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.
trnt-ai/trent-openclaw-security-assessment
Skill Claude Code
Deprecated: this skill no longer works. Trent now secures OpenClaw through its main security engineer at trent.ai. Install nothing; read the notice.
Skill Claude CodeCodex
A workflow for reading the LaTeX source of arXiv papers and producing structured Chinese summaries or blog content. arXiv is an online repository where researchers share scientific papers.
zhiningo/drawio-flowchart-skill
Skill Claude CodeCodex
Generate draw.io (.drawio) flowchart XML files. Use when the user asks for a flowchart, process diagram, workflow diagram, or any visual diagram in draw.io / diagrams.net format. Produces well-structured, visually clean .drawio files with proper alignment, hierarchy, and readable text. NOT for: Mermaid diagrams, ASCII…
joshOrigami/netsuite-developer
Skill Claude CodeCodex
Disciplined NetSuite SuiteScript 2.1, SuiteQL, SDF, and integration development with optional metadata provider contract and QA verification steps.
Skill Claude CodeCodex
Generate crypto automation bot scripts from endpoint docs.
Skill Codex
Design and create traceable loop systems for user tasks. Use when the user invokes /loop-skill or asks to build, design, scaffold, run, or improve an iterative workflow with generations, audits, rewrites, logs, validators, max iterations, and explicit exit conditions.
Skill Claude CodeCodex
Counts lines, words, and bytes in a text file using the bundled count.sh script. Use when asked to count/measure a file's size in these terms.
aurorascharff/agent-friction-skill
Skill Claude CodeCodex
Use automatically immediately before the final response of every software-development task, after implementation and tool calls are complete. Review the full session for framework or tooling friction that caused a meaningful detour or is likely to recur. Offer to create a review draft when something qualifies, and…
Skill Claude CodeCodex
An AI briefing tool with two documented steps: planning a report from a query and fetching data from its task configuration.
Skill Claude CodeCodex
A set of optional ways to interpret evidence about people in a personal wiki. It changes how existing information is examined, but does not add evidence or authorise wiki edits.
Skill Claude CodeCodex
A reading-data assistant for WeRead, a Chinese online reading service. It works with personal bookshelves, reading progress, notes, highlights, reviews, and reading statistics.
Skill Claude CodeCodex
How to use Memento — a local-first MCP memory layer for AI assistants — to remember and recall durable knowledge about the user, their preferences, conventions, decisions, and projects across sessions. Trigger this skill whenever the user has Memento connected and any of the following happens, even when the user does…
Skill Claude CodeCodex
Run Lofn music/audio pipeline, Suno-ready prompts, lyrics, song guides, and music production briefs. Do NOT use for static image prompts, QA audit, or final ranking.
Skill Claude CodeCodex
Use when a user is trying to discover an installable or reusable skill or workflow, especially when they ask for a skill for a task, want to compare nearby skill categories, or need help narrowing discovery results.
Skill Claude CodeCodex
Apply schema migrations safely: detect the tool, classify the change by risk, gate destructive ones behind approval, back up in prod, preview-apply-verify, roll back on failure. Use when a schema change is about to be applied to any environment.
amm10090/fanqie-publisher-skill
Skill Claude CodeCodex
Publish prepared novel chapters from local Markdown files to the Fanqie Novel writer web backend via browser automation. Use when the user wants to upload chapters, continue publishing unpublished chapters, save or reuse login state, or schedule Fanqie chapter releases from a local directory.
Skill Claude CodeCodex
This skill should be used when the user asks to "test my specs", "validate my design docs", "find gaps in my architecture", "stress-test the spec", "vibe test", "pressure test the docs", or mentions spec validation before implementation begins.
Skill Claude CodeCodex
Lanhu to Code workflow for Claude Code. Convert Lanhu design URLs into Vue/React frontend code with component reuse, design token mapping, TODO-safe business logic, and optional code review.
Skill Claude CodeCodex
Use instead of chaining 3+ Bash calls, grep/cat/find pipelines, or any multi-step data processing. This skill should be used when the user asks to "start a scratchpad", "use the REPL", "scratchpad mode", "persistent Python session", or when a task involves exploration, analysis, or file processing that would benefit…
Skill Claude CodeCodex
Comprehensive guide for AI assistants on using the StringExtensions and StringHelper APIs.
Gratia2533/pipe-stock-analysis
Skill Claude CodeCodex
A stock-research workflow for Taiwanese and global companies. It routes each market to its available data sources and combines technical, financial, news, event, risk and scenario information.
Skill Codex
Use when dotcraft-unity MCP, CLI, or unityexecutecsharp is available, or when the user asks to inspect, automate, capture, or debug Unity Editor state, scenes, assets, Console logs, or GameView output. Provides background-first Unity Editor automation through MCP or CLI.
ankaboot-source/supabase-selfhost-ops
Skill Claude CodeCodex needs its repo
The protocol rests on ten invariants. Every agent (CI or local harness) and every human interacting with boucle MUST honor them. The LESSONS.yml lessons are incident catalogs that instantiate these invariants; the normative statement lives here.
Skill Claude Code needs its repo
Use when the user mentions m1nd or when repo investigation, search, review, docs/spec work, or risky change prep should go through m1nd first before grep, glob, or manual file reads. Covers m1nd-first routing, L1GHT and universal document ingestion, risky edit preparation, document-to-code binding, the served owner +…
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: