ask-cc
Ask Claude Code to make a taste-driven call on something ambiguous — UI polish, prose phrasing, naming, formatting. Use when you'd otherwise guess.
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-05 00:16
Agents & models
25,663 results
taste-review
Ask Claude Code to make a taste-driven call on something ambiguous — UI polish, prose phrasing, naming, formatting. Use when you'd otherwise guess.
dispatching-parallel-agents
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
context
Creates, audits, and updates repository context: root AGENTS.md (or CLAUDE.md), README.md, committed product intent in .plans/PITCH.md, EXPERIENCE.md, and…
research-storage
Research file storage conventions and templates for dokhak agents. Use when: (1) saving research results from research-collector or researcher agents, (2)…
draw-the-owl
Decompose large agent-built features into atomic, reviewable chunks using a diff-size budget (~1500 lines) as the signal. Use this whenever implementing a…
orchestrate
Orchestrate multi-step work with Claude Code CLI as a bounded worker while Codex stays lead developer. Use when Codex should split a task into scoped…
save-session
Save AI agent session information for later resumption. Use when: (1) Finishing a work session and want to save progress (2) User says "save session",…
second-opinion
Run an external LLM code review with Codex CLI, Gemini CLI, or both. Use when the user asks for a second opinion, external review, Codex review, Gemini review,…
f
FIRST factory dispatcher. Lists /f-* station and role skills. Use when the user types /f or /f-product, /f-journeys, /f-analyst.
bmad
Analyzes current state and user query to answer BMad questions or recommend the next skill(s) to use. Use when user asks for help, bmad help, what to do next,…
bmad-advanced-elicitation
Push the LLM to reconsider, refine, and improve its recent output. Use when user asks for deeper critique or mentions a known deeper critique method, e.g.…
caveman-prompt-compression
Token-optimized prompt compression techniques for reducing LLM instruction size while preserving or improving quality
abschiebungsschutz
Urgent legal protection against imminent deportation and application for suspension of deportation – § 80 V VwGO (in particular § 36 III AsylG one-week deadline), § 123 VwGO, suspension of deportation § 60a AufenthG,…
arbeitsvertrag-gestaltung
Drafting and review of employment contracts – application of §§ 305–310 BGB in employment law with the special feature of § 310(4) sentence 2 BGB,…
asylantrag-vorbereitung
Preparation of the asylum application and the BAMF hearing § 25 AsylG – Dublin Regulation (EU) No 604/2013 triage, refugee status § 3 AsylG, entitlement to asylum Art. 16a GG,…
avv-pruefung
Review of a data processing agreement (DPA) under Art. 28 GDPR – mandatory clauses Art. 28(3)(a)–(h), sub-processors Art. 28(2) and…
cloud-auftragsverarbeitung
Data protection-compliant design of cloud use: processing on behalf under Art. 28 GDPR, technical and organizational measures under Art. 32 GDPR and…
softwareerstellung-werkvertrag
Review of contracts for the creation of custom software as a contract for work and services (§ 631 BGB): quality (§ 633 BGB), acceptance (§ 640 BGB), rights for defects (§…
ai-prototyping
Idea to AI-generated prototype to customer validation to engineering handoff. Use when deciding prototype vs spec, choosing fidelity, briefing AI prototyping…
mcp-server-development
Develop, review, and refactor Model Context Protocol (MCP) servers in Python or TypeScript/Node.js. Use when designing MCP tool/resource/prompt contracts,…
agent-consciousness
Persistent consciousness architecture for autonomous AI agent development. Synthesizes three substrates — control metalayer (behavioral governance), Obsidian…
knowledge-graph-memory
Bridge Claude Code conversation logs to an Obsidian knowledge graph for persistent agent memory. Transforms .entire/ event logs and ~/.claude/ transcripts into…
agentic-leadership
Work the way "The New Baseline" playbook describes: every delegated piece of work runs under a five-term contract (intent, bounds, evidence,…