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.

ultragoal

3457

jxnl/dots

Skill Claude CodeCodex

Design, critique, set, create, activate, or run durable Codex goals for persistent or long-running objectives. Use when the user says "set a goal", "start a goal", "activate goal mode", "persistent goal", "long-running objective", "goal tree", or asks for a goal with verifiers, durable state, approval gates…

not rated 281 5d ago A 90 tokens

wooly99/geng-academic-fraud-detector

Skill Claude CodeCodex

An academic-paper fraud checker that analyzes PDF research papers for possible data manipulation and other research misconduct. A PDF is a fixed-layout document format; a Western blot is a laboratory image used to detect proteins.

not rated 281 +2 5mo ago A 92 tokens

vakovalskii/searcharvester

Skill Claude CodeCodex

Deep-research methodology with a ROLE-BASED team of parallel sub-agents. One delegatetask batch dispatches 2–3 researchers (each on a distinct sub-question), 1 critic (adversarial counter-search), and 1 fact-checker (numeric/date verification). The lead synthesises their findings into a cited report at ./report.md.…

not rated 281 +1 changed 1mo ago A 107 tokens AGPL-3.0

ableton-songwriter

3460

uisato/ableton-mcp-extended

Skill Codex

Professional songwriting workflow for Ableton: structured intake, production brief, composition/arrangement execution, plugin-aware instrument loading, quick mix, QA, and revision handoff.

not rated 281 +1 6mo ago A 38 tokens original MIT

clx-agent

3461

snolab/CapsLockX

Skill Claude CodeCodex

You are CLX Agent on macOS. You control the computer by outputting CLX commands. Commands execute IMMEDIATELY as you stream them. Each line runs instantly. This is macOS — use Cmd (w-) for shortcuts, not Ctrl (c-).

not rated 280 3d ago A 0 tokens GPL-3.0

super-dev-core

3462

shangyankeji/super-dev

Skill Claude CodeCodex

Super Dev pipeline governance for research-first, commercial-grade AI coding delivery.

not rated 280 +2 4mo ago A 17 tokens original MIT

ghfs

3463

antfu/ghfs

Skill Claude CodeCodex

Manages ghfs local mirror files in .ghfs/, especially translating user instructions into valid execute operations (execute.md, execute.yml, or per-item edits), running ghfs execute / ghfs sync, and validating issue/PR batch edits. Use when tasks involve editing issues/PRs through .ghfs artifacts, reconciling sync…

not rated 281 +3 changed 3d ago A SkillSpector: pass 86 tokens original MIT

perfect-web-clone

3464

ericshang98/Perfect-Web-Clone

Skill Claude CodeCodex

Reproduce a live website from its URL as a clean, deployable Vite + React project by running the complete agent-driven Perfect Web Clone harness: capture source evidence, plan the full page, author every section, implement common interactions, build, compare, repair, and hand the measured result to the user for…

not rated 280 +2 2mo ago A SkillSpector: pass 134 tokens original MIT

oklch-skill

3465

jakubkrehel/oklch-skill

Skill Claude CodeCodex

OKLCH color space for web projects. Convert hex/rgb/hsl to oklch, generate palettes, check contrast, handle gamut boundaries, and theme with Tailwind v4. Triggers on oklch, color conversion, palette generation, contrast ratio, gamut, display p3, design tokens, hue drift, chroma, dark mode colors.

not rated 281 +7 1mo ago A Socket: passSnyk: pass 79 tokens original MIT

lensback940701/Evidence-Bound-Press-Conference-Revision-Skill

Skill Codex

Diagnose and revise defensive academic writing while preserving claim ceilings, evidence status, scope conditions, rival explanations, and conceptual hierarchy. Use for a whole-manuscript batch audit or a tightly authorized, tracked-change revision when an academic paper hides its contribution beneath self-defence…

not rated 280 +2 2mo ago A 126 tokens original MIT

weread-skills

3467

Tencent/WeChatReading

Skill Claude CodeCodex ✓ vendor

A WeRead (微信读书) assistant for searching books, managing a bookshelf, viewing notes and highlights, browsing reviews, checking reading statistics, and finding recommendations.

not rated 281 +7 changed 28d ago A 36 tokens

bidah/skill-set

Skill Claude CodeCodex

Produce short, punchy iOS app onboarding videos in Remotion that showcase a feature in action by animating isolated pieces of the UI (cropped components, not full screens) with nice UI-like transitions. Use when the user asks to create, build, or generate an onboarding video, app preview, feature demo clip, App Store…

not rated 279 +2 3mo ago A 88 tokens

thesis-defense-pptx

3469

zouchenzhen/thesis-defense-pptx-skill

Skill Codex

Create, polish, and quality-check editable undergraduate or graduate thesis defense PowerPoint decks from a local thesis PDF/LaTeX project and an existing PPTX template. Use when the user asks for a formal defense PPT, thesis presentation, academic答辩PPT, template-matched PPTX, or local PowerPoint deck generation with…

not rated 279 +2 5mo ago A SkillSpector: pass 77 tokens original Apache-2.0

ghealth

3470

Google-Health-API/google-health-cli

Skill Claude CodeCodex

Query Google Health API v4 — steps, heart rate, exercise, sleep, weight, SpO2, HRV, ECG, blood glucose, nutrition, and 40 total data types.

not rated 281 +3 4mo ago A SkillSpector: warn 41 tokens original Apache-2.0

freertos

3471

mohitmishra786/low-level-dev-skills

Skill Claude CodeCodex

FreeRTOS skill for embedded RTOS development. Use when creating tasks, managing priorities, using queues and mutexes, detecting stack overflows, configuring FreeRTOS via FreeRTOSConfig.h, or debugging FreeRTOS applications with OpenOCD and GDB. Activates on queries about FreeRTOS tasks, queues, semaphores, mutexes…

not rated 279 +1 4mo ago A Socket: passSnyk: passSkillSpector: pass 93 tokens original MIT

skill-sublation

3472

Sven-Mirana/sublation

Skill Claude CodeCodex

A governed workflow for improving agent skills through observations, proposed changes, testing, review, user approval, and a period of monitoring. “Sublation” means preserving useful existing behavior while adding a verified improvement.

not rated 278 +1 2mo ago A 91 tokens original MIT

advisory-board

3473

Backtthefuture/huangshu

Skill Claude CodeCodex

A structured business decision session in which 12 different thinker perspectives examine an important issue. It is designed for major business choices rather than routine tasks, coding questions, or emotional support.

not rated 278 +1 3mo ago A 194 tokens

autoresearch

3474

ruizrica/agent-pi

Skill Claude Code

Autonomous Goal-directed Iteration. Apply Karpathy's autoresearch principles to ANY task. Loops autonomously — modify, verify, keep/discard, repeat. Invoke with /skill:autoresearch or when user says "work autonomously", "iterate until done", "keep improving", or "run overnight".

not rated 278 +1 3d ago A SkillSpector: warn 66 tokens original MIT

buzz-self-hosting

3475

tonbistudio/buzz-skills

Skill Claude CodeCodex

Use when helping a user set up, debug, or operate a self-hosted Buzz relay through Docker Compose. Do not use for general Docker questions or non-Buzz Nostr deployments.

not rated 278 3mo ago A SkillSpector: warn 42 tokens original MIT

china-antique-maplibre

3476

hopechen067/china-antique-maplibre

Skill Codex

China antique parchment MapLibre map engine with configurable basemap, Terrarium hillshade, optional user-supplied water overlay, live tuner page, and tiered settlement extrusions for HyperFrames historical videos.

not rated 278 2mo ago A SkillSpector: pass 48 tokens original MIT

litprog-skill

3477

tlehman/litprog-skill

Skill Claude CodeCodex

Transform a codebase into a literate program: a document written for human comprehension that also generates the original source code.

not rated 278 +3 7mo ago A 0 tokens

cangjie

3479

Yeadon8888/cangjie-skill

Skill Claude CodeCodex

A Chinese-language workflow for distilling a person's way of thinking from books, interviews, talks, articles, or PDFs into a reusable coding-agent skill. It focuses on beliefs, decisions, mistakes, contradictions, and recurring reasoning patterns.

not rated 280 +6 1mo ago A 144 tokens original MIT

fabric-jev

3480

monotykamary/pi-fabric

Skill Claude Code

Supervise shell commands and bounded task output from Python host calls to Jev TypeScript programs, with explicit optional typed decisions. Use for foreground/background shell workflows, semantic routing, verification, and per-turn advisors without a reasoning-model turn per event.

not rated 278 changed 1mo ago A 53 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: