Update a markdown file section with an index/table of files from a specified folder.
Score 70/100
Efficiently bring upstream NanoClaw updates into a customized install, with preview, selective cherry-pick, and low token usage.
Score 70/100
Update an existing pull request with new changes. Use when the user wants to update a PR, push follow-up changes to a PR, refresh a PR description, or sync a PR with latest…
Score 70/100
Process the practices inbox, evaluate, incorporate into dotforge, and suggest propagation to projects.
Score 70/100
Use when updating docs, syncing CLAUDE.md or README.md, fixing stale documentation, or refreshing project rules and skills. Keeps docs aligned with code changes.
Score 70/100
Add new or remove obsolete model IDs for existing AI SDK providers. Use when adding a model to a provider, removing an obsolete model, or processing a list of model changes from…
Score 70/100
Refresh README structure and content using repo context from git-workspace-review
Score 70/100
Bump build script version examples in README.md + README.ru.md after a release. Keeps "powershell build.ps1 -Version 'X.Y.Z-rN'" + "./build-mac.sh X.Y.Z-rN" snippets in sync with…
Score 70/100
Use GitHub Next's update-docs workflow when code changes should trigger documentation maintenance instead of waiting for humans to remember it later.
Score 70/100
Update requirements and cascade changes to specs and plans. Accepts natural language change descriptions to modify the full spec chain.
Score 70/100
View, add, modify, or remove project rules in `.claude/rules/`. 管理項目開發規則。 Use when: update rules, add a rule, edit a rule, remove a rule, manage rules, add rules for a new module
Score 70/100
Actualizar el contenido de un SKILL.md existente para mejorar su precisión, completitud y claridad. Cubre el incremento de versión, el refinamiento de procedimientos, la expansión…
Score 70/100
Create or update repository skills and instructions when major learnings are discovered during a session.
Score 70/100
Update an existing specification file for the solution, optimized for Generative AI consumption based on new requirements or updates to any existing code.
Score 70/100
ストア情報の更新自動化 — スクリーンショット撮影（シミュレーター × モック画面 × Marionette MCP）とメタデータテキスト更新。ストア更新、スクショ更新、App Store / Google Play のメタデータ更新、リリースノート作成の際に使用すること。
Score 70/100
Scan Apple's SwiftUI documentation for deprecated APIs and update the SwiftUI Expert Skill with modern replacements.
Score 70/100
Use when the user wants to update their X (Twitter) profile: bio, display name, location, website URL, avatar, or banner image. Each field update requires explicit user approval.
Score 70/100
Automatically detect and update outdated Claude Code skills. Use when the user says "update skill", "updateskill", "refresh skill", "skill is outdated", "sync skills", or…
Score 70/100
Automate Updown IO tasks via Rube MCP (Composio). Always search tools first for current schemas.
Score 70/100
Upgrade upstack to the latest version. Detects global vs vendored install, runs the upgrade, and shows what's new.
Score 70/100
Clean up after (or abandon) a Rails upgrade. Drop NextRails.next? and NextRails.current? branches and retire dual-boot scaffolding (Gemfile.next, Gemfile.next.lock, conditional…
Score 70/100
Use when user mentions "upload", "data collection", "file specifications", "data units", "organize files", "map files to specs", "bulk upload", "s3 upload", "cloud storage",…
Score 70/100
Automate Uploadcare file management including listing, storing, inspecting, downloading, and organizing file groups through natural language commands
Score 70/100
An ASE skill built around Upptime, the open source uptime monitor and status page system powered by GitHub Actions, Issues, and Pages.
Score 70/100
Upscayl is a free, open-source AI image upscaler for Linux, macOS, and Windows. It uses Real-ESRGAN models with Vulkan GPU acceleration to enhance low-resolution images,…
Score 70/100
Full sprint flow: /plan -> /execute -> /validate -> /review -> /ship-pr. Always runs /plan (which auto-detects small follow-ups via fast-path). Loops review/execute until clean.
Score 70/100
Upstash QStash expert for serverless message queues, scheduled jobs, and reliable HTTP-based task delivery without managing infrastructure.
Score 70/100
Interact with Upstox API v2 — fetch portfolio, live market data, place orders, and check P&L for Indian equity and F&O markets
Score 70/100
用于这个仓库中“先分析 upstream 提交与代码变更，再按功能主题选择性引入 upstream 变更；所有操作在临时 worktree 中完成，并在难解冲突时优先保留当前 fork 实现”。当用户提到 upstream sync、同步源仓库、选择性合并 upstream、分析上游提交、挑功能合并等意图时使用。仅适用于 nervmor/codexui…
Score 70/100
Interfaces with the Uptime Kuma Socket.IO API to monitor service health checks. Syncs status page data to Statuspage.io via Atlassian REST API and triggers incident workflows in…
Score 70/100
Manages bulk uptime monitoring via the Uptime Robot API v2. Creates HTTP, keyword, and port monitors with alert contacts, maintenance windows, and status page synchronization.
