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.

natprd

7129

anatasof/NatPRD

Skill Claude Code

Activate this skill when the user wants to create, update, validate, or review a Product Requirement Document. Triggers on mentions of PRD, product requirements, user stories, acceptance criteria, or initiative documentation, or when the user describes a feature and asks for structured documentation.

not rated 52 3mo ago A 58 tokens original BSD-3-Clause

opus-style-output

7130

0xsakura666/opus-style-output

Skill Codex

Always use this skill globally for Codex responses unless the user explicitly requests a different style. Applies to all final answers, implementation summaries, plans, reviews, comparisons, frontend copy, UI text, product copy, tables, emoji-enhanced summaries, and concise user-facing delivery notes. Makes GPT model…

not rated 52 +1 4mo ago A 101 tokens

davinci-resolve-cli

7131

Poechant/davinci-resolve-cli

Skill Claude CodeCodex

Use this skill when the user wants to script DaVinci Resolve from the command line — list/open/save projects, batch-import media, queue or wait on render jobs, list timelines/clips, or add/delete timeline markers. Trigger on mentions of DaVinci Resolve, "render this timeline", "import this footage", "tag clips", or…

not rated 52 +1 3mo ago A 100 tokens original MIT

skill-creator

7132

EvannZhongg/nanobot-desktop

Skill Claude CodeCodex

Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.

not rated 52 +1 5mo ago A 28 tokens copy · 91% MIT

zettaranc-perspective

7133

YixingCheng/zettaranc-skill

Skill Claude CodeCodex

An investment-analysis perspective based on Zettaranc’s published trading experience, mental models, heuristics, and communication style. It is intended to analyse markets and trading decisions from that stated viewpoint.

not rated 52 5mo ago A 150 tokens

build-task-benchmarks

7134

radiantlogicinc/fastworkflow

Skill Claude CodeCodex

Build a two-tier conversation benchmark for a fastWorkflow workflow: short single-errand conversations that act as unit tests and reusable blocks, then long real-world tasks of 20-100 steps composed from those blocks. Covers turn and conversation structure, seeding objects with enough structure to sustain a chain…

not rated 52 changed 5d ago A SkillSpector: pass 161 tokens original Apache-2.0

dale-proof

7135

lubluniky/dale

Skill Codex

Verify an existing implementation, fix, migration, deployment, runtime behavior, compatibility boundary, or other technical claim by mapping atomic claims to direct, fresh, reproducible primary signals and returning scoped PROVEN, PARTIAL, UNPROVEN, or CONTRADICTED verdicts with a compact proof capsule. Use when the…

not rated 52 +1 10d ago A SkillSpector: pass 127 tokens original MPL-2.0

paper-reading

7136

Immortalqx/my_codex_skills

Skill Claude CodeCodex

Deep, critical paper-reading workflow that produces a structured reading note. Use when the user wants to read, understand, summarize, break down, or take notes on a single research paper. English triggers: "read this paper", "read the paper", "paper reading", "paper notes", "deeply read", "critically read"…

not rated 52 1mo ago A SkillSpector: warn 207 tokens original MIT

scout

7137

tester-army/scout

Skill Claude CodeCodex

Safely explore and adversarially test an authorized HTTP API using the scout CLI, with or without an OpenAPI spec. Use when asked to test, probe, validate, or explore an API, whether or not an OpenAPI/Swagger spec is available. Scout is the harness; you are the operator.

not rated 52 5d ago A 65 tokens original MIT

noamdorr/saas-product-demo-video

Skill Claude CodeCodex

Produce a 20-45s SaaS product demo video in Remotion. Use whenever the user wants to make a product film, marketing reel, explainer, launch video, or LinkedIn/Instagram video of their app - including requests like "make a video of my product", "remotion video", "product demo reel", "launch film", "vertical reel"…

not rated 52 +1 3mo ago C 165 tokens original MIT

debug-tunnel-network

7139

LongNgn204/local-coding-agent

Skill Claude CodeCodex

Diagnose Local Coding Agent tunnel, DNS, TCP, TLS, proxy, organization, and office-network blocking issues.

not rated 52 +1 17d ago A 28 tokens AGPL-3.0

debug-slow-spark-job

7140

EmbrasureAI/spark-observability-skills

Skill Claude CodeCodex

Diagnose slow, expensive, or regressed Apache Spark and PySpark applications by comparing runtime evidence against a healthy run. Use for long stages, stragglers, skew, shuffle, spill, garbage collection, poor parallelism, small files, slow scans, scheduler delay, executor imbalance, and unexplained compute-cost…

not rated 52 1mo ago A SkillSpector: warn 73 tokens original Apache-2.0

skill-creator

7141

CherryHQ/stella

Skill Claude CodeCodex

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

not rated 52 +2 3d ago A 64 tokens AGPL-3.0

book

7142

DavidROliverBA/ArchitectKB

Skill Claude Code

Create Book note with knowledge compounding through spawned Concept/Pattern/Theme nodes.

not rated 52 6mo ago A 15 tokens original MIT

wetrace

7143

afumu/wetrace-skill

Skill Claude CodeCodex

A local WeChat chat-record analysis tool for searching, examining, and exporting messages from a WeChat database. WeChat is a messaging service widely used in China.

not rated 52 7mo ago A 196 tokens

fleet

7145

brizzai/fleet

Skill Claude CodeCodex

Drives fleet, a CLI that runs parallel Claude Code, Codex, and OpenCode sessions in git worktrees or existing directories. Use when handing independent work to a background agent session, creating a git worktree to work in, starting a session on a chosen agent/model/effort, sending a message to or checking on a…

not rated 52 yesterday A SkillSpector: warn 101 tokens original Apache-2.0

bmad-run-inspector

7146

tronghieu/agent-skills

Skill Claude Code

Inspect and explain bmad-loop run artifacts under .bmad-loop/runs/. Use for live health checks ("is it stuck?", "is the loop alive?", "what is the agent doing?") and post-run forensics ("what happened?", "why did story X fail?", "where did the tokens go?"). Also triggers on "monitor/check/summarize the loop", "why did…

not rated 52 +2 changed 10d ago A 141 tokens

xyzxyq/docx-course-report-writer

Skill Codex

Use when Codex handles Chinese coursework/report DOCX deliverables, including experiment reports, course papers, literature reviews, reading reports, report conversion, report repair, figure-heavy Word reports, and submission-ready report packages.

not rated 52 +1 3mo ago A 50 tokens original MIT

ruflo-token-audit

7148

pacphi/agentic-kit

Skill Claude Code

Use when the user asks where their Claude Code usage/tokens are going, is burning through their plan unexpectedly fast, hitting limits, or wants a breakdown of their Claude Code activity. Produces a COMPREHENSIVE usage report from local session transcripts: tokens by day/model/project, tool usage, MCP usage, subagent…

not rated 52 changed 6d ago A SkillSpector: pass 105 tokens original MIT

30x-seo-local

7149

norahe0304-art/30x-seo

Skill Claude Code

Local SEO audit and optimization for Google Business Profile, Google Maps, and Gemini Ask Maps. Covers GBP completeness, NAP consistency, review strategy, local schema, competitor benchmarking, GeoGrid visibility, multi-location, AI Local Pack readiness, and GBP suspension prevention. Use when user says "local SEO"…

not rated 52 +2 6mo ago A 110 tokens original MIT

PostgreSQL Database

7150

delphicleancode/delphi-spec-kit

Skill Claude Code

Development patterns with PostgreSQL via FireDAC — connection, PL/pgSQL, sequences, JSONB, UPSERT, full-text search, migrations.

not rated 52 +2 5mo ago A 34 tokens original MIT

litllm

7151

LitLLM/LitLLM

Skill Claude Code

Generate a related-work section, find prior literature, or rank candidate citations for an academic paper. Uses LLM-driven debate ranking over Semantic Scholar / arXiv / OpenAlex search, with optional citation-graph BFS expansion (deep research). Use when the user provides a paper (PDF or markdown) and asks for…

not rated 52 4mo ago C 80 tokens original Apache-2.0

product-video-ads

7152

Chase-Zzx/product-ad-video-generator

Skill Claude CodeCodex

A workflow for turning product images into advertising videos, including image cutouts, product information extraction, script writing, shot planning, video creation, and final editing.

not rated 52 7mo ago A 55 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: