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.
Build, fix, review, install, and validate Balsa UI open-code components for Vue applications. Use for focused Balsa repository maintenance, Vue UI built from Balsa components, compositions or blocks, semantic tokens, registry metadata, accessibility behavior, and installed-source update safety. Scale the workflow from…
Central manager for PersonalizationMCP operations across all platforms. Use for cross-platform health checks, unified summaries, and day-2 maintenance after initial onboarding.
This skill enables deep semantic and structural analysis of C/C++ codebases using a pre-built Neo4j GraphRAG. It provides insights into call chains, class hierarchies, macro causality, and type aliases.
Generate, edit, and batch-process images through the bundled script and configured API Key provider (OpenAI-compatible, Atlas, xAI, or Gemini). Use for photos, illustrations, product visuals, posters, covers, diagrams, UI references, game art, transparent subjects, reference-image edits, inpainting, multi-reference…
★not rated 63▲
+2
changed 3d agoA102 tokens
originalMIT
Rephrase tasks and requests by avoiding Demand Avoidance triggers for someone with PDA autism spectrum disorder. It transforms demands into exploration and autonomous actions.
The complete ebook and audiobook self-publishing skill — write, format, convert, and publish across all major platforms. Use this skill whenever the user asks about Amazon KDP, Apple Books, Gumroad, Payhip, Kobo, Draft2Digital, IngramSpark, Barnes & Noble Press, Google Play Books, PublishDrive, StreetLib, ACX…
Run workflow-as-code jobs in Codex for large fanout, release diff review, security review, bug sweeps, adversarial verification, or multi-agent orchestration.
Reverse-engineer and pixel-perfect clone any live website, a single landing page or an entire site. Captures DOM, CSS design tokens, assets, fonts, and compiled-JS config data from the live page, reverse-engineers scroll animations and stateful interactions, rebuilds (raw-HTML mirror for static-export sites like…
A video-editing skill that turns professional editing practices into repeatable rules for an AI agent. It covers tasks such as cutting spoken videos, adding music and B-roll, adjusting color, using keyframes, masking, tracking, compositing, and exporting.
A Chinese-language writing aid that identifies and removes common formulaic or vague phrasing from drafts. It keeps the original facts, position, certainty, and meaning while making the text more direct.
End-to-end research paper generation, review, and revision for ML/AI/CV/NLP projects from repositories, notes, experiment logs, drafts, and conference templates. Use when building a paper story, mapping claims to evidence, writing or revising sections, producing figures and tables, verifying citations, acting as a…
Help researchers decide what must be checked before using AI, OCR, literature assistants, storage, or cloud services with research materials. Use for permission, privacy, provenance, institutional approval, retention, deletion, sharing, or incident-planning questions. Work from metadata and synthetic examples only…
Fine-tune an instruct LLM on a single text field containing prompt+answer using TRL's DataCollatorForCompletionOnlyLM, which masks the loss to only the answer tokens by detecting a response template string at collation time.
Turn any folder of files into a navigable knowledge graph with community detection, an honest audit trail, and three outputs: interactive HTML, GraphRAG-ready JSON, and a plain-language GRAPHREPORT.md.
The crow-cli map — where the source lives, how a running agent was spawned, and how to change, upgrade, or repair crow-cli itself. Use when the task touches crow-cli's own code or install ("fix crow-cli", "upgrade crow-cli", "reinstall", "where is the source", "the checkout", "crow-cli init", "project agent", "why is…
Map incidents, control checks and SCA results to ISO 27001:2022, PCI DSS v4.0.1, NIST SP 800-53r5 and CIS Controls v8.1 and write auditor-ready evidence statements; use for compliance checks, audit questions, or incidents on regulated assets.
Finds, previews, and resumes local coding-agent sessions using the showagent MCP server. Use when the user asks to search prior agent conversations, continue old work, branch a session, or transfer context between coding agents.
Cut a manual agent-afk release end to end. Auto-release was removed in #4146, so merging to main publishes nothing. This skill runs the read-only preflight (clean main equal to origin/main, CI green on that exact SHA, no publish in flight, npm in sync with the last tag), picks the semver bump from conventional commits…
Agent Browser Runtime for browsing, observing, and interacting with web pages via Chrome DevTools Protocol (CDP). Use this skill when Claude needs to: (1) navigate to and browse websites, (2) extract page content, text, or links from any URL, (3) fill forms or type into input fields, (4) click buttons or links on a…
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
★not rated 62 23d agoA64 tokens
copy · 88%MIT
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: