195 skills · sorted by relevance
Execute a task with sub-agent implementation and LLM-as-a-judge verification with automatic retry loop
The English summary is being prepared. Showing the original description.
Reset the FPF reasoning cycle to start fresh
The English summary is being prepared. Showing the original description.
Review an existing GitHub pull request and post inline review comments on its diff. Use when the changes are on an opened PR rather than your local working tree.
The English summary is being prepared. Showing the original description.
Auto-selects best Kaizen method (Gemba Walk, Value Stream, or Muda) for target
The English summary is being prepared. Showing the original description.
Launch a meta-judge then a judge sub-agent to evaluate results produced in the current conversation
The English summary is being prepared. Showing the original description.
Reflect on previus response and output, based on Self-refinement framework for iterative improvement with complexity triage and verification
The English summary is being prepared. Showing the original description.
Use when creating or developing, before writing code or implementation plans - refines rough ideas into fully-formed designs through collaborative questioning, alternative exploration, and incremental validation. Don't use during clear 'mechanical' processes
The English summary is being prepared. Showing the original description.
Add line-specific review comments to pull requests using GitHub CLI API
The English summary is being prepared. Showing the original description.
Evaluate and improve Claude Code commands, skills, and agents. Use when testing prompt effectiveness, validating context engineering choices, or measuring improvement quality.
The English summary is being prepared. Showing the original description.
Generate ideas in one shot using creative sampling
The English summary is being prepared. Showing the original description.
Use when found gap or repetative issue, that produced by you or implemenataion agent. Esentially use it each time when you say "You absolutly right, I should have done it differently." -> need create rule for this issue so it not appears again.
The English summary is being prepared. Showing the original description.
Use when Code implementation and refactoring, architecturing or designing systems, process and workflow improvements, error handling and validation. Provide tehniquest to avoid over-engineering and apply iterative improvements.
The English summary is being prepared. Showing the original description.
Guide for creating effective skills. This command should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations. Use when creating new skills, editing existing skills, or verifying skills work before deployment - applies TDD to process documentation by testing with subagents before writing, iterating until bulletproof against rationalization
The English summary is being prepared. Showing the original description.
Run independent tasks concurrently across multiple files or targets using parallel sub-agents, with per-task model selection and LLM-as-a-judge verification. Use when tasks do not depend on each other and can run side by side.
The English summary is being prepared. Showing the original description.
Execute one complex task as ordered, dependent steps run sequentially, passing context from each step to the next, with per-step LLM-as-a-judge verification. Use when later steps depend on the results of earlier ones.
The English summary is being prepared. Showing the original description.
Use to load open/unresolved PR review comments then aggregate them as tasks in .specs/comments/*.md for parallel agents to fix.
The English summary is being prepared. Showing the original description.
Review what an LLM feature or agent actually puts in its context window — and find what's bloating, missing, or fighting itself. Use when asked to review a system prompt and context assembly, cut token usage without losing quality, debug an agent that ignores instructions, or audit how retrieval results, history, and tool definitions are packed into the window. Produces a context inventory with a keep/cut/restructure verdict per component, ordering and caching fixes, and a token budget. For wording-level prompt tuning use prompt-optimizer.
The English summary is being prepared. Showing the original description.
项目级上下文工程框架：通过 PROJECT / REQUIREMENTS / ROADMAP / STATE 四层文档 为每个任务建立结构化上下文，控制 token 预算，防止上下文腐烂， 确保跨会话连续性。与 context-lifecycle 的 L0-L3 层互补。
The English summary is being prepared. Showing the original description.
Audit a repo's agent context — CLAUDE.md files, codebase docs, skills, and tool/MCP designs — against Anthropic's Claude 5 context-engineering guidance ("unhobbling": Anthropic cut ~80% of Claude Code's system prompt with no eval loss). Finds overconstraint, conflicting instructions, redundancy, stale facts, and missing "unknown knowns"; produces a scored findings report with concrete rewrites, then applies approved fixes. Use when someone says "audit my CLAUDE.md", "context audit", "unhobble this repo", "review our agent docs/skills/tools", or after upgrading to Claude 5-generation models.
The English summary is being prepared. Showing the original description.
Context management engine for AI coding agents. Use when building agent memory systems, optimizing context windows, allocating token budgets, designing RAG pipelines for code, or managing persistent multi-session agent state.
The English summary is being prepared. Showing the original description.
Load shared marketing context: brand profile, benchmarks, compliance rules, specs. "load my brand context"
The English summary is being prepared. Showing the original description.
Manages attention and evidence in long agent sessions. Use for lost instructions, dropped evidence, or large multi-agent contexts.
The English summary is being prepared. Showing the original description.
Rules for when an agent should recall from long-term memory before acting and when it should save decisions, corrections and failures afterwards. Works with any memory backend.
The English summary is being prepared. Showing the original description.
Make technology decisions for every product capability by discovering existing assets, evaluating vendor-aligned options, and categorizing as Reuse/Extend/Build/Buy/Integrate/Research during PRD v0.5 Red Team Review. Handles both greenfield and brownfield contexts. Triggers on "tech stack", "build or buy?", "what technologies?", "technical decisions", "what do we reuse?", "existing stack", "vendor constraint", "IBM-first", "what tools do we need?", "evaluate solutions", "select tech stack". Consumes FEA- (features), SCR- (screens), RISK- (constraints). Outputs TECH- entries with decisions, rationale, and cross-references. Feeds v0.6 Architecture Design.
The English summary is being prepared. Showing the original description.