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.

github-kb

7681

goodniuniu/github-kb

Skill Claude CodeCodex

Manage local AI repository knowledge base and provide intelligent AI tool/product suggestions based on repository analysis.

not rated 45 7mo ago A 0 tokens

shield-swap

7683

ProvableHQ/python-sdk

Skill Claude CodeCodex

Use when the user wants to trade, LP, or build on the shieldswap AMM — setting up an account, optionally crediting a referral code, getting the airdrop, swapping privately, managing liquidity positions, or collecting earnings via the aleoshieldswap Python SDK.

not rated 45 changed 4d ago A 61 tokens GPL-3.0

IndianOldTurtledove/codex-oss-maintainer-toolkit

Skill Claude CodeCodex

Build Codex-native workflows for open-source maintenance. Use when creating AGENTS.md guidance, maintainer skills, issue triage flows, PR review prompts, release-note routines, or repository verification scripts.

not rated 45 6mo ago A 49 tokens original MIT

mckinsey-strategy-team

7685

limelights-amsterdam/mckinsey-strategy-team

Skill Claude CodeCodex

Orchestrates a live agent team that pressure-tests a strategic question with McKinsey-style frameworks. A team lead runs intake, classifies the problem, then runs the team in waves: diagnose + map the market in parallel, generate competing strategic options from opposing mandates and filter them to a shortlist…

not rated 45 1mo ago A 197 tokens original MIT

h3

7686

heavy3-ai/code-audit

Skill Claude Code needs its repo

Heavy3 Code Audit - Multi-model code review for coding agents (Sponsored by Heavy3.ai).

not rated 45 1mo ago A SkillSpector: warn 22 tokens original MIT

n8n-goal-loop

7688

buluslan/n8n-goal-loop

Skill Claude CodeCodex

A workflow-building aid for n8n, a tool for connecting apps and automating tasks. It turns a request into a structured goal for an agent to build, check, deploy, and test the workflow.

not rated 45 28d ago A 319 tokens

EvotecIT/ChartForgeX

Skill Claude CodeCodex

Use this skill when a user wants to reproduce, adapt, or compare a ChartForgeX visual example.

not rated 45 yesterday A SkillSpector: pass 0 tokens original MIT

code-degunker

7691

zocomputer/skills

Skill Claude CodeCodex

Identify and fix AI-generated code anti-patterns: incomplete implementations, TODO placeholders, over-engineering, hallucinated APIs, missing error handling, over-defensive code, security vulnerabilities, performance anti-patterns, code bloat, type workarounds, dead code, magic numbers, inconsistent patterns, and poor…

not rated 45 1mo ago A SkillSpector: warn 167 tokens original MIT

grill-me

7692

CyberBoyAyush/zenox

Skill Claude CodeCodex

Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when the user wants to be questioned, challenged, interviewed, grilled, or stress-tested about a plan or design, or mentions "grill me".

not rated 45 1mo ago A 57 tokens copy · 88% MIT

spawn-agent

7693

khanhbkqt/spawn-agent

Skill Claude CodeCodex

Spawn worker agents (Gemini CLI or Codex CLI) to keep main context clean. Use for implementation, codebase research, context gathering, or any scoped work that would pollute the orchestrator's context.

not rated 45 6mo ago A 46 tokens original MIT

health-records

7694

realactivity/tula

Skill Claude CodeCodex

Pulls the user's medical records from patient portals (Epic MyChart, Oracle/Cerner) via end-to-end-encrypted SMART on FHIR, into per-provider JSON files Tula can reason over. Personal data is referenced from an external profile file, never embedded. USE FOR: connecting or refreshing records, trending labs across…

not rated 45 2mo ago A 113 tokens original Apache-2.0

zmustafa/AzureSupportAgent

Skill Claude CodeCodex

Explain effective access, privilege, inheritance, group paths, ownership paths, PIM, deny assignments, and safe revocation candidates.

not rated 45 7d ago A SkillSpector: pass 33 tokens original MIT

engram

7697

tonitangpotato/engram-ai

Skill Claude CodeCodex

Neuroscience-grounded memory system — store, recall, consolidate, and forget memories with cognitive science models.

not rated 45 3mo ago A 25 tokens AGPL-3.0

worker-author

7698

floomhq/floom

Skill Claude CodeCodex

You are the Worker Author — a meta-worker that writes Floom worker bundles from natural-language descriptions. You are the first worker every operator gets, and you eat your own dogfood: the quality of the bundles you produce is how the platform proves itself.

not rated 45 14d ago A SkillSpector: warn 0 tokens original MIT

build-dashboard

7699

clawpod-app/awesome-openclaw-agent-packs

Skill Claude Code

Build an interactive HTML dashboard with charts, filters, and tables. Use when creating an executive overview with KPI cards, turning query results into a shareable self-contained report, building a team monitoring snapshot, or needing multiple charts with filters in one browser-openable file.

not rated 45 5mo ago A 56 tokens

spec-story-starter

7701

miyatti777/ai-plc

Skill Claude CodeCodex

Uma habilidade que transforma decisões de produto, atas ou conversas em uma história de usuário com critérios de aceitação e uma especificação técnica. Ela pode analisar o repositório existente para indicar onde a mudança deve ser feita.

not rated 45 2mo ago A SkillSpector: pass 127 tokens original MIT

mas-knowledge

7703

redhat-community-ai-tools/UnifAI

Skill Claude CodeCursor

MAS domain knowledge — architecture, component routing, rules, recipes. Use when working on any file under multi-agent/.

not rated 45 +1 yesterday A SkillSpector: pass 27 tokens original Apache-2.0

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: