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.

annotate

10993

haizelabs/annotate

Skill Claude Code

Create flexible annotation workflows for AI applications. Contains common tools to explore raw ai agent logs/transcripts, extract out relevant evaluation data, and llm-as-a-judge creation.

not rated 17 10mo ago B 38 tokens

just-progress-bar-skill

10994

Just-Agent/just-progress-bar-skill

Skill Claude CodeCodex needs its repo

Design, select, generate, and audit accessible creative progress bars for React, HTML/CSS, Gallery demos, recipes, CLI workflows, and Agent/MCP integrations.

not rated 17 4mo ago A 39 tokens original MIT

ironcode

10995

djfksjd/ironcode

Skill Claude CodeCodex

Production-grade engineering gate for writing OR reviewing code. Enforces security, resource safety (memory leaks, unclosed listeners/streams/timers), efficient data access (N+1, pagination/infinite-scroll, over-fetching, backend cost), defensive coding, and evidence-based verification. Use when the user invokes it…

not rated 17 1mo ago A 124 tokens original MIT

ops_reverse_proxy

10996

frontier-ai-next/mgarlbot

Skill Claude CodeCodex

Public deploy via Traefik/Nginx/frp on a VPS — inspect first; reverse proxy is HTTP-only by default (no TLS on the edge).

not rated 17 1mo ago A 38 tokens original MIT

backup-restore

10997

sawrus/agent-guides

Skill Claude Code

PostgreSQL backup and restore with pgBackRest — full/incremental/WAL, PITR, K8s CronJob scheduling, and restore verification.

not rated 17 21d ago A SkillSpector: pass 36 tokens original MIT

lark-agent-simple

10998

Interstellar-code/claud-skills

Skill Claude CodeCodex

Skill "lark-agent-simple" from Interstellar-code/claud-skills, covering lark agent simple skill, architecture, token efficiency design, component roles and when to use this skill.

not rated 17 7mo ago A 135 tokens

swift-unit-testing

10999

nonameplum/agent-skills

Skill Claude CodeCodex

Write, modify, and review deterministic Swift unit tests using the Swift Testing framework. Use when working with @Test.

not rated 17 1mo ago A 27 tokens

diataxis

11000

keithpatton/diataxis-agent-skill

Skill Claude CodeCodex

Classify, validate, generate, and audit documentation using the Diátaxis framework. Enforces quadrant purity across tutorials, how-to guides, reference, and explanation. Use when creating documentation, reviewing docs, auditing doc sets, restructuring existing content, or when the user mentions Diátaxis, documentation…

not rated 17 7mo ago A 69 tokens CC-BY-SA-4.0

audit-tracking

11001

WaniWani-AI/sdk

Skill Claude CodeCodex

Audit Waniwani event tracking across an MCP project. Does an in-depth overview check of the whole app (server, flows, tools, widgets, chat embed), verifies that only events defined in the Waniwani taxonomy are sent, and identifies missing events worth adding at each funnel stage (identify, leadqualified, priceshown…

not rated 17 3d ago A SkillSpector: warn 118 tokens original MIT

ccg-namespace

11002

tae2089/code-context-graph

Skill Claude CodeCodex

Isolate read-only CCG search, documentation discovery, and analysis by namespace. Use when working across multiple repositories or services, preventing cross-project graph leakage, federating supported reads, or traversing materialized cross-namespace references. Do not use for graph writes or scoped updates; the user…

not rated 17 1mo ago A SkillSpector: pass 73 tokens original MIT

desktop-agent-ops

11003

appergb/desktop-agent-ops

Skill Codex

Use when the user needs cross-platform desktop GUI control of a native app or window and no MCP server, native CLI, or OS API can safely complete the task.

not rated 17 5mo ago A 38 tokens original MIT

pipeline-core

11004

FrameCoreWorks/framecore-works-codex-chatgpt-workflow-kit

Skill Codex

Use this skill for portable Codex or ChatGPT workflow routing, bounded roles, gates, handoffs, visible state, artifact templates, reasoning routes, request diagnostics, QA loops, delivery discipline, and provider-neutral governance.

not rated 17 changed 7d ago A 47 tokens

deep-research

11005

Jay-523/agent-skills

Skill Claude Code

MECE decompose a research question, run parallel Codex web-research agents via tmux, iteratively deepen via DAG, synthesize findings.

not rated 17 5mo ago A 33 tokens

PSPDFKit-labs/pi-skills

Skill Claude CodeCodex

Multi-agent workflow (tracer/resolver/bypass) for secure code review, exploitability triage, and PoC validation in codebases. Use when conducting structured security research or penetration test analysis.

not rated 17 4mo ago A 45 tokens

xxskill

11007

aixiaoxiang/xx-skills

Skill Claude CodeCodex

A product-building guide with two modes: it chooses the right skill before a task and suggests the next step after one is finished. It covers the stages of clarifying an idea, building the product, and getting it running.

not rated 17 2mo ago A 106 tokens

pecmd-pro-max

11008

VirtualHotBar/PECMD-Pro-Max

Skill Claude CodeCodex

A skill for programming PECMD2012 scripts, which are used in lightweight Windows PE startup environments and system tools. It covers GUI tools, initialization scripts, disk partitioning, batch-file conversion, information collection, and debugging.

not rated 17 4mo ago A 139 tokens

lean-security-audit

11009

InternetMaximalism/lean-reinforced-concrete

Skill Claude CodeCodex

A follow-on skill for deeper security auditing once a system has been formalized in Lean (e.g. by lean-formal-audit and the audit/ folder exists). It turns the existing Lean formalization into an offensive tool: running Lean code (#eval / decide / #print axioms), using reasoning to form attack hypotheses, doubting and…

not rated 17 2mo ago A 0 tokens

moscow

11010

AndreAlbuquerque/claude-config

Skill Claude CodeCodex

Apply MoSCoW prioritization (Must / Should / Could / Won't) to a list of candidate solutions, defending each placement against explicit criteria and inviting challenge. Designed for discussion mode — never just outputs a table, always defends placements and surfaces where MoSCoW is the wrong framework. Use after OST…

not rated 17 1mo ago A 86 tokens

sop-packager

11011

dotanminh/sop-packager

Skill Claude Code

Use when the user wants to package a repetitive business process for AI automation, needs to create an SOP from scratch, or asks how to make AI understand their daily workflow.

not rated 17 2mo ago A 38 tokens

aristotle

11012

alexwwang/aristotle

Skill Claude CodeCodex

An error-reflection and learning workflow activated with /aristotle after someone reports a mistake or incorrect result.

not rated 17 20d ago A SkillSpector: warn 209 tokens original MIT

cv-update-review

11013

erafat/skills

Skill Codex

Run a confirmation-gated CV update workflow for Word CV documents: set up a reusable profile, scan configured local activity sources plus public evidence such as PubMed through NCBI E-utilities and configured website/RSS feeds, prepare a CV update packet, ask the user to approve completed/public/accepted items, create…

not rated 17 +1 2mo ago A 126 tokens original MIT

manage-skills

11014

cfircoo/claude-code-toolkit

Skill Claude Code

This skill should be used when the user asks to "create a skill", "build a new skill", "write a SKILL.md", "improve a skill", "update a skill", "audit a skill", "verify a skill", or mentions skill structure, skill best practices, or skill authoring. Provides expert guidance for creating, updating, auditing, and…

not rated 17 5mo ago A 83 tokens original MIT

rails-conventions

11015

ethos-link/rails-conventions

Skill Codex

Rails 8.x application architecture, implementation, and review guidance for production codebases. Use when building or reviewing Ruby on Rails 8 features across models, controllers, routes, Hotwire, jobs, APIs, performance, security, and testing. Trigger for requests mentioning Rails 8, Active Record, Active Job…

not rated 17 changed 3d ago A 92 tokens original MIT

eastmoney_financial_data

11016

meission/eastmoney

Skill Claude CodeCodex

A skill for querying current financial and market data from Eastmoney, a Chinese financial-data provider. It covers securities prices, funds, bonds, company details, financial measures, executives, ownership, and business relationships.

not rated 17 6mo ago A 114 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: