Engineering
Iterate
Fully automated multi-round code iteration with configurable N-dimension parallel review, onboarding/personalization, and a cross-assistant installer/update system with mandatory S…
Engineering
abvx-agent-skills
Auditable cross-platform coding-agent skillpack for smaller diffs, evidence-led debugging, token control, browser verification, and reviewable `SKILL.md` workflows with static secu…
Engineering
code-workflow
4-stage code-change workflow: research → plan → user review → implement (TDD). Topics — steps (Step 0-3: resume + research + plan + review + branch), implement (Step 4: TDD + build…
DevOps
git-workspace-review
Verifies workspace state and staged changes as a read-only preflight. Use before commits or PRs to confirm staged set is clean and correct
Productivity
metacognitive-self-mod
Analyze and improve the improvement process. Use for detecting regressions and meta-optimization
DevOps
damage-control
Recovers broken agent state via crash recovery, context overflow, and merge conflict protocols
Research
call-chain
Traces execution paths through the code graph with criticality scoring and Mermaid charts
Engineering
error-patterns
Provides error classification, recovery, and graceful-degradation patterns
Engineering
python-performance
Profiles Python code for performance bottlenecks and memory issues
Testing
subagent-testing
Test skills via TDD in fresh subagents
Testing
bug-review
Hunts bugs with evidence trails
Engineering
ai-coding-ok
USE THIS SKILL FIRST on any coding task (feat, fix, bug, refactor, plan, design, brainstorm, code review, implement, add feature, write tests, 新功能, 修复, 重构) when the project contain…
Productivity
coding-agent-sessions
MUST USE when asked to find, read, list, search, inspect, fetch, export, or reconstruct coding-agent sessions across Codex, Claude Code/Desktop, OpenCode, OMO/Senpi/pi, oh-my-pi (o…
Productivity
coding-agent-sessions
MUST USE when asked to find, read, list, search, inspect, fetch, export, or reconstruct coding-agent sessions across Codex, Claude Code/Desktop, OpenCode, Senpi/pi, oh-my-pi (omp),…
Engineering
metrognome
Autonomous, scientific React Native & Expo performance optimization via a propose -> measure -> keep/revert loop. Use this WHENEVER an RN/Expo app is slow, laggy, janky, stuttering…
Engineering
cakephp-migration
baserCMS の CakePHP バージョンアップ（5.0 → 5.1 → 5.2 ～）対応の非推奨・破壊的変更パターン集と修正レシピ。「Association alias already set」「A validation rule with the name already exists」「_Token not found」「headers alre…
Engineering
effective-git
Use for any git operation, especially destructive ones. Prevents lost work from `git reset --hard`, `git push --force`, `git rebase`, `git clean`, `git branch -D`, `git checkout`, …
Engineering
alfa2-development
Guía obligatoria para desarrollar el bot ALFA-2 (reconstrucción modular limpia de ALFA-1). Triggerea cuando el usuario menciona "ALFA-2", "alfa2", "alfa2-clean", "samaritan", "fase…
Automation
agent-devtools
Browser automation and web debugging CLI for AI agents. Use when the user needs to interact with websites, fill forms, click buttons, take screenshots, extract data, test web apps,…
DevOps
via54macfix
Use when installing or running native macOS binaries (via54, via54-mcp, feishu, or any Go binary) on macOS 12+/Sequoia, especially when launchd auto-start, Gatekeeper, or codesign …
Engineering
zig
Build, modify, debug, test, optimize, migrate, and review Zig applications and libraries. Use for `.zig` source, coding style, API design, `build.zig`, `build.zig.zon`, dependencie…
Engineering
impeccable-flutter
Use when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a Flutter f…
Web
dev-inspector
Pick elements in the running dev app's browser and hand them to Claude. When the user refers to "this button", "that card", "the element I just clicked", or anything they've select…
Web
odoo-19.0
Odoo 19 development knowledge base with 18 specialized guides covering Actions (ir.actions.*, cron jobs, server actions), Controllers (HTTP routing, endpoints, auth types), Data fi…
DevOps
wifi-optimizer
Diagnose intermittent Wi-Fi buffering, lag, packet loss, jitter, weak coverage, interference, roaming or MLO compatibility, and congestion; safely optimize authorized router settin…
Productivity
coding-agent-sessions
MUST USE when asked to find, read, list, search, inspect, fetch, export, or reconstruct coding-agent sessions across Codex, Claude Code/Desktop, Aside, OpenCode, Senpi/pi, OpenClaw…
Web
odoo-17.0
Odoo 17 development reference for Python models and ORM (search, domain, read_group, compute fields), XML/CSV data and views, OWL/JS client code, QWeb reports, security (ACL, recor…
Web
odoo-18.0
Odoo 18 development reference for Python models and ORM (search, domain, read_group, compute fields), XML/CSV data and views, OWL/JS client code, QWeb reports, security (ACL, recor…
Testing
go
Opens the running app in a browser and verifies recent UI changes actually work. Use whenever the user wants a quick smoke test or sanity check of recent work, or says "go", "open …
DevOps
agentburn
Local read-only profiler for where an always-on agent burns money. Splits spend by source (cron, gateways, subagents, CLI), isolates the overnight window, walks message logs for re…
Web
modals
Use when editing Modal.jsx, useFlipModal, AddInnerModal, ConfirmCancelButtons, ErrorModal, SuccessModal, FilterModal, HelpModal, SelectMenu, profileModal/*, or when adding a new mo…
Engineering
project-generalist
Skill raíz para proyectos de software existentes o nuevos. Inspecciona el repo, detecta stack (Laravel, Node, React, Next, Inertia, Vue, Angular, Ionic, Capacitor), clasifica la ta…
Engineering
mysql-query-optimization-skills
