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 CodeCodex
Use AgentReceipt CLI as a local evidence sidecar for AI coding sessions. Use when an agent needs compact replay/focus reports, patch-equivalence checks, schema outputs, or deterministic JSON workflows.
Skill Claude CodeCodex
Generate a weekly review summarizing messages, events, and action items from the past 7 days.
Skill Claude CodeCodex
Use this skill when the user asks to half-clone the conversation, shrink or free up context, or continue in a smaller conversation. It clones the later half of the current conversation into a new one the user can resume.
Skill Claude Code
Govern consequential Codex tool calls with Custodian before execution, including writes, network access, credentials, destructive commands, production changes, and money movement.
Skill Claude CodeCodex
Use this skill when building, running, calibrating, validating, or diagnosing SWAT+ hydrological models. Triggers include SWAT+, watershed modeling, streamflow simulation, hydrograph calibration, USGS discharge matching, routing failures, and outlet selection debugging.
Skill Claude Code
Use when improving performance, latency, throughput, memory usage, or general efficiency. Start by defining target metrics, measuring comprehensively, attributing bottlenecks, validating with static analysis, and prioritizing macro-optimizations before micro-optimizations.
migmcc/agent-skill-quality-gate
Skill Claude CodeCodex
Use when a release is being prepared and a human-readable changelog must be generated from merged pull requests.
neilshermes-project/hermes-memory-hybrid
Skill Claude CodeCodex
One-command hybrid memory upgrade for Hermes (FTS5 + sqlite-vec embeddings + relational pre-filtering). Snapshot-safe and fully reproducible.
Skill Codex
Extract readable main body content from arbitrary HTML pages, local HTML files, saved browser pages, or URLs where the article/body structure is unknown or inconsistent. Use when Codex needs to remove navigation, ads, boilerplate, comments, sidebars, scripts, hidden text, duplicated menus, or layout chrome and return…
Skill Claude Code
Multi-agent market validation skill. Spawns 6 parallel research analysts (Community uses last30days for fresh 30-day signal; Claim Verifier uses deep-research for fact-checking) and delivers a BUILD / CONDITIONAL / PIVOT / STOP verdict with a 7-pillar scorecard. Use when user says "should I build this", "/sib"…
Skill Codex
Run Colla Agent, a traceable bounded collaboration loop in which the current Codex session implements a project and Antigravity plans and reviews it read-only. Use for complex or high-risk coding, design, refactoring, debugging, document, media, data, or multi-file project work when the user asks for Colla Agent…
Skill Claude CodeCodex
Comprehensive security audit for web applications and APIs. Performs a full-stack security review covering authentication, authorization, rate limiting, input validation, secrets management, security headers, cost controls (AI/API spend), email abuse prevention, dependency vulnerabilities, and data exposure risks.…
Skill Claude CodeCodex
QUESTPIE Probe — dev testing CLI for AI coding agents. Start servers, test APIs, control browsers via agent-browser, record and replay regression tests with zero tokens. Use when testing web apps, starting dev servers, reading logs, debugging errors, making API calls, checking browser console/network, or composing…
Skill Claude CodeCodex
CLI for the Make.com automation platform. Manage organizations, teams, folders, scenarios, webhooks, connections, data stores, functions, and sync entire orgs to local disk for analysis. Also covers Make.com MCP server setup, zone configuration, blueprint analysis, and searching for properties across synced scenario…
Skill Claude CodeCodex
Critical evaluation of proposed changes BEFORE their implementation. Use when: Need to evaluate proposed changes before implementation Want to reduce merge rejection risk Need to cut scope to minimum valuable change Require pre-implementation quality gate Builds structured JSON with decision (approve/revise/reject)…
Skill Claude CodeCodex
Use when OpenClaw is connected to a WordClaw MCP server or WordClaw-backed REST runtime. Start with system://capabilities, system://deployment-status, system://current-actor, and system://workspace-context, then use guidetask or resolveworkspacetarget before writing. Covers schema-bound authoring, review workflows…
Skill Claude CodeCodex
Code review checklist and best practices. Use when reviewing code or preparing code for review.
Skill Claude CodeCodex
A Chinese-language guide for finding, evaluating, creating, improving, testing, and packaging Agent Skills, which are reusable instructions that guide an AI coding or task agent.
Skill Claude Code
Create, rewrite, split, or quality-check Linear issues so each task has an evidence-based problem statement, one executable outcome, explicit scope, falsifiable acceptance criteria, concrete validation, dependencies, and the existing labels required for repository, agent, and reviewer routing. Use when a user asks to…
Praut-Startup-Support/AgenticDev
Skill Claude CodeCodex
Větvení, checkpointy a odevzdání práce přes agenticdev-git.
Skill Claude CodeCodex
Manage durable agent handoffs, Cadence state, pickup signatures, and clean-square shutdowns for long-running or self-evolving workflows.
Yingqi-Han/learning-retrospective-skill
Skill Codex
A skill for saving verified lessons from difficult coding tasks so future agents can use them. It covers both learning after a task succeeds and recalling an existing lesson when the same problem appears again.
stepanenkoviktor0110-boop/ai-dev-methodology
Skill Claude CodeCodex
A skill for resolving conflicting development requirements, where one part of a system is expected to satisfy opposing conditions. It looks for existing resources in the code and data structure, then tests possible ways to separate the conflict by structure, timing, conditions, or relationships.
Skill Claude CodeCodex
Create and maintain AGENTS.md files that provide AI coding agents with project context, commands, code style, and boundaries. Use when updating an existing AGENTS.md, creating a new AGENTS.md for a repository, or improving agent instructions for a codebase.
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: