精选 Skills 索引（第 169 页）
按质量分排序的前 8,000 个 Skills，每个都有可收录的独立页面。需要全库 15.8 万条检索时，请使用 Skills 目录。
- redis-memory-backend
Redis backend for conversation state persistence and caching
- requirements-interview
Interactive PM interview with expertise-adaptive questioning for requirements elicitation
- research-first-dev
Research-first development methodology that investigates existing solutions, brainstorms alternatives, and evaluates trade-offs