Iteratively edit and refine a named plan for a task through a conversational loop. Each round, the current plan is shown and the user is asked whether to keep refining, mark the…
Interview the user relentlessly about the task plan until reaching a shared understanding, resolving each branch of the question decision tree.
Get or set unique task id . Use when user requests to work on a certain task or wants to know what the current task is.
Implement current or given task plan. Use when the user calls to "implement", "realize" or "apply" the "task", "plan", "spec", or "specification".
Reboot the current or given task plan by re-creating it from scratch. Use when the user calls to "reboot", "recreate" or "refresh" the "task", "plan", "spec", or "specification".
Rename the current or given task plan. Use when the user calls to "rename", "move" or "relabel" the "task", "plan", "spec", or "specification".
View current or given task plan. Use when the user calls to "view", "show" or "see" the "task", "plan", "spec", or "specification".
抓取 A 股消息面情报：从财联社、华尔街见闻、金十、新浪 7x24、东财快讯、 证监会/央行/上交所/财政部政策公告、东方财富股吧等公开来源抓取与股票相关的 新闻、政策、情绪，输出结构化 JSON 或 Markdown。 当用户提到“A 股消息面”、“抓新闻”、“个股消息”、“政策监管”、“股吧情绪”、…
Send a question to the running onboarding agent API and show the answer. Use when you want to test the RAG endpoint locally.
Ask Claude Code to make a taste-driven call on something ambiguous — UI polish, prose phrasing, naming, formatting. Use when you'd otherwise guess.
Live ASO data via AppTweak REST API. Keyword suggestions with volume/difficulty, app rankings, competitor analysis, review sentiment, and historical data.
Apple App Store Connect API integration. Fetch iOS app metadata, reviews, ratings, and version info directly from App Store Connect. Requires API key.
Competitor analysis and gap finding. Compares keyword targeting, metadata strategy, visual approaches, ratings, and identifies differentiation opportunities.
Store policy compliance checker for iOS App Store and Google Play. Validates metadata against Apple App Store Review Guidelines and Google Play Developer Program Policies.
Pre-launch and launch day ASO strategy. Covers metadata preparation, soft launch, day-1 optimization, review solicitation, and post-launch monitoring plan.
Review and rating analysis for app store listings. Sentiment classification, keyword extraction from reviews, theme clustering, rating distribution, developer response strategy.
Seasonal and trending keyword optimization. Identifies keyword opportunity windows, holiday calendars, metadata rotation strategy.
Technical ASO factors analysis. Android Vitals, app size, crash rates, update frequency, category selection, content rating impact.
Assemble the final calendar delivery document (DOCX) with all posts, images, and copy.
资产购置审核 — 核查新增固定资产的采购合规性、折旧政策适用性，完成入账。 适用情形：新增资产入账时执行，从 [FA]/[PO] 获取采购信息， 核查采购流程合规性，确认折旧政策，输出入账建议。 核心：采购合规 + 折旧政策确认 + 入账金额验证。
Audits game assets for compliance with naming conventions, file size budgets, format standards, and pipeline requirements.
资产处置审核 — 核查固定资产出售/报废/盘亏的合规性，确认处置损益。 适用情形：资产处置（出售/报废/盘亏）时执行，从 [FA]/[ERP] 获取信息， 核查处置原因、审批流程、资产评估，计算处置损益，输出处置建议。 核心：处置原因分析 + 审批合规 + 净值确认 + 损益计算。
Plan and batch-generate a project's asset set in a locked visual style, by orchestrating /codex-image:style-gen
Generate per-asset visual specifications and AI generation prompts from GDDs, level docs, or character profiles.
ALWAYS prefer ctxhelpr tools for code navigation when the repo is indexed. Use search_symbols instead of Grep for finding functions/classes/types.
Wraps each surfaced dimension as a self-contained 9-section autonomous-work-assignment envelope — scope, context, success criteria, allowed tools, return format, handoff — all the…
Inspect LiveView socket assigns for memory bloat — missing temporary_assigns, unused assigns, unbounded lists needing streams, memory estimates.
Use when: surfacing implicit assumptions in a spec, plan, design, or estimate before work starts: data shapes, ordering, scale, auth context, environment, compatibility,…
Rebuild the L1-L4 tree-sitter AST index for fast semantic search. L1=files, L2=symbols, L3=signatures, L4=dependencies. Respects .gitignore.
Review code changes for async-signal-safety violations in KSCrash crash handlers, signal handlers, and monitor code.
Generate a Conventional Commits message from staged changes and wait for confirmation before committing. Use when the user asks to commit or generate a commit message.
Summarize each day's Git activity into a concise daily work log, for a single date or a range. Uses the current repository, optional configured work projects, or paths named in…
Review code changes for bugs, regressions, convention violations, and high-value cleanup opportunities.
