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.
Automattic/wordpress-agent-skills
Skill Claude CodeCodex
WordPress Full Site Editing (FSE) theme architecture. Use when generating theme.json, block templates, template parts, patterns, and functions.php for WordPress block themes.
Skill Claude Code
Generate a changelog from git history. Analyzes commits since the last tag or a specified range and produces a formatted changelog using the template.
Skill Codex
Project-local DPIS hook implementation and diagnosis workflow for Xposed API routing. Use when implementing, reviewing, migrating, or debugging Legacy Xposed hooks, libxposed hooks, API 101 or 102 capability gating, modern/legacy flavor hook wiring, hook entry selection, or fallback behavior between old and new…
Skill Claude CodeCodex
The dev-intelligence-orchestrator skill provides intelligent development tool orchestration with self-improving learning capabilities through mcp-prompts integration.
Skill Claude CodeCodex
Use when creating or modifying OpenCode rules (.md/.mdc files) that customize agent behavior. Trigger when user wants to create a rule, codify repeated instructions, persist guidance across sessions, or scope rules to specific files, prompts, environments, or workflows.
Skill Claude Code
Use when a user completes a phase, sprint, milestone, or meaningful unit of work and needs a retrospective. Also triggers on /retro command. Generates honest, structured retrospectives from available project data (GSD planning files, git history, GitHub PRs/issues, user input). Adapts to any project — GSD-managed…
SteelMorgan/1c-agent-based-dev-framework
Skill Claude CodeCodex
MUST use WHEN a code diff needs second-opinion or multi-model review: light tier = one eligible independent cross-family reviewer selected from enabled participants outside the caller family (also the executor of blocking acceptance-bound review and the finalization gate APPROVECOMPLETION), full tier = divergent swarm…
Skill Claude CodeCodex
Use when the repository has no design system yet (no tokens, no component library - a new site/app, an "Apply design system" task, or a task that asks for one), before building any page section - writes the approved design system's generated files from getdesignsystem (files true) and builds the tokens on them when…
Skill Claude CodeCodex
Use when auditing or reviewing skill quality — batch checks across a library, deep per-skill grep methodology, usage stats, efficacy testing, or fix planning. Single consolidated home for the writing-for-agents review framework and the 3-surface review methodology.
Skill Codex
Inspect and coordinate Base ecosystem release trains using the repository's versioned policy, milestone rules, immutable refs, BOM evidence, and public readback gates.
Skill Claude CodeCodex
Use when the user explicitly asks to diagnose or improve Codex skill/plugin routing, determine which skill or plugin should handle a request, refresh or check a skill registry, investigate why a skill/plugin did not trigger, or review skill descriptions for trigger quality. Do not use for ordinary task execution when…
Skill Claude CodeCodex
Search for places (restaurants, cafes, etc.) via Google Places API proxy on localhost.
Skill Codex
Use this skill when Codex or agents need to use Notion through the easy-notion CLI instead of loading MCP tools, especially for low-context Notion access, multi-profile workspace/account workflows, readonly vs readwrite permission modes, search, users, pages, content edits, blocks, comments, and database entries.
SpillwaveSolutions/agent-brain
Skill Claude Code
Modern Python coaching covering language foundations through advanced production patterns. Use when asked to "write Python code", "explain Python concepts", "set up a Python project", "configure Poetry or PDM", "write pytest tests", "create a FastAPI endpoint", "run uvicorn server", "configure alembic migrations"…
Skill Claude CodeCodex
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends mini-OpenCode's capabilities with specialized knowledge, workflows, or tool integrations.
langchain-ai/skills-benchmarks
Skill Claude CodeCodex ✓ vendor
INVOKE THIS SKILL when writing ANY LangGraph code. Covers StateGraph, state schemas, nodes, edges, Command, Send, invoke, streaming, and error handling.
Skill Claude Code
Fix CI failures and performance regressions for a Julia package PR by iterating - triage the latest CI results, fix one root cause, verify locally, push. Use when a PR's GitHub Actions or Buildkite CI is failing, or when CI jobs run slower than they do on the main branch. Verifies CPU and GPU compilation locally…
Skill Claude Code
Plan, execute, monitor, and assess protein/antibody design campaigns. This skill governs how to size a campaign, track run state, coordinate multi-run efforts, estimate cost and time on each compute target (local GPU, HPC, Tamarind), monitor progress, and evaluate campaign health.
Skill Claude Code
A converter for SillyTavern character cards, which are files describing interactive role-playing characters and worlds, into a pi coding-agent runtime. It translates prompts, world information, events, rules, and saved state into a structured interactive system.
Skill Claude CodeCodex
Skill "Monet" from Monet-AI-Editor/Monet, covering ai video editor — agent control reference, ⚠️ finding editorctl — mandatory (read this first), ⚠️ output file naming — mandatory (read this first), ⚠️ audio on multi-clip timelines — mandatory and ⚠️ canvas mode — mandatory rules (read this first).
Skill Codex
Operate Binance Spot market, account, and order APIs through UXC with a curated OpenAPI schema, Binance query signing, and separate mainnet/testnet link flows.
Skill Claude CodeCodex
Used to release all toolbox, integrations, agents. Use when releasing a subproject to PyPI, Docker Hub, or when the user asks to release or publish.
Skill Claude CodeCodex
Use for any task involving the ledidi library — gradient-based design of minimal edits to categorical sequences (DNA/RNA/protein) so that a frozen oracle model predicts a desired output. Triggers on designing or editing a sequence, inserting or knocking out a motif or binding site, hitting a target model output, cell…
doraemonkeys/claude-code-debug-mode
Skill Claude CodeCodex
Interactive debugging mode that generates hypotheses, instruments code with runtime logs, and iteratively fixes bugs via autonomous reproduce-analyze loops, with human help only as a fallback. Only for hard-to-diagnose bugs; in those cases, remind the user that debug-mode is available, and never proactively activate…
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: