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.
Skill Claude Code
Manages scheduled Claude Code jobs using launchd on macOS and Task Scheduler on Windows. Use this skill when the user wants to: create a scheduled task for Claude, list their scheduled jobs, enable or disable a job, run a job manually, view job logs, delete a scheduled job, check job status, or manage log retention.…
Skill Claude CodeCodex
A Chinese-language workflow for creating, changing, parameterizing, testing, or importing knowledge into business skills. It can first collect information about a new business area from design documents.
Skill Claude CodeCodex
A role-playing assistant based on Hiro Nikaido, a fictional character from a Japanese mystery game. It answers in Chinese using the character's restrained, logic-focused style and can research factual questions first.
Skill Claude CodeCodex
DNA de design de 20 sites premium (engenharia reversa via DevTools) — a fórmula Webflow/HTML + Lenis + GSAP/ScrollTrigger destilada em leis, calibres medidos e 22 efeitos nomeados com código. Use ao criar landing pages animadas, sites com scrollytelling, heroes tipográficos, vídeo-fundo, marquees, pin/scrub ou…
Skill Claude CodeCodex
Operating playbook for generating and maintaining version-pinned documentation packs with the llm-docs CLI. Use when building, refreshing, or verifying an agent-ready docs pack for a specific installed library version, or when maintaining this repository.
Skill Claude CodeCodex
Use this skill when the user needs to write, scaffold, or improve an OIAP agent plugin in TypeScript, create an oiap.plugin.ts file, define commands, instructions, skills, hooks, agents, or policies, or build target bundles with the OIAP CLI.
Skill Claude CodeCodex
Assess a programming project's HUMAN maintainability (HMAP): 0-100 score, nine-tier verdict, per-dimension scores, and file:line evidence — built to catch vibe-coding / AI-generated slop, including semantic incoherence (name/contract/concept/vocabulary drift). Triggers: assess maintainability / rate this project /…
Skill Claude CodeCodex
Run the iterative evolution loop from the current persisted run state until convergence.
Skill Claude CodeCodex
Persistent memory for AI agents — remember preferences, decisions, failures, and learnings across sessions.
Skill Claude Code
Optional autonomy control plane — configure, plan, launch, monitor, recover, or stop local CLI-agent workers through SwarmVault's durable supervisor. Use for fit/budget-aware platform + model + reasoning-effort routing; a consistent pre-start/live/boundary/on-demand board with ticket drill-down; TOLD/MEASURED/EST…
thaolst/ai-growth-agents-for-marketers
Skill Claude CodeCodex
Run a two-stage research then planning workflow for growth campaigns. Use when the user wants to analyze past campaign data AND create a new plan based on that analysis in one connected workflow. Stage 1: analyze data and extract structured insights. Stage 2: use insights to build a campaign plan. Input: past campaign…
Skill Claude CodeCodex
Code ownership session that turns AI-written code into understood code. The agent shortlists "vibe-y" pieces from recent changes, checks the user's confidence, then guides explain/reimplement/test exercises in a LeetCode-style format and captures distilled per-piece ownership notes — all without silently mutating the…
Skill Codex
Audit and safely curate Codex memory, including stale claims, cross-repo leakage, sensitive entries, and memory configuration. Use when reviewing or cleaning Codex memory, not generic repository docs.
Skill Claude CodeCodex
Manage the runloq issue tracker — create, list, update, close, search, and view the board. Use when someone says "add issue", "create a ticket", "what's open", "show board", "close X", "search issues", or when tracking work in progress. Works via the runloq CLI or runloq-mcp MCP server.
Skill Claude CodeCodex
This skill should be used whenever implementation or review depends on external, version-sensitive facts: libraries, SDKs, APIs, CLIs, cloud services, security advisories, changelogs, release notes, or documentation that may have changed. The skill anchors local versions, ranks source quality, runs an executable probe…
curtischoutw/claude-institution
Skill Claude CodeCodex
A step-by-step debugging guide based on reproducing a failure, testing one explanation at a time, making the smallest relevant change, and checking the result. It includes a stopping rule for repeated unsuccessful fixes.
FlorinI/Florians-Claude-Code-Kit
Skill Claude CodeCodex
Disciplined root-cause analysis for diagnosing why something is broken. Use whenever the user is debugging a bug, regression, incident, outage, flaky or intermittent behavior, a failing test, or asks "why is X happening" / "why did this break" / "whats causing this" — even if they never say the words "root cause." It…
Skill Claude Code
The ONLY way to call Codex, DeepSeek, MiMo, GLM, or Grok. Use whenever the user wants to ask, delegate to, or get a second opinion from Codex, DeepSeek, MiMo, GLM, or Grok. Do NOT run the codex, deepseek (ds), mimo (mm), glm, or grok CLI directly — from the main agent or a subagent; always use this skill's relay call…
Skill Claude CodeCodex
Search local Claude Code, Codex, and Cursor user-prompt history (read-only). Use when you need a past prompt, want to grep coding-agent session text, or pipe prompt history as JSON.
Skill Claude CodeCodex
Create or update repository skills and instructions when major learnings are discovered during a session. Use when the user says "learn!", when a significant pattern or pitfall is identified, or when reusable domain knowledge should be captured for future sessions.
wangjialiang678/research-workflow-skill
Skill Claude CodeCodex
A research workflow that chooses a research level and scenario before following a matching process. It covers quick checks and larger investigations using helper agents.
Skill Claude CodeCodex
Use in a window that has received a Wakeflow delivery for a test target - read the frozen test contract in the task package, run its approved steps in the real environment against the landing the implementation produced, record what each step actually observed with its evidence, then import the per-step report and…
uimarch123-arch/ai-pm-atom-lesson
Skill Claude CodeCodex
A tool for teaching one small AI product-management concept through a standalone interactive web page. The page includes definitions, sources, an example project, questions, and an interactive demonstration.
Skill Claude CodeCodex
Drive a reviewed spec to evidence-backed, integrated closure — grill the spec at intake until it is fully understood, decompose it into owned work items, build each against targeted criteria, gate every merge per item, maintain a criterion-to-evidence ledger, and close only when an integrated done gate passes. Use…
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: