self-improve
Retrospect the current agent session (failures, user corrections, detours, token-heavy or slow turns) into lessons, shipped as minimal edits to jinsyin/skills…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 10-31 00:15
Agents & models
25,344 results
product-manager
Strategic product agent that triages customer feedback beads, writes actionable user stories with acceptance criteria, prioritizes work by user impact, and…
mc-render-compile
The compiler from ARR-SPEC to any generation backend (compilation layer). One compiler, many backends - the backend differences live in backends.yaml as data, never as…
pci-dss-audit
Use when auditing code for PCI-DSS v4.0 compliance, reviewing cardholder data handling, checking credit-card storage and transmission, hunting PAN logging, or…
search-integration
Invoke this Skill when the system prompt needs to define when the AI model searches, how it searches, which data sources it searches, and how it handles search results. Applicable to all AI product designs involving real-time knowledge retrieval—chatbots, research assistants, enterprise knowledge base Q&A, etc. Not applicable to: purely offline scenarios (environments without search capability), knowledge Q&A that has been fully internalized (such as mathematical derivation), and creative generation tasks. When the requirement only involves "reading from local files…
voice-optimization
Called when the system prompt targets voice interaction scenarios (voice assistants, voice search, spoken answers, telephone customer service AI). Suitable for system prompt design that needs to optimize text output for spoken expression. Not suitable for pure text chat interfaces, not suitable for text-to-speech (TTS) technology selection, not suitable for image/video multimodal scenarios.
scaffold
Project initial setup skill for AI-driven development. Automates the creation of AGENTS.md, configuration of basic instructions, and installation of core skills.
vault-audit
Audit the vault's PARA and Zettelkasten-inspired Atomic Note organization, linked knowledge, journals, metadata, LLM Wiki quality, and bounded statistics. Use…
subagent-driven-development
Execute a multi-task implementation plan by dispatching one fresh subagent per task with isolated context, then applying a two-stage review (spec compliance…
autonomous-mode
Use ONLY when invoked via the `/gangsta:heist` or `/gangsta:go` commands (see `commands/heist.md` and `commands/go.md`) — orchestrates the Heist pipeline…
skill-vetter
Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope,…
agent-desktop-ffi
C-ABI bindings over agent-desktop's PlatformAdapter. Consumers (Python ctypes, Swift, Node ffi-napi, Go cgo, C++, Ruby fiddle) link…
api-ai-augmented
Designs AI-powered API features, LLM tool/function definitions, MCP server tool schemas, natural language to API conversion, and agentic API workflows. Use…
ai-fine-tuning
Fine-tune models on your data to maximize quality and cut costs. Use when prompt optimization hit a ceiling, you need domain specialization, you want cheaper…
review-pr
Review pull requests with complexity-adaptive depth — spawning deep-dive agents for medium and complex PRs. Use this skill when the user says "review this PR",…
skill-inventory-auditor
Audit all installed agent skills across global and project scopes to find and remove duplicate skills. Use when asked to audit my skills, deduplicate skills,…
atelier-orchestrator
Skill routing and workflow orchestration. Selects Inline Plan or Spec-backed Plan, routes to the correct workflow skill, and manages transitions between…
coverage-analyzer
Analyze test coverage with detailed metrics, identify gaps, and generate comprehensive reports. Use when measuring code coverage, finding untested code, or…
agentic-layer-audit
Audit codebase for agentic layer coverage and identify gaps. Use when assessing agentic layer maturity, identifying investment opportunities, or evaluating…
prompt-improvement
Meta-skill for improving and optimizing prompts using Anthropic's prompt engineering best practices. Provides the 4-step improvement workflow (example…
find-skills
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express…
kf-g-agent-orchestrator
Delegates all execution to workers, then synthesizes results for design and planning. Use when the user invokes /kf-g-agent-orchestrator or asks for…
skill-creator
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an…
project-behavior
Author or update a project's AGENTS.md to install behavioral guidelines that govern any agent acting in that project. Use when the user wants to configure…