Score 70/100
Integrates with the Uptime Robot API to monitor status page changes and push webhook alerts to Slack or PagerDuty.
Score 70/100
Automate Uptimerobot tasks via Rube MCP (Composio). Always search tools first for current schemas.
Score 70/100
Homer L3 — Measurement Muse. Pulls numeric receipts from Toke telemetry (decisions.jsonl, _learnings.md, stats-cache.json, Homer VAULT, brain scans).
Score 70/100
Expert skill for robot model creation and validation in URDF and SDF formats. Generate URDF files with proper link-joint hierarchy, create Xacro macros, calculate inertial…
Score 70/100
Production-ready URP HLSL/ShaderLab code templates with SRP Batcher compatibility for Unity
Score 70/100
American business English writing style for professional communications. Direct, action-oriented, EN-US spelling.
Score 70/100
Track and analyze US government shutdown liquidity impacts by monitoring TGA (Treasury General Account), bank reserves, EFFR, and SOFR data from FRED API.
Score 70/100
Assess US state privacy law compliance — VCDPA, CPA, CTDPA, UCPA, and emerging laws
Score 70/100
Report real Claude Code session-quota state — percent of the 5-hour and 7-day windows used, reset times, and status (ok/warning/rejected).
Score 70/100
Usage-based pricing in Revenue Cloud: metered billing, usage records, rating, tiering, consumption schedules. NOT for CPQ flat-rate discounts (use revenue-cloud-cpq-setup).
Score 70/100
Optimize Claude Code sessions for Max-plan usage limits. Use when users ask about token/context savings, CLAUDE.md compression, noisy tool output, quota burn, drift protection,…
Score 70/100
Analyze Claude Code usage trends over time using the Agent Monitor's analytics API — daily session counts, daily event counts, token volumes by type, model distribution, tool…
Score 70/100
Answer questions about the AI SDK and help build AI-powered features. Use when developers: (1) Ask about AI SDK functions like generateText, streamText, ToolLoopAgent, embed, or…
Score 70/100
Write and run AILANG code with correct syntax. Use when user asks to write AILANG programs, fix AILANG syntax errors, run AILANG code, or needs help with AILANG syntax.
Score 70/100
Start with cheap static fetches, escalate to a browser only when needed, validate findings, and turn the result into a production-ready scraping approach.
Score 70/100
Full reference for the beads task management workflow. Use when working with beads issues, planning multi-step work, or managing task lifecycle.
Score 70/100
Reference for using Codefresh via the CodeFresh CLI. Use when a Codefresh CI check is failing in a recursionpharma PR, or when working with Codefresh builds.
Score 70/100
Sets the active company context or diagnoses company routing. Two modes: (1) Set — declare which company to work with, bypassing auto-detection.
Score 70/100
Scan conductor/ directory for project direction, workflows, and task planning when present
Score 70/100
Use Expo DOM components to run web code in a webview on native and as-is on web. Migrate web code to native incrementally.
Score 70/100
从外部 skills 库（~/.agents/skills）中查找、匹配并加载最合适的 skill 指令。注意：本 skill 专门用于操作外部 skill 库，加载本项目内置 skill 请使用 skill_load
Score 70/100
【大型代码库分析专用】当需要分析整个项目架构、识别代码模式、追踪功能实现、梳理模块关系时必须使用本技能。触发关键词：分析整个项目/代码库、架构梳理、模块划分、代码模式识别、功能追踪、全局扫描。本技能通过 Gemini CLI 快速扫描完整代码库，提供 AI 驱动的架构洞察和代码分析，大幅节省手动探索时间。仅返回原始分析结果，不做二次解读。
Score 70/100
Replace OneCLI gateway with the built-in credential proxy. For users who want simple .env-based credential management without installing OneCLI.
Score 70/100
Full reference for the trekker task management workflow. Use when working with trekker issues, planning multi-step work, or managing task lifecycle.
Score 70/100
Conception de parcours utilisateurs et flows d'interaction optimaux. Se déclenche avec "user flow", "parcours utilisateur", "flow", "onboarding flow", "checkout flow",…
Score 70/100
Resolve user-input attachment triggers before running later thread-safe attachment builders so dependent state is in place.
Score 70/100
Set up babysitter for yourself. Guides you through onboarding — installs dependencies, interviews you about your specialties and preferences, builds your user profile, and…
Score 70/100
Serialize announced command and skill surfaces from a shared capability shape, excluding entries explicitly marked non-user-invocable.
Score 70/100
Detect user's technical level from first messages. Adjust all output language accordingly.
Score 70/100