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
Writes, reviews, and optimizes TinyGo code for microcontrollers and WebAssembly. Use when building embedded systems with TinyGo, flashing firmware to boards, writing WASM/WASI modules with TinyGo, integrating hardware drivers, or optimizing binary size for constrained devices.
Skill Claude CodeCodex
Integrate runtime LLM orchestration for NPC and mission generation with guardrails.
Skill Claude CodeCodex
Automates the end-to-end contribution workflow to Alchemy open-source repos (github.com/alchemyplatform/) — read CONTRIBUTING, fork via gh, clone, set upstream, install deps with the right package manager, create a feature branch, run lint/tests, stage/commit, push, and open a Pull Request. Use this skill whenever the…
Skill Claude CodeCodex
A tool that turns one or more information sources into a new article written in simple language. It keeps the main facts and reasoning while using original wording, structure, and examples.
Skill Claude CodeCodex
Use when asked to create, file, open, or raise a GitHub issue — including turning a bug report, a feature request, or a just-shipped backend change into a companion issue in another repository.
Skill Claude CodeCodex
A food and nutrition logging assistant for the Mojo app, a tracker for weight-loss journeys involving medicines such as Ozempic, Mounjaro, Wegovy, or Zepbound. It analyzes a meal from a photo or description and creates an import link.
Skill Claude CodeCodex
Implement custom window chrome for Tauri v2 desktop apps, including app-drawn titlebars and toolbars, borderless windows, cross-platform caption controls, drag regions, and platform-specific window-frame behavior. On macOS, preserve native red/yellow/green traffic lights and restore transparent rounded shells, native…
Skill Claude CodeCodex
Use when a run, review, experiment, implementation, agent workflow, or artifact has failed or produced a suspect result and the user wants root cause analysis, causal trace, hypothesis challenge, repair planning, or recurrence prevention. Especially useful for contradictory artifacts, failed final gates, regressions…
Skill Claude CodeCodex
Use when analyzing Claude Code session logs to extract insights, debug agent behavior, measure performance, or audit tool usage — provides jq recipes for the JSONL transcript format.
Skill Claude CodeCodex
Ensures baseline security practices are followed in the project. Use this when asked to perform a security audit on the codebase. Can create Jira stories for selected security findings.
Skill Claude Code
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague…
Skill Claude CodeCodex
Use this skill when writing new features, fixing bugs, or refactoring code. Enforces test-driven development with 80%+ coverage including unit, integration, and E2E tests.
Skill Claude Code
Review a GitLab Merge Request using the ai-review CLI. Fetches the MR diff, analyses it as a senior software engineer, produces structured inline comments by severity, and optionally posts them back to GitLab. Use when the user wants to review, analyse, or post feedback on a GitLab MR.
Skill Claude CodeCodex
Query and analyze data in a Tower-managed Apache Iceberg lakehouse using the Tower CLI's built-in read-only SQL query command (tower catalogs query), and record what you learn about the data with tower catalogs knowledge. Use this skill whenever the user asks a question about their company or business data (revenue…
Skill Claude CodeCodex
Preserve the minimum sufficient working state required for another coding agent to continue a task without repeating repository discovery, reconstructing prior decisions, or losing task-specific constraints.
Skill Claude CodeCodex
Domain-oriented architecture for Laravel without external package dependencies, based on concepts from "Laravel Beyond CRUD" (Spatie). Use this skill when the user wants to structure a Laravel project using DDD, domain-oriented architecture, or organize code by business concepts instead of technical properties. Also…
Skill Claude CodeCodex
Odoo 17.0 full-stack development skill for AI agents. Covers backend module architecture, ORM models and fields, API decorators, recordset operations, actions, performance patterns, testing, and built-in mixins. Use when building, extending, or debugging Odoo 17.0 custom modules. Triggers on tasks involving…
Skill Claude CodeCodex
Use this skill when the user asks for a review, audit, evaluation or analysis of a codebase, to identify bugs, security vulnerabilities, outdated dependencies or runtimes, performance bottlenecks, or code quality concerns.
collectiveai-team/agent-skills
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 Claude's capabilities with specialized knowledge, workflows, or tool integrations.
Skill Claude CodeCodex
Performs a focused audit of a declared system intent to restore confidence by examining relevant states, signals, and evidence, without modifying intent definitions or health automatically.
Skill Claude CodeCodex
Action GitHub pull request review feedback. Use when the user wants to address PR review comments, respond to code review feedback, fix review issues, or says things like "action the review", "address feedback", "handle review comments", or "go through the PR comments". Fetches all unresolved review threads, triages…
Skill Claude CodeCodex
Use when writing, reviewing, or refactoring Java code to enforce baseline conventions for imports, nullability, immutability, exceptions, resource handling, naming, and concurrency.
Skill Claude Code
A biographer-style skill that guides memoir structure, outlines, and evaluates drafts through question-driven interaction.
Skill Codex
Coauthor, restructure, and quality-review formal system documents with a single canonical outline and traceable decisions. Use when creating or revising a requirements definition, technical specification, basic design, detailed design, system proposal, or business proposal. Default to GitHub-Flavored Markdown; create…
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: