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.
Works with Bitrise CI. ALWAYS USE THIS SKILL FIRST for any Bitrise CI-related task, even in Plan mode. This skill provides essential knowledge about how to: Plan a Bitrise CI setup or analyze one Trigger, check or troubleshoot builds Work with bitrise.yml files: Design pipelines, workflows, step bundles or step…
Install a Claude-Code PreToolUse hook that blocks destructive git commands (push variants including force-push, hard reset, force clean, branch -D, checkout/restore overwrites) before Bash runs them. Use when the user wants git safety rails, force-push prevention, or repository-wipe protection.
Triage Open Feature/Bug issues on the GitHub project: assign Priority and Effort, route ambiguous issues to Feedback status for human clarification, record Analysis Token Usage, and generate IMPLEMENTATION.md — the ordered queue consumed by the implementation skill.
Review code changes or repositories for correctness, security, performance, architecture, maintainability, dead code, unnecessary complexity, and technical debt.
A playbook and local dashboard for running an AI hackathon, including participant submissions, automated judging, peer or judge reviews, and a leaderboard.
Generate a Dynatrace Gen 3 KPI dashboard (15–20 business KPIs, required map tile, branded section dividers) and a matching 30‑minute BizEvents injector for a named company, then deploy both via dtctl. Use this skill ONLY when the user explicitly asks for a Dynatrace KPI dashboard, business-event KPI demo, BizEvents…
An investment reference collection based on Chinese investor Tang Chao’s writings about value investing, company valuation, financial reports, and holdings.
A way to create videos with code using Remotion, a framework where React components describe each video frame and its behavior. It supports programmatic videos, animations, subtitles, music visualisations, tutorials, 3D scenes, and data-driven content.
Meta-skill for creating production-ready Claude Code skills using evaluation-driven development, automated eval loops, blind A/B comparison, benchmark aggregation, description optimization, and progressive disclosure patterns. Includes grader, comparator, and analyzer agents with schema-enforced data interchange.
Use when migrating an OpenClaw installation to Claude Code. Triggers on "migrate openclaw", "openclaw to claude code", "convert openclaw", "import openclaw", or when a user provides an OpenClaw directory path and wants to move to Claude Code. Also use when the user says "switch from openclaw" or "leave openclaw".
Invoke this skill for any testing or quality assurance task — writing unit tests, integration tests, E2E tests, auditing test coverage, finding edge cases, or reviewing existing test suites. Triggers on: 'write tests for this', 'add unit tests', 'find edge cases', 'audit my test coverage', 'my tests are flaky', 'write…
Review, explain, or assess the Pull Request represented by the currently checked-out feature branch in a local git repository. Use for requests such as "review this PR", "explain this PR", "what does this PR do", or "review the current branch". Produce an evidence-backed, interactive single-file HTML dashboard with an…
Use this skill when the user asks to use GalSpec to fit a spectrum, do spectral fitting with GalSpec, or fit AGN or galaxy emission-line or absorption-line spectra with GalSpec.
Monitor and guide a Codex (or other AI coding agent) session running in a tmux pane. Use this skill when the user wants to babysit, monitor, supervise, or watch over a Codex/AI agent session, or when they mention tmux + codex together, or ask you to keep an eye on another AI agent working on implementation tasks. Also…
Review a GitHub pull request using an opinionated, collaborative review style. Trigger when the user asks to review a PR, check a PR, or look over a PR.
A knowledge-base assistant for managing stored files and generating content from them, with optional online search and importing. It requires an API key and supports configuration through a file or environment variable.
Delegate tasks to OpenAI Codex (GPT-6 Astra) as background tasks for precision coding, code review, deliberation, and complex implementation. Always launch in background (runinbackground=true), continue working, then collect results with TaskOutput when needed.
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: