, and throughput across engines/variants. Arguments include asr, tts, vad, diarize, asr-quick.

not rated 1.2k +4 4d ago A SkillSpector: warn 0 tokens original Apache-2.0

talking-head-edit

1300

pireel/pireel

Skill Claude CodeCodex

Edit interviews, lessons, commentary, podcasts, and direct-to-camera recordings built around speech. Use it to remove dead air, filler words, false starts, repeated lines, and discarded retakes while preserving natural delivery and keeping captions aligned. When the user asks for visual enhancement, also use it for…

not rated 1.2k +21 changed 4d ago A SkillSpector: warn 79 tokens AGPL-3.0

chen0416ccc-cpu/codex-windows-fast-patch-skill

Skill Claude CodeCodex

Reapply and repair Windows Codex Desktop after Store upgrades, including custom provider models hidden by Statsig availablemodels filtering, the dependent blue-purple Power slider and its Ultra toggle, Fast Mode request/UI gates, locale i18n, plugin UI gates, Chrome/browseruse gates, Goal command gates, Windows…

not rated 1.2k +23 changed 3d ago A 153 tokens

short-drama

1302

0xsline/short-drama

Skill Claude CodeCodex

A writing workflow for creating a 50-to-100-episode short online drama in Chinese. It guides the work from story idea and characters through episode planning, drafting, review, and export.

not rated 1.2k +33 4mo ago A 0 tokens original MIT

fix-tests

1303

CopilotKit/OpenTag

Skill Claude CodeCodex

Fix failing tests in a GitHub repo or PR. Use when the brief skill is fix-tests or the user wants the named test command to exit 0.

not rated 1.2k +9 4d ago A SkillSpector: pass 35 tokens original MIT

openspec-aware-chorus

1304

Chorus-AIDLC/Chorus

Skill Claude CodeCodex

Opt-in OpenSpec-mode authoring for Chorus PM workflows on dsh. Runs inline three-check detection for the local openspec CLI, scaffolds openspec/changes/ / on disk, and mirrors Markdown files into Chorus document drafts via chorus mcp call --arg-file (package-local chorus-mcp-call.mjs wrapper as fallback). Required…

not rated 1.2k +4 changed 2d ago A SkillSpector: warn 109 tokens AGPL-3.0

Pika-Labs/Pika-Skills

Skill Claude CodeCodex

Join a Google Meet or Zoom call as a video meeting agent via PikaStreaming. Trigger: user drops a Google Meet or Zoom link, or asks to join a meeting.

not rated 1.2k 1mo ago A SkillSpector: pass 41 tokens original Apache-2.0

channels

1306

ModalityDance/PalmClaw

Skill Claude CodeCodex

Configure per-session remote channels (Telegram/Discord/Slack/Feishu/Email/WeCom), then verify inbound/outbound routing and processing visibility.

not rated 1.2k +1 14d ago A SkillSpector: pass 32 tokens AGPL-3.0

test-skill

1307

skillsgate/skillsgate

Skill Claude CodeCodex

A test skill for validation.

not rated 1.2k +12 19d ago A SkillSpector: pass 9 tokens original MIT

openclaw-plugin

1308

LycheeMem/LycheeMem

Skill Claude CodeCodex

This plugin is a thin adapter between OpenClaw and LycheeMem. It does not replace memory-core, does not claim plugins.slots.memory, and does not duplicate LycheeMem algorithms.

not rated 1.2k +4 1mo ago A SkillSpector: pass 0 tokens original Apache-2.0

btca-local

1309

davis7dotsh/better-context

Skill Claude CodeCodex

Invoke this skill when the user says "use btca".

not rated 1.2k +2 5mo ago A Socket: passSnyk: warn 16 tokens copy · 100% MIT

autogoal

1310

udecode/dotai

Skill Claude CodeCodex

Create, verify, repair, and close durable Codex goals with measurable outcomes, evidence gates, plan templates, blocker handling, completion audits, and goal-backed workflow repair.

not rated 1.2k +1 changed 5d ago A SkillSpector: warn 38 tokens

activity-monitor

1311

zylos-ai/zylos-core

Skill Claude Code

Guardian service that monitors the active runtime agent's state and automatically restarts it if stopped. Use when checking agent liveness state or understanding the auto-restart mechanism.

not rated 1.2k +1 yesterday A SkillSpector: warn 36 tokens original MIT

remotion-scene-anatomy

1312

RinDig/Interpretable-Context-Methodology

Skill Claude CodeCodex

Conventions for building a narrated Remotion video where the audio drives the timeline. Covers timing.ts, beat-local time, gap-fill sequences, and the end-card pattern.

not rated 1.2k +18 1mo ago A SkillSpector: pass 42 tokens original MIT

axiom-audit-camera

1313

CharlesWiltgen/Axiom

Skill Claude CodeCodex

Use this agent to scan Swift code for camera, video, and audio capture issues including deprecated APIs, missing interruption handlers, threading violations, and permission anti-patterns.

not rated 1.2k +5 3d ago A SkillSpector: warn 39 tokens original MIT

openpets

1314

alvinunreal/openpets

Skill Claude CodeCodex

Use when the user asks to install, configure, verify, troubleshoot, or understand OpenPets; install or select a pet; connect Claude Code, OpenCode, Cursor, Codex, or MCP clients; configure a project to use a specific pet; or debug openpetsstatus, openpetsreact, or openpetssay.

not rated 1.1k 11d ago A SkillSpector: warn 70 tokens original MIT

paper-analyzer

1315

zsyggg/paper-craft-skills

Skill Claude CodeCodex

An academic-paper analysis workflow. It requires getting the full paper text and searching for publicly available source code before completing the analysis.

not rated 1.1k +18 3mo ago A Socket: passSnyk: fail 56 tokens

kill-ai-slop

1317

yetone/kill-ai-slop

Skill Claude CodeCodex

Find and remove AI slop — the generic, machine-default visual and copy tics of vibe-coded products — from a web project. Use when the user asks to "kill AI slop", "de-slop", "remove the AI look", "make this not look AI-generated", or clean up a landing page / UI / docs that feels templated. Detects and fixes the…

not rated 1.1k +32 1mo ago A SkillSpector: pass 249 tokens original Apache-2.0

fizz

1318

pashov/skills

Skill Claude CodeCodex

Generate Echidna/Medusa-compatible Solidity fuzz suites from Foundry or Hardhat projects. Trigger on "fizz", "generate fuzz suite", "build fuzz harness", "stateful fuzzing", "fuzzing harness", "property testing", and "invariant suite".

not rated 1.1k +23 2mo ago A SkillSpector: warn 60 tokens original MIT

fetch-agents

1319

fetchai/innovation-lab-examples

Skill Claude CodeCodex

Call Fetch.ai Agentverse agents by address. Search the Agentverse marketplace, browse a curated catalog of top agents (Tavily Search, ASI1-Mini, DALL-E 3, Technical Analysis, Asset Signal, Translator, Statistics, Github), and send ChatMessages to any agent. Use when working with Fetch.ai, Agentverse, uAgents…

not rated 1.1k +2 8d ago A SkillSpector: pass 98 tokens original MIT

qimen-dunjia

1320

FANzR-arch/Numerologist_skills

Skill Claude CodeCodex

A Chinese divination tool based on Qi Men Dun Jia, a traditional system for interpreting timing, directions, and events. It conducts a structured interview, calculates a chart with a script, and then explains the result.

not rated 1.1k +15 1mo ago A 114 tokens

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: