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.
A guide for controlling a Paperang Gen 2 thermal printer, a small printer that uses heat-sensitive paper. It covers text, images, QR codes, self-tests, paper feeding, and serial-port settings.
Write Thai-language prose (technical documentation, marketing copy, explainers, blog posts, translations) that reads like a real Thai writer — not generic AI output. Counters training-data skew toward over-formal, over-polite, calqued Thai. TRIGGER when: user asks for any non-trivial Thai prose output (paragraph or…
Guide complete FileMaker Pro migrations from DDR XML to verified discovery, schema, authorization, business-logic, API, UI, and cutover artifacts. Use when analyzing FileMaker Database Design Report XML or parsed specs, comparing implementations, recovering scripts/calculations/layout/security semantics, recommending…
Talk to your Garmin data naturally - "what was my fastest speed snowboarding?", "how did I sleep last night?", "what was my heart rate at 3pm?". Access 20+ metrics (sleep stages, Body Battery, HRV, VO2 max, training readiness, body composition, SPO2), download FIT/GPX files for route analysis, query elevation/pace at…
Implement Clean Architecture with domain, application, and infrastructure layers. Use when creating modules, organizing code in layers, separating business rules from infrastructure, or structuring a new project.
Automatically install and manage Agent Skills from GitHub repositories. Use when asked to "install a skill", "add a skill", "find skills", "browse skills", "get skills from GitHub", or when the user needs a specific capability that might exist as a community skill. Supports anthropics/skills, github/awesome-copilot…
Generate or refresh project documentation artifacts including surfaces.yaml and codemaps. Use when the user needs to initialize project docs, update codemaps after changes, or create AI-readable project overviews.
Daily cost reporting + session hygiene for OpenClaw deployments. Tracks per-session API spend, shows 7-day trend, and wipes zombie sessions >24h old to prevent context snowball. Zero personal info — configure with your own paths and Discord channel. Runs nightly via cron.
Add a "code mode" tool to an existing MCP server so LLMs can write small processing scripts that run against large API responses in a sandboxed runtime — only the script's compact output enters the LLM context window. Use this skill whenever someone wants to add code mode, context reduction, script execution, sandbox…
A template for writing instructions for a new skill, with placeholders for its name, purpose, workflow, limits, inputs, and outputs. It is written in Traditional Chinese and expects materials in an input folder and results in an output folder.
Use when a code change has multiple plausible implementation paths, high regression risk, uncertain root cause, or unclear tradeoffs. Creates isolated candidate implementations, runs comparable verification across each candidate, compares evidence, and applies the best proven approach while preserving user changes.
Use when working with Core Memory from OpenClaw, including finalized-turn writes, memory retrieval, bridge behavior, semantic bead fields, promotion, claims, associations, or integration debugging.
Analyzes the codebase, creates project documentation, generates a rebuildable codebase index, and updates AGENTS.md. Used during /5:implement CONFIGURE.
Create skills for automating Windows desktop applications on WorkSpaces via computer use tools. Use this skill whenever someone wants to create a new application skill, improve an existing desktop automation skill, or document how to interact with a specific Windows application (e.g., Excel, Notepad, Paint, File…
Query a configured MySQL data source for read-only analysis, reporting, and schema exploration. Use SQL discovery and validation tools, honor tenant Scope when trusted SaaS context is present, and never invent database or table names.
Realise a user-gate validation of an artifact (spec, plan, or any document) through the configured backend. The single canonical implementation of the backend-configurable gate protocol — CrewRig lifecycle stages and any external workflow invoke this skill instead of reimplementing a gate inline. Backends: plannotator…
Use when building a RAG pipeline that ingests PDFs, Excel, CSV, or images — especially when debugging silent data loss, choosing between OCR tools, or handling edge cases like scanned pages, merged cells, or embedded charts.
Export Dev Graph UI assets and dashboard data. Use when the user asks for structure SVG exports, timeline SVG/MP4 exports, per-commit SVGs, sprint-linked visuals, or dashboard/analytics JSON from the Dev Graph API.
Cross-agent terminal process hygiene for Codex and Claude Code. Use before running terminal commands that may open shells, dev servers, watchers, workers, bots, miners, indexers, daemons, Docker/Kubernetes foreground processes, or any Node/Python/Rust/Go/Java/PHP/.NET command whose normal success state is to remain…
Diagnose any AI agent, automation workflow, or proposed agent build against AAC 2.0 and produce a marketing-grade HTML wellness report (Summary view + Process Map view). Always use this skill when the user asks to evaluate, audit, score, diagnose, map, visualize, or "AgentTwin" an AI agent, automation, workflow…
Interview the developer about their Ruby on Rails project (app type, database, frontend stack, background jobs, deployment target, traffic profile, compliance, current Rails version) and then route to the right downstream rails-skills. Use at the start of any new Rails work session, when the user says they want to…
Specialist for building features inside an s&box game project via the s&box Codex Bridge. Use when handing off a self-contained game-dev task — a new gameplay system, animation, UI panel, ability, world-gen pass — that benefits from focused execution with the screenshot-driven workflow. Pair with the…
WHEN: User asks for a code quality audit, code review, or wants to find code smells, anti-patterns, or non-idiomatic Go code in their project. Also when asked "how good is this code?" or "audit my code." WHEN NOT: When the user wants to fix bugs, run tests, or just lint (use go-lint-audit for linting).
Guided onboarding for OpenSpec - walk through a complete workflow cycle with narration and real codebase work.
★not rated 21 6mo agoA26 tokens
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: