adversarial-plan-review-codex
Use when a plan needs hostile review before execution, especially high-risk coding, business deliverables, migrations, no-git changes, weak validation, stale…
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-05 00:16
25,648 results
Use when a plan needs hostile review before execution, especially high-risk coding, business deliverables, migrations, no-git changes, weak validation, stale…
This skill should be used when working with the npx skills CLI (skills@1.4.5 by Vercel Labs) for managing agent skills — installing, discovering, updating, and…
Moving mechanical computation from LLM prompts into tested CLI commands. Use when writing or reviewing slash commands with embedded bash, when a skill/command…
Protocol specification for multi-perspective brainstorming via 5 parallel agents with confidence-weighted synthesis. Executed by brainstorming-pm orchestrator.
Implement RAG with memory, learning, and index updating — ingestion, chunks, embeddings, retrieval, rerank, and corpus correction. Use when building knowledge…
Discover WHICH new skills you should create, from your own work history plus your satisfaction/frustration signals. Read-only and proposal-only: it surfaces…
Run long or failure-prone Claude Code tasks as bounded, resumable loops with a durable state machine, attempt budget, and verification evidence checkpoint.
Paralelismo GPU para ejecutar múltiples inferencias simultáneamente
Automate Jira tasks via Rube MCP (Composio): issues, projects, sprints, boards, comments, users. Always search tools first for current schemas.
Automate Linear tasks via Rube MCP (Composio): issues, projects, cycles, teams, labels. Always search tools first for current schemas.
Safely reclaim disk space on a Mac — the trustworthy, transparent, reversible alternative to CleanMyMac and similar tools. Use whenever the user says their Mac…
Draw and review official DeepSeek Harness plugin icons and optional feature previews, including experimental plugins. Use for package artwork and PluginArtwork…
Run code review tools in parallel, validate findings with a second-opinion agent, and aggregate a comprehensive review report.
Grill a plan with field research: fetched standards, provider rules and proven tools become grilling questions; `check` audits the plan before /to-spec.…
Automate Gmail actions using Chrome DevTools MCP - search, read, compose, reply, and manage emails
When the user wants to submit their product to startup, SaaS, AI, agent, MCP, no-code, or review directories for backlinks, domain rating, and discovery. Also…
Use this skill to audit, fix, and document accessibility for TYPO3 websites and Fluid sitepackages. It orchestrates Playwright, axe-core, optional Deque axe…
Ralph Wiggum persistence loop with intelligent multi-model routing (Gemini, Codex, Claude, Council)
Analyze recent /define sessions to extract user preference patterns and write them to CLAUDE.md. Use when you want to learn from past define sessions, extract…
Enable MixSeek-Plus debugging features and control log output. Use for requests such as "enable debug mode," "verbose," "output logs," "log level," and "debug settings."
Generate the MixSeek prompt builder configuration file (prompt_builder.toml). Use this for requests such as "configure a prompt", "create a prompt builder", or "per-round prompts".
MixSeek Agent Skills collection for AI coding assistants. Provides workspace management, team configuration, evaluation setup, and debugging tools for…
Generates the MixSeek team configuration file (team.toml). Use it for requests such as "Create a team," "Generate agent configuration," "Create a web search team," or "Configure an analysis team." It defines the structure of the Leader Agent and Member Agents.
[Tooling & Meta] Manage learned patterns - list, view, archive, boost or penalize confidence. Use when you want to see what patterns Claude has learned, review…