Software Development AI Skills

Execute tasks through systematic exploration, pruning, and expansion using Tree of Thoughts methodology with meta-judge evaluation specifications and multi-agent evaluation

Use Trellis channel for live multi-agent collaboration, spawned workers, cross-agent review, progress inspection, forum channels, and channel log debugging.

Verify that a stored Lathe tutorial actually works by following it end to end in a fresh scratch dir, in session. Use when the user invokes /lathe-verify with a slug like "/lathe-verify…

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Codex's capabilities with specialized knowledge,…

Use ONLY when the user asks to check, validate, review or audit analysis code for scientific correctness, or when you are the reviewer agent running its checks. Never run it unprompted as part of…

Fix GitHub issues end-to-end — analysis, branch creation, implementation, testing, and PR submission. Use whenever the user mentions fixing a GitHub issue, says "fix issue

Assesses whether and how an existing mobile product should migrate to React Native. Use when auditing one or more product repositories for migration readiness, including products whose iOS, Android,…

Query the local code graph (functions, classes, calls, imports) through the Deeplake mount at memory/graph/. Use when the user asks structural questions about the codebase — "what calls X?", "what…

Snapshot the computational environment for a replication package — detects the analysis stack (R / Stata / Python) and emits the right lockfiles (renv.lock + sessionInfo.txt, requirements.txt /…

Generate and publish concise, evidence-based notes in the body of the latest existing GitHub Release. Use only when the user explicitly invokes `$release-notes` or explicitly asks to update the latest…

Measure the flagship GAIA agent against Claude Code and across models — quality, truthfulness, steps, tokens, time and real cost — with `gaia eval tasks`. Use when asked to benchmark the agent,…

Web search and content fetching. Use when the user needs to search the web for information or fetch content from URLs.

Orchestrator skill for resolving multi-daemon binding contention. Use when you (the orchestrator) detect an `agent.binding.contested` sync event indicating two daemons are racing for the same agent —…

Comprehensive git worktree management. Use when the user wants to create, remove, list, or manage worktrees. Handles all worktree operations including creation, deletion, and status checking.

Manage ClaudeBar's GitHub Actions CI/CD pipelines: build, test, and release workflows. Use this skill when: (1) Setting up secrets for CI/CD (certificate, API key, Sparkle key, Codecov) (2) Creating a…

Use SDK with React, Vue, Svelte, Solid, Preact, and Web Components. sdkReady callback pattern, reactive props, and framework-specific setup. Load this skill when embedding LiveCodes in a framework…

Cut a brooks-lint release: set the version in package.json, propagate it across all four plugin manifests and every version-bearing text file (README badges, docs site metadata), write the CHANGELOG…

Explore the codebase to understand a task before planning. Write findings to .agtx/research.md and stop. This is a read-only exploration — do not modify any files.

Create robust browser automation skills for sites like LinkedIn, X/Twitter, YouTube, Stripe, or other logged-in web apps by saving page context, analyzing HTML/CSS, writing skill-local JS…

Read-only evo run reporting. Use when the user invokes /evo:report, asks what happened overnight, asks what improved recently, asks for the best/frontier candidates, asks for a quick score chart…

Intelligent media optimization with automated workflows for images, videos, and SVGs. Includes decision trees that detect LCP images (triggers format/lazy-loading/priority analysis), identify layout…

Restart the Vellum assistant and gateway services. Smart branch handling: pulls from main by default, restarts in-place on feature branches, or switches to a specified branch. Pass --pull to…

Create learning paths for programming tools, and define what information should be researched to create learning guides. Use when user asks to learn, understand, or get started with any programming…

Provision and launch the Simulation Challenge baseline inference model end to end: clone the inference code from a given git repo/branch, download the checkpoints from ModelScope into the repo's local…

Run /debug to find and fix a bug's root cause: a test failing for an unclear reason, /check verify finding a failure, or behavior being wrong. Runs a reproduce, localize, hypothesize, test, fix,…

