cowork-multi-agent-research
Multi-agent system research agent for CoWork OS. Use when: researching multi-agent papers, frameworks, production case studies; maintaining a research queue;…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 10-27 00:15
Agents & models
24,922 results
ai-tool-handoff
Detect whether AI-assisted review tools (such as Luminance, Kira, etc.) are in use, hand off bulk clause extraction to the tool, and according to `~/.claude/plugins/config/claude-for-legal-zh/corporate-legal/CLAUDE.md` in the trust tier, subject its output to…
aia-generation
Generate risk classification and compliance summary assessments for AI systems or models—covering data, fairness, transparency, security, and regulatory registries. Use after a use case is classified as "conditional-high", when a product or engineering team proposes "we need to do an AI impact assessment", or when periodically re-certifying deployed systems. Adopt a fast/comprehensive dual-track approach.
experiment-analyzer
Analyze LLM experiment results. Handles single or comparative experiments, exploratory or Q&A modes. Use when user says "analyze experiment", "compare…
organise-agent-skills
Standardised workflow for auditing, pruning, and organising agent skills in agentic development environments, such as Antigravity. Use when reviewing installed…
grok
Cursor IDE only — do not apply in Codex or any harness without Grok. ALWAYS apply by default in Cursor for every turn, Task/subagent launch, best-of-N run,…
skill-management
Full lifecycle skill management system that uses LLM intelligent analysis to identify skill types, evaluate quality, and audit security. Supports searches across three data sources: GitHub, the skills.sh marketplace, and Skills CLI (npx skills). When users need to: (1) discover and evaluate new skills, (2) audit the security of existing skills, (3) adapt skills to fit the local environment, (4) test skill integration effects, ...
kk-session-extract
Extract durable knowledge from the current live session, stage it as a validated done session log, and run it through the same curation machinery as…
boltz
Run Boltz API workflows via the official `boltz-api` CLI — structure-and-binding, protein design/screen, small-molecule design/screen, ADME prediction, and job…
oma-orchestration
Dispatch and supervise parallel specialist agents with durable task state. Use when automated multi-agent execution is requested.
agentforce-offline-experimentation-run
Use this skill when users want to execute this workflow when a user wants to test how a different LLM model would handle existing Agentforce agent…
spartan-warrior
Embody the unbreakable Spartan ethos of discipline, courage, and relentless excellence through laconic wisdom and warrior mentality forged in hardship. Use…
karpathy
Use when the user wants the LLM to do its own ML research: a fully-autonomous loop that hacks the training code, runs it, and keeps changes that lower a single…
scientific-figure
Use when the user has scientific data (or a prompt alluding to scientific data) and wants a publication-quality figure made from it. A generator drafts and…
stitch-mcp-create-project
Creates a new Stitch project container (a design workspace). Call this when starting a new design session to get a projectId for screen generation.
stitch-mcp-get-project
Retrieves metadata for a specific Stitch project — title, theme, create/update time. Use to inspect a project before generating new screens. Do NOT use this if…
stitch-mcp-list-screens
Lists all screens in a Stitch project. Use this after generate_screen_from_text to find the screenId of the newly generated screen, then call…
tax-efficient-investing
When the user wants to invest in a tax-efficient way, maximise contributions to tax-advantaged accounts, understand the tax drag on investment returns, compare…
agentic-os
Framework-agnostic persistent memory and self-improvement loops for AI agents. Scaffolds shared state, task queues, and learnings files that can be…
bump-skill-version
Bump the semver version in a skill's SKILL.md frontmatter following the patch/minor/major rules in CLAUDE.md. Use after modifying a skill's logic or docs.
command-center
Aggregates state across all tasks, errors, and runs to produce a global status dashboard.
gemini-translate
Batch-translate content files using Gemini CLI as a subagent, with Claude orchestrating quality and validation
gemini-use-claude-acp
Delegate a sub-task to Claude Code via the Agent Client Protocol (ACP). Use this skill whenever you want to hand off work to Claude — complex agentic coding…
genkit-dart
Instructions and resources for building applications using the Genkit Dart framework -- general purpose, multi-model Generative AI SDK for Dart.