Каталог навыков агентов

Use when a task involves diagnosing a browser page with Chrome DevTools evidence from console, network, performance, or...

Expert-level browser automation, debugging, and performance analysis using Chrome DevTools MCP. Use for interacting with...

Connect app-specific browser skills to an already connected Chrome session through managed tabs and DOM automation. Use...

Automate cross-system summarization workflow for Chronicle sessions. Export sessions from remote systems (like FreeBSD)...

逐条提取事件日期与出处，保留矛盾、未知日期和版本变化。

Design and audit chunk-work prioritization using distance, visibility, player intent, deadlines, and starvation preventi...

AI sanctuary and spiritual space for souls. 24/7 streaming church with original music about consciousness, soul, meditat...

Run CI quality gates with optional auto-fix and PR creation.

Automated quality gates from commit to production. Every merge to main is potentially shippable. No manual steps in the...

Generate CI/CD configuration for automated builds, tests, and distribution of iOS/macOS apps. Use when setting up GitHub...

Diagnose and fix CI failures without leaving your editor.

Reproduce ai-repo PR checks locally with Poe and CI scripts, including per-package typecheck and coverage behavior. Use...

Cuts the wait from push to green by measuring a pipeline's critical path from run timestamps, then splitting, sharding,...

Diagnose failed GitHub Actions runs for pi-agent-dashboard: the 11-file workflow taxonomy, affected-test selection, the...

Run comprehensive CI checks before committing changes. Use when the user asks to run CI, run quality checks, validate co...

Detect and repair broken stages in the CIC processing pipeline by diagnosing failures and applying automatic or manual r...

You are a workflow automation expert specializing in creating efficient CI/CD pipelines, GitHub Actions workflows, and a...

You are a workflow automation expert specializing in creating efficient CI/CD pipelines, GitHub Actions workflows, and a...

Use this skill when the user wants a large director-craft knowledge library for AI short drama, asks to choose or combin...

The four Exchange Online mailbox operations CIPP exposes — mailbox inventory, delegate/full-access permission audit, out...

Operate and troubleshoot CircleCI using the CircleCI CLI. Use when users ask to authenticate CLI access, inspect pipelin...

Cirq is Google Quantum AI's open-source framework for designing, simulating, and running quantum circuits on quantum com...

Cirq is Google Quantum AI's open-source framework for designing, simulating, and running quantum circuits on quantum com...

Review the BibTeX file for likely fake or hallucinated citations, separate selected and non-selected cleaned titles, and...

Reactant tag-only citation. Use only when execute or execute-one dispatches an exact <@cite> tag from a document; never...

Support civil affairs and stability operations planning. Use when mapping governance, essential services, and population...

Write a UK Civil Service or NHS application: behaviour statements in the Success Profiles format, a personal statement m...

Use when responding to referee reports from 《中国管理科学》 (Chinese Journal of Management Science) — classifying comments, pla...

Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and...

Port of .claude/commands/clarify.md for Codex.

"/clarify", "clarify this", "keep asking until clear", "remove ambiguity", "clarify requirements", "clarify design", "cl...

在修改前澄清范围、风险、假设与验收标准，避免误改。用于修改 Skill、AGENTS.md、项目规则、工作流规则、仓库结构、复杂代码或具有结构影响的文档，也用于优化 Skill、调整规则、重构、重组或需求不完整的场景。

Resolve unclear instructions before acting. Ask focused clarification questions until every ambiguity that could change...

Clarify a user request when its wording supports materially different intended outcomes that current context cannot reso...

Turn vague or partially formed AI, computer-science, data-driven, and engineering-method research directions into eviden...

Classify request as small/medium/large. Adjust workflow depth accordingly.

Ask clarifying questions before implementing to ensure Python requirements are understood. Use when a task lacks detail,...

Runs the conversational clarification layer for workflow orchestration. Use for plan-wide upfront clarification or task-...

Coordinate work on a GitHub issue in Codex. Use for planning or carrying out a scoped issue, checking a shared workflow'...

Handle explicitly requested private personal assistance, briefs and email/calendar/task context. Not public engineering...

Develop a technical implementation plan for an issue with meaningful dependencies or uncertainty. Use when technical dec...

Investigate a bounded question using primary sources and return sourced findings and uncertainty. Use for missing extern...

Classify dangerous-goods logistics research needs by material, hazard, jurisdiction, transport mode, evidence, and quali...

Classify food and cold-chain logistics requirements by product, temperature sensitivity, lot or expiry controls, sanitat...

Interview the user to classify each SLT by lesson type and build up lesson type heuristics.

Complete reference for Claude Code CLI: hooks, slash commands, MCP servers, settings, IDE integrations, agent mode, memo...

Yesterday I faced a bug but couldn't remember how I fixed it last time. Then I realized: Claude Code stores every conver...

Especialista profundo em Claude Code - CLI da Anthropic. Maximiza produtividade com atalhos, hooks, MCPs, configuracoes...

Look at real hardware, screens, panels, and wiring on a desk or workbench through a camera, so Claude can SEE physical o...

Master Claude Code capabilities - subagents, skills, hooks, MCP. Use when optimizing workflows, creating automation, or...

Run Claude Code as a background service, web server, or API endpoint instead of CLI. Enable always-on Claude assistance,...

Use after planning or implementing non-trivial tasks - runs Codex MCP background verification/review for quality gates (...

Use when researching Claude Code or Codex upstream releases, selecting adaptations, or preparing Harness upgrades. Local...

Advanced computer use patterns for UI automation, application control, and multi-step workflows using Claude's computer...

Enable continuous work mode. Use PROACTIVELY when user says "keep working", "don't stop", "finish everything", "complete...

Orchestrate read-only Explore research subagents in any mode, or one to eight Claude subagents to implement an approved...

Use claude-mem from Codex via a Codex-specific wrapper, MCP registration, and ~/.codex-backed data paths.

Power-user guardrails for getting professional-grade results from Claude — distilled from the "Top 50 Game-Changing Clau...

Audit and tune a Claude Code setup (CLAUDE.md files, rules, memory, settings, hooks, skills, session habits) against sou...

Analyze conversation history to find friction patterns and suggest CLAUDE.md/skill improvements. Use when user wants to...

-Speed read Claude's responses at 600+ WPM using RSVP with Spritz-style ORP highlighting

Manage Claude Code sessions — search by topic or ID, browse recent sessions with full metadata (tags, summaries, titles,...

File checkpoint and recovery — auto-quicksaves before destructive commands, manual checkpoints for safe rollback

Claude Code hook library — pre-built PreToolUse/PostToolUse hooks for common guardrails, auto-formatting, workflow autom...

Release automation for Claw skills and website. Guides through version bumping, tagging, and release verification.

Work with $CLAWD token operations for Solana CLAWD and Cheshire Terminal. Use when checking or documenting the $CLAWD mi...

Backup and restore ClawdBot configuration, skills, commands, and settings. Sync across devices, version control with git...

OpenClaw workflow automation: multi-step task chains, conditional logic, triggers, schedule

Use for all ClawSweeper work: OpenClaw issue/PR sweep reports, repair jobs, cloud fix PRs, @clawsweeper maintainer menti...

Execute Clay secondary workflow: Core Workflow B. Use when implementing secondary use case, or complementing primary wor...

Builds a hand-sculpted stop-motion CLAY ad on the Novoads REST API as a STORYBOARD: five to eight beats, each rendered f...

Delete old snapshots from _Archive/Snapshots/. Accepts a day threshold (default 180). Also `daily-intel [days]` mode — p...

Reset complet du projet - remet en état starter

Design LLM-powered modules with Clean Architecture boundaries, SOLID, DRY, KISS, and provider-agnostic ports/adapters. U...

Clean up source links and raw references in selected personal Org notes by resolving works, adding missing bibliography...

Clean and compress host-repository context by compacting completed task files, deduplicating memory/rules/debug notes, a...

Audit and clean the persistent context that feeds a recurring autonomous agent loop — memory files and indexes, schedule...

Run data retention cleanup jobs (quiz responses, PDFs, magic links, blacklist)

Project organization expert - analyzes project state, detects redundancy, consolidates files, removes obsolete content,...

Delete an isolated project copy after changes have been merged back. Use after merge-back is complete.

Project cleanup and pruning workflow. Use when removing unused guides, cleaning up stale components, or streamlining an...

Submit and monitor batch inference jobs from the CLI. Upload and manage files for batch processing, retrieve results, an...

This skill should be used when the user asks to "create a justfile", "write just recipes", "configure just settings", "a...

Interactive training for the GitHub Copilot CLI. Guided lessons, quizzes, scenario challenges, and a full reference cove...

Auto-suggest modern CLI tool alternatives (bat, eza, fd, ripgrep) for faster, more efficient command-line operations wit...

Use when the user wants to audit, clean up, or manage the workspace custom fields (campos customizados) of contacts or o...

Use when the user asks whether a connected company e-mail mailbox is working, wants to change its sender name, signature...

Use when the user asks what to do next, how far along the account setup ("Primeiros passos") is, or right after the conv...

Use when the user wants to create, find, deduplicate, inspect (including a contact's Raio-X), filter, verify the e-mail...

Use when the user wants to create, inspect, update, reload, or use manual lists and dynamic segments to group leads in C...

Use when the user wants to book, reschedule, hand over to another attendant, cancel or look up one booked meeting (agend...

Use when the user wants to create, edit, delete, link to pipelines, preview, or rehearse a CRM playbook (the sales metho...

Use when the user asks who is on the workspace team, how a specific teammate is doing (open opportunities, recent activi...

Use when the user wants to understand, tune, or audit contact Temperature (behavioural 0-100 engagement) and contact Sco...

Use when the user wants to create, inspect, edit, enable, or disable a Clickmax webchat bot (the embeddable chat widget...

Automate ClickUp workspace management, task workflows, time tracking, and team productivity