Intelligent code cleanup with mainline detection, stale artifact discovery, and safe execution. Supports targeted cleanup and confirmation.
Skills(SKILL.md)は、AIエージェント(Claude Code、Cursor、Codexなど)に特定の能力を追加するための設定ファイルです。
詳しく見る →Intelligent code cleanup with mainline detection, stale artifact discovery, and safe execution. Supports targeted cleanup and confirmation.
Investigate and fix a Sentry issue in this codebase. Use when the user provides a Sentry issue URL or ID and wants diagnosis, a fix, verification, or a PR.
Use to browse or verify external info—run web searches, open pages, drive Chrome via CDP tools, and cite sources when facts may be outdated, niche, or user-requested.
Initiate or respond to sibling contract sync — advisory only, non-blocking. Both sides update local peer topology copies.
Full autonomous engineering workflow
Issue tracking with Beads (bd CLI). Use when commands need to create, query, update, or close issues, or manage dependencies.
Sync workflows for Workbench CLI. Use when aligning local work items with GitHub issues, creating branches, or reconciling doc backlinks.
Check the current Railway project status for this directory.
'[DEPRECATED] Use /ce:compound instead — renamed for clarity.'
Business logic, order lifecycle, workflow states, quality gates, and pricing rules. Use when implementing order features or understanding business workflows.
'Stage, commit, and push changes with conventional branch prefixes and safety checks. Use when the user asks to commit, push, save, or publish local changes to GitHub, or wants a standard commit workflow in this project.'
Gather phase context through adaptive questioning before planning. Use --auto to skip interactive questions (the agent picks recommended defaults).
Full autonomous engineering workflow using swarm mode for parallel execution
Navigate and analyse repository structure in Codex sessions. Use when locating symbols, tracing references, or summarising architecture before editing.
Plan a sprint with capacity estimation, story selection, dependency mapping, and risk identification. Use when preparing for sprint planning, estimating team capacity, selecting stories, or balancing sprint scope against velocity.
Orchestrate the release team: coordinates release-manager, qa-lead, devops-engineer, and producer to execute a release from candidate to deployment.
Announce: "I'm using the /do skill to orchestrate feature development with lifecycle tracking."
Use when the user wants Compass BMAD automation wrappers, Beads-aware orchestration, approval gates, or resume/retry behavior instead of a single manual workflow.
Investigate the codebase and draft a well-structured GitHub issue with evidence; use when asked to file or write an issue.
Validate a GitHub issue against the codebase and expected behavior; use when asked to verify an issue report.
Use this skill for mission/sector/upgrade balancing and authored data changes.
在发版前执行发布门禁检查,并输出“可发布/带条件可发布/不可发布”结论与阻断项。适用于部署前、打 tag 前、发布分支合并前。
Workspace-first GrepAI search workflow for programming agents (v0.34+): project-scoped semantic search, token-efficient output, and reliable fallbacks.
name: smoke
Write and maintain self-contained ExecPlans (execution plans) that a novice can follow end-to-end; use when planning or implementing non-trivial repo changes.
Manage your Simplenote notes conversationally.
Multi-chain wallet balance monitoring with threshold alerts. Tracks ETH and token balances across Base and Ethereum networks, comparing against historical snapshots to detect suspicious activity.
Index and search code repositories, documentation, research papers, HuggingFace datasets, local folders, Slack workspaces, Google Drive, and packages with Nia AI. Includes auth bootstrapping, Oracle autonomous research, GitHub live search, dependency analysis, context sharing, and code advisor.
Autonomously validate environment state and execute a safe Magento 2 deployment with correct command order and confirmation gates before destructive steps.
Aggregate, score, and prioritize social mentions across X/Twitter. Outputs a ranked inbox with engagement scores and draft context for efficient reply batching.
Scan project dependencies for outdated packages, security vulnerabilities, and maintenance issues across multiple languages and package managers.
Create thorough implementation plans for complex tasks.
Verify blockchain transactions before announcing success. Use to avoid premature celebration and trust issues. Learned from getting a basename sniped.
>
>
>
Configures tmux status bars, installs frameworks and plugins, adds widgets and scripts, and sets up multiple status bars. Use when working with oh-my-tmux, Catppuccin, or tmux-powerline; adding weather/finance/clock/news widgets; troubleshooting why bar changes aren't appearing; or setting up tmux on a new machine.
Convert this into a web based slide deck using reveal.js.
writing-content
Aftermarket cybernetic network device framework. nhero is the umbrella for all pill-dispenser-as-network-device modifications — from Hero Health hardware RE to PyHole DNS-style medication routing to killdispenser supply chain primitives. One lowercase word. Append-only reference architecture.
infinity
This skill should be used when the user is writing code with mixed casing conventions, choosing casing for identifiers, enforcing casing consistency across a codebase, or when camelCase and snake_case appear in the same file. Covers per-context casing rules, acronym handling, and the absolute prohibition of mixed conventions.
>
Byzantine consensus voting for multi-agent decision making. Implements voting protocols, conflict resolution, and agreement algorithms for reaching consensus among multiple agents.
>
A skill for creating, updating, and managing slide presentations. Use for tasks involving slide decks, speaker notes, and integrating presentation materials with Git.
Research and classify stablecoins for resilience sub-factor overrides (chainRisk, collateralQuality, custodyModel). Run after types/defaults are implemented to identify coins needing explicit overrides.
Apply final governance and release-gate checks to a judged change set by reading `handoff.json`, `verdict.json`, optional eval evidence, and emitting machine-readable `audit.json` with `gate` status. Use when implementation already has a judge verdict and a separate auditor must decide landability (`pass`, `fail`, or `needs-human`) without modifying source files.
Identify upcoming and recent catalysts that could move the stock
Realizar un análisis técnico y funcional profundo de un requerimiento, repositorio, módulo, script o conjunto de cambios para entender su propósito, flujo, dependencias, riesgos, deuda técnica y oport