Fix Provider, Collector, Transformer compilation errors

JWT attack playbook — algorithm confusion (alg=none, HS/RS confusion), kid path traversal/SQLi, jku/x5u SSRF, weak HS256 cracking, and embedded JWK trickery. Use when the target uses JWTs for auth…

通过微信按关键词列表与指定联系人自动聊天。当用户提到微信自动回复、关键词回复、微信机器人聊天时使用。

Detect GraphQL injection vulnerabilities in a codebase using a three-phase approach: recon (confirm GraphQL usage and find unsafe operation document assembly sites), batched verify (trace user input…

巡查 Skill — 通过 CLI 工具巡查任务状态、标记异常、发送告警

Under genuine uncertainty with no reliable forecast, inventory means, cap downside at affordable loss, act for commitments, and let goals emerge from controllable moves.

Takes existing content markdown files and builds production-final resource center pages on client websites using their existing tech stack and design system. Output is live-ready — no review pass, no…

Java logging best practices with SLF4J, structured logging (JSON), and MDC for request tracing. Includes AI-friendly log formats for Claude Code debugging. Use when user asks about logging, debugging…

Hunt broken function-level authorization via verb drift, route shadowing, and transport gaps.

Report the compatibility redirect to `ap-worker`; this retired role cannot perform new work.

Saves user instructions as persistent learnings for future sessions. Use when the user says 'remember this', 'always do X', 'from now on', 'never do Y', or gives any instruction they want persisted…

Set up an end-to-end test suite in any repo, following practices that make e2e a reliable per-PR gate: real flows over bypass, layered assertions, a reusable auth/session helper, video+trace evidence,…

Iteratively improves a PR (GitHub), MR (GitLab), or shelved changelist (Perforce) until Greptile gives it a 5/5 confidence score with zero unresolved comments. Identical to greploop, but triggers…

Analyze Swift Package Manager dependencies, package plugins, module variants, and CI-oriented build overhead that slow Xcode builds. Use when a developer suspects packages, plugins, or dependency…

Watch an open PR — fix failing CI, handle the straightforward review comments, and drive it to a mergeable state. Claude Code analog of Cursor's built-in /babysit. Use after opening a PR when the user…

Configure the browser tool for Clacky. Guides the user through Chrome or Edge setup, verifies the connection, and writes ~/.clacky/browser.yml. Supports macOS, Linux, and WSL (Windows Chrome/Edge via…

行业情报雷达：多源扫描(X/即刻/V2EX/HN) → 关键词过滤 → 趋势检测 → 每日情报简报。触发词：行业情报、竞品监控、热点扫描、情报雷达

ALWAYS invoke this skill when work wraps up or the user asks how it went - "done or not", "are we done", "what happened", "report", "what's the status of this ticket" - in any language, and when a…

Deterministic gate for ONE already-computed polygenic score result and ONE person: returns SUPPORTED (raw score, standardised score and reference percentile may be shown), RAW_ONLY (raw score only) or…

Desktop JVM and build traps: JNA natives, bundling, memory, packaging, code signing, R8, deep links, Gradle and CI releases. Use when a desktop build fails packaged, signed, on another OS or arch, or…

Sweep a whole running web app for what is broken, without writing a script or knowing the codebase. Clicks every reachable control and reports dead buttons, console errors, failed requests, and places…

Open every git worktree of a project in one VS Code window, each folder labeled by its agent session's title. Use for /worktree-workspace, reviewing worktrees in VS Code, or seeing which worktree…

Extracts text and tables from PDF files, fills PDF forms, and creates/merges/splits PDF documents. Use when users mention PDFs, forms, document extraction, or PDF generation.

ASCII art: pyfiglet, cowsay, boxes, image-to-ascii.

Audit active project plan files for staleness, completion, and routing truth. Use when cleaning up plans, reconciling active work, or archiving completed artifacts.

Transforms vague prompts into optimized Claude Code prompts. Adds verification, specific context, constraints, and proper phasing. Invoke with /best-practices.