Diagnoses and tunes slow MySQL/Aurora queries using EXPLAIN ANALYZE evidence—row counts, loops, pages touched—then applies proven rewrites such as ROW_NUMBER for max-per-group, con…
Testing
pulser
Diagnose and test Claude Code skills against Anthropic's 7 principles. Scans SKILL.md files, checks 8 rules (gotchas, description, allowed-tools, file-size, structure, frontmatter,…
Productivity
cerebro-doctor
Meta-audit of the skill system. Walks `{brain_root}/skills/` + `{brain_root}/AGENTS.md` and reports three classes of drift: (a) skills with no resolver row (unreachable), (b) AGENT…
Engineering
midnight-contract-deployment
Use this skill when the user asks to deploy a Midnight smart contract, compile Compact 0.30.0 code, debug Midnight SDK 4.x errors, write integration tests for Midnight DApps, or se…
Engineering
claude-code-agents
Invoke Claude Code from Codex for bounded delegation to Claude Code agents or subagents. Use when the user explicitly asks to run, invoke, compare with, or delegate work to Claude …
Engineering
clojure-repl
Use this skill whenever you need to evaluate Clojure expressions in a REPL — for iterative development, debugging, API exploration, or validating code before saving to files. Cover…
Engineering
fix-proguard-model
Diagnostica y arregla errores de release build Android causados por R8/ProGuard eliminando u ofuscando modelos de datos, DTOs o data classes usados por serialización/reflection. Us…
Engineering
go-pro-max
Go development intelligence. 12 domains, 10 stacks, 300+ entries. Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check Go code.…
Engineering
brutal-agent
Orchestrate subsystem-by-subsystem project hardening by combining brutal-project-review and task-worker in a strict loop: review one subsystem, create CRITICAL/MAJOR tasks, run all…
AI / ML
pytorch-tutor
Use when generating, writing, modifying, or explaining PyTorch code (models, nn.Module, training loops, tensors, dataloaders, losses) for a learner who wants beginner-friendly Chin…
Engineering
m5stack-arduino-cli
Set up, diagnose, flash, and support development for M5Stack boards with Arduino CLI on Windows. Use when Codex needs to install ESP32 board support, detect the correct COM port, e…
Engineering
optflow
Discover and deliver repository optimization work end to end: identify performance, reliability, maintainability, security, DX, and cost optimization points, prioritize by impact-e…
DevOps
gcp-networking-observability
Investigate GCP network issues by analyzing VPC Flow Logs, firewall logs, Cloud NAT logs, threat logs, and networking metrics. Diagnose connectivity, packet loss, top talkers, and …
Engineering
fix-issue
Fixes GitHub issues using parallel analysis agents for root cause investigation, code exploration, and regression detection. Reads issue context from gh CLI, searches codebase and …
DevOps
ssh-command-screenshot
Run SSH commands in Windows Terminal and capture per-command screenshot evidence into a new folder. Use early whenever a task involves Linux/Unix system inspection, troubleshooting…
Design
figma-pixel
Figma-to-frontend visual QA workflow for building pages from Figma designs and tightening existing implementations. Captures the target page, exports the selected Figma frame, runs…
DevOps
llm-gateway-incident-triage
Diagnostic playbook for triaging a self-hosted LLM gateway (LiteLLM or any Postgres-backed OpenAI-compatible proxy) running via Docker Compose on a homelab host. Use when a client …
Security
ciphertext-recovery
ARM64 trace ciphertext recovery methodology. Use when given an ARM64 execution trace file and asked to reverse-engineer encryption, signature, or encoding algorithms from ciphertex…
Engineering
minor-defect-fix
Handles Jira minor-defect tickets end-to-end: analyzes the issue, patches the code, expands tests to 80% coverage, syncs specs in the separate repo, logs progress in Jira, and prep…
Testing
qa
Behaviour QA of a PR/branch before merge in ayunis-core — spin up an isolated dev slot, seed, drive the changed flow end-to-end (API + headless browser), assert acceptance criteria…
Engineering
file-organizer-dev
Development guide for the File Organizer MCP server codebase. Use when (1) adding new MCP tools, (2) adding new services, (3) modifying existing tools or services, (4) writing test…
AI / ML
mlx-model-porting
Guides and validates architecture-aware ports of PyTorch/Hugging Face models to Apple MLX, inspects existing local MLX projects, and plans evidence-gated optimizations for Apple Si…
Testing
flake-axis-bisection
Isolates the trigger behind a known-flaky test by varying one axis at a time—order, isolation, workers, viewport, latency, repetition—while tracking pass/fail counts and checking w…
Testing
parity-diff
Detects and classifies deterministic visual, property, and ARIA diffs between baseline and replacement apps using pixel, trait, and accessibility checks. Routes only “is this diff …
Engineering
hotplex-diagnostics
Runtime diagnostics for HotPlex Gateway. Narrows symptoms to root cause for worker crashes, slow responses, session issues, feedback interruptions, and pipeline problems. Detects s…
Testing
parity-replace
Performs parity-based replacement: partitions a feature into page-level phases, fills locator-mapping gaps, and runs adversarial review on uncommitted diffs. Reads current code as …
Productivity
antigravity
Use Google Antigravity CLI (agy) for code review, adversarial review, debugging, long-running task delegation, or large-context investigation. Hands off to agy's large-context wind…
Engineering
halcon-skill
Generate, refactor, run, and review HALCON HDevelop (`.hdev`) and HDevelopEVO (`.hscript`) programs with accurate operator usage, parameter defaults, value ranges, and practical vi…
Showing the top 60 of 12,764. See the full list →