Work ZenTao bugs/tasks end to end: fetch details, confirm understanding, fix, verify, stage with git add, then ask before committing and before writing status back to ZenTao.
Stage 3 of the cncf-atlas engine. Review a project's deep-dive (or any markdown output) for the things that make docs bad: AI tells, broken top-to-bottom readability, missing…
Attach a photo of a plotted artwork to a plot example, resize it, generate thumbnail, and update the README with a description.
Attend the human-in-the-loop queue for loop-lane operation: ONE attention view merging worker-escalated items (human-gated role label + machine-marked escalation comment) with…
Establish cause-effect relationships between events or states. Use when analyzing root causes, mapping dependencies, tracing effects, or building causal models.
审计调整审核 — 核查 [ERP] 审计调整分录，评估调整合理性，处理调整分歧。 适用情形：审计过程中执行，从审计调整台账获取调整数据， 核查调整分录准确性，评估对报表影响，输出调整审核报告。 核心：调整识别 + 影响评估 + 分歧处理 + 最终确认。
Audit existing API endpoints for consistency when the user asks to check API quality, review API patterns, audit endpoints, or find API inconsistencies
Audit de sécurité complet de l'authentification d'une application (backend + frontend + infra)
Audit a repo's Claude Code automation landscape (hooks, MCP servers, skills, subagents, scheduled tasks) against the enforcement hierarchy, producing PASS/REJECT/CONDITIONAL…
Use when auditing comments, docstrings, or embedded documentation prose in a scope — to strip bloat and rewrite cluttered-but-justified entries.
审计委员会支持 — 为审计委员会提供专业支持，包括审计计划审阅、 审计发现跟踪、审计报告审阅和委员会议程管理。 适用情形：审计委员会会议前 [X] 天，或用户要求"准备 AC 材料"时执行。 核心：审计发现汇总 + 整改追踪 + 委员会议程设计。
Use when auditing and fixing logic bugs in a scope — off-by-one, wrong operator, inverted condition, unhandled boundary cases, unit/dimension mismatch, code that doesn't do what…
Use when auditing and fixing end-to-end data integrity in a scope — invariant violations, partial or conflicting writes, unsafe migrations/backfills, duplicate or reordered…
Audit open dependabot PRs in this repo. Spawns one investigator per PR (each with a codebase-walk sub-agent), produces a comparison table with per-PR risk + recommendation, and…
Use when auditing and fixing error handling in a scope — swallowed exceptions, defaults returned on error, optional chaining masking missing data, floating promises / missing…
审计资料收集 — 按审计要求收集 [ERP]/[DOC] 资料，完成资料清单编制与核对。 适用情形：审计进场准备时执行，从 [ERP]/[DOC] 获取资料， 按审计资料清单整理，核查完整性，输出资料收集报告。 核心：清单核对 + 缺失识别 + 替代方案 + 按时交付。
审计发现整改跟踪 — 对所有未关闭的审计发现进行跟踪管理， 验证整改效果，对超期未整改项执行升级流程。 适用情形：审计经理/总监每月审查整改状态、 验证已完成整改、或对超期整改执行升级时执行。
Per-game audit of Fallout 4 compatibility — BA2, half-float verts, BGSM materials, M49 precombines (CSG)
Audit a user's IWE installation. Runs scripts/iwe-audit.sh + MCP healthcheck + ritual smoke-test via sentinel mechanism (dry-run-contract.md), passes report to a VR.R.002 Auditor…
Audit locally-owned Claude Code instruction surfaces — user + project CLAUDE.md, .claude/rules, skill bodies, agent definitions, prompt-type hooks, output styles — for…
Use when auditing and fixing logging in a scope — missing observability, INFO bloat that doesn't scale, stale or wrong-level messages, payload dumps on routine paths.
Use when cutting code in a folder that doesn't earn its keep — whether a solution is over-engineered, where maintenance cost can be reduced, or where a feature should be removed…
Run ONE coordinated, ordered, resumable pass over a named target repository: a three-scope inventory first (managed policy read-only, user scope routed as recommendations, project…
Use when auditing and unifying pattern consistency in a scope — divergent implementations of the same concern, reimplementations of existing utilities, naming violations, import…
Audit Claude Code permission GRANTS for portability and auto-mode durability — scans skill/command/agent frontmatter allowed-tools and settings.json/settings.local.json…
Audits a codebase to verify that an implementation matches a plan file. Use when you want to check if code changes made by any tool (Gemini, another AI, a developer) correctly…
PR-level merge gate. Audits the WHOLE pull request (not just the diff) against a merge-readiness contract: SPEC acceptance criteria met, all phases complete, docs updated per the…