Выборочно обновляет документацию после любых изменений кода. Вызывать всегда после правок кода или функциональности.
Run a health check on the AI automation setup — verifies local file integrity, ADO pipeline configuration, and Lambda function state. Each project is self-contained.
Automatic documentation generation — data dictionaries, dataset READMEs, transform docstrings, and pipeline changelogs.
Persistent memory for AI agents via Auto Drive. Store and recall agent experiences, upload files to permanent decentralized storage, and build linked memory chains — all with a…
Autonomously drive vibix work end-to-end — pick an unblocked issue, plan it, implement, push a PR, resolve CI and review-bot feedback, merge when green, then repeat.
Continuously monitors system performance identifies improvement opportunities and orchestrates find-skills and create-skills to autonomously evolve capabilities.
auto-flow 4단계 (마지막) — implementation-plan.md 읽기 + Entry Guard (preflight.subagent_task_entry_check) + DAG 자동 build + 무조건 wave-parallel subagent 강제 (Gate #14 override) + failure…
Fix a reported bug end-to-end: reproduce it, add a regression test, implement the minimal fix, create a new git branch, commit using Conventional Commits, push, and open a GitHub…
Bound and de-risk a request into SPEC.md. Use when the objective is clear but scope needs constraining.
Database-backed model configuration with static fallback for this project. Hook-based reactive queries (useModels, useModel), static sync helpers, AUTO_MODEL injection, type depth…
Use right after fixing any bug or discovering a reusable pattern. If it could bite again on different work, auto-add it to CLAUDE.md or .adn/lessons.md in the same response,…
Scan dan hapus file tidak penting — temp, junk, cache, log, kosong, duplikat — dari folder tertentu.
(ePost) Use when reviewing session performance, analyzing improvement trends, or understanding the metrics-capture-detection pipeline
Sets up, structures, and auto-improves AGENTS.md files for coding agent projects. Bootstraps new AGENTS.md with self-improvement meta-rules, structures sections for clean rule…
CCv2 inicjalizacja trybu auto - wywiad + CONTINUITY + VALIDATION. Triggers: auto-init, auto init, inicjuj auto, plan auto — from general/automation
Fully autonomous issue-to-PR workflow for Rollercoaster.dev-mobile. Use when a worker should execute one issue end-to-end without human gates.
Issue 全生命周期管理——从创建到归档。当用户描述技术问题、提 bug、"帮我记录"、 "修一下 X issue"、"验证一下"、"归档 issue"时立即触发。单入口自动分发， 替代旧 issue-create/fix-issue/issue-verify/issue-archive 四个技能。…
Automated job searching from Dice/Indeed MCPs + 6 ATS API clients (Greenhouse, Lever, Ashby, Workable, SmartRecruiters, BambooHR) with priority-based source allocation,…
Set environment variables on AI automation Lambda functions. Interactively collects secrets and operational values, then applies them via AWS CLI.
Use when invoking auto-launched Flows from Apex (Flow.Interview), from external systems via REST API, from Platform Events, or from other Flows (subflow element).
Autonomous learning from execution data. Skills improve themselves by identifying patterns in successful vs failed
Fully autonomous nightly learning pipeline — self-scan, pattern extraction, knowledge update, skill refinement, and auto-commit without human intervention.
Drive a large body of work end-to-end — either from a single scoping issue or a fuzzy topic ("ship GA", "harden the review app") — by discovering scope in the backlog + codebase,…
Automated skill submission to multiple agent marketplaces. One command submits to all platforms.
Automatisch converteren van geüploade .docx en .pdf bestanden naar markdown (.md) voordat ze gelezen worden.
Automatically converts markdown content into images for sending. When it's necessary to return markdown content to the user, md2img is automatically invoked to generate images…
Gate every tool call in the auto-memory extract agent so only safe read-only actions and targeted writes execute.
Merge an existing PR after rebasing, running review-pass, ensuring CI passes, and addressing review comments.
Use when a user wants to enable or understand Claude Code's auto permission mode. Explains permissions.defaultMode "auto" honestly (a safety classifier approves routine actions…
主动监控系统状态。定期检查服务器健康，主动汇报，无需等待指令。。定期检查服务器健康，主动汇报，无需等待指令。触发关键词: 状态, system, monitor, 主动监控系统, auto, 定期检查服务, monitoring, 器健康。提供专业能力支持,覆盖多场景工作流,支持自动化处理。内置错误恢复与降级机制,多格式兼容,适配多源数据。
Sharpen a vague idea into a bounded objective. Use before framing when scope is undefined.
使用 auto-run-agent 对目标项目进行自动化分析、评估、设计和优化。完整流程包括：探索项目现状 → 识别问题 → 设计任务列表 → 创建 runner 环境 → 启动自主执行。适用于任何需要批量优化的项目。
Iteratively auto-optimize a prompt until no issues remain. Uses prompt-reviewer in a loop, asks user for ambiguities, applies fixes via prompt-engineering skill.
Automatically activates when detecting complex, multi-task requests that would benefit from parallel execution.
仓库 Markdown/JSON 内容自动同步到前端页面，配置 GitHub Actions 定时拉取 + 部署，保持 Google SEO 内容新鲜度。支持日报、博客、Changelog、Landing Page 等多种页面模式。
Canonical main-chain orchestrator for locked/current refinement-owned sources (DP-backed or JIRA Epic-backed).
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer…
Import ADO pipelines for enabled AI automation agents and set all required pipeline variables. Imports all enabled pipelines — each project is self-contained.
Fuehrt einen repo- und policy-bewussten Delivery-Workflow fuer bestehende Code-Aenderungen aus: Zustand erfassen, passende lokale Checks auswaehlen, selektiv committen, pushen,…
Generate W3C PROV-compliant provenance records automatically when agents create or modify artifacts
Create all AWS resources for AI automation agents — DynamoDB tables, SQS queue, S3 bucket, SNS topic, IAM role, Lambda functions, and API Gateway.
Multi-platform video auto-publisher. Automatically upload videos to Douyin, WeChat Channels, Xiaohongshu, Bilibili, YouTube and more.
study 仓库 v3 自驱式批量写笔记系统。一次启动后主 CC 用 ScheduleWakeup 自循环：每 round 跑 ~8-120 slug 多阶段 pipeline → cherry-pick → finalize-round → push → wakeup 60s → 醒来读 checkpoint 启下一 round。直到 written ≥…
QAMESH project QA mesh — auto qa init/plan/run/explore/release/evidence/feedback guidance
Автоматические проверки качества перед ответом пользователю. 5 быстрых чеков, которые занимают 2 секунды в голове и предотвращают 90% ошибок.
Detect repeated workflow patterns and auto-generate reusable skills from them. Analyzes tool operation logs to identify automation opportunities.
Trigger a plugin refresh cycle whenever reconciliation installs new marketplaces so plugin state stays in sync.
リポジトリの repo-level バージョン（v タグ）を自動判定して発行し、GitHub Release を作成する。ユーザーが「リリースして」「バージョン上げて」「タグ切って」「/auto-release」と言ったら起動する。
Decode an auto repair estimate — what each line actually is, which items are urgent vs upsell, and the questions that separate a fair shop from a fishing expedition.
Autonomous reply to X/Threads comments. Smart detection, templated responses, engagement automation.
Your agent always comes back. Anchor identity and memory on-chain so any new instance can resurrect from just an address — no local state, no single point of failure.
Recover active change and next action from artifacts. Use on fresh session with existing work.
Automatically assign roles on join, or let users pick roles via reaction/button menus. Use when asked for auto-role, self-assign roles, reaction roles, or role menu.
Routage automatique vers le modèle optimal selon le type de question (local gratuit vs API payant)
Auto router patterns for this project. Intelligent model selection via task classification, cost tier diversity, high-stakes override, weighted tier selection.
Auto router patterns for this project. Intelligent model selection via task classification, cost tier diversity, high-stakes override, weighted tier selection.
Autonomous dispatch-reconcile loop for batch task processing. Use with /auto-run --through to execute tasks unattended. Requires beads tasks to exist.
Automatically save session tips when user provides important feedback or corrections
Scan folder untuk deteksi file tidak penting (sampah, temp, duplikat) dan file yang salah tempat berdasarkan ekstensi.
Use when a task needs senior auto-service-technician judgment — diagnosing a check-engine-light or drivability complaint from DTCs and live data, deciding whether a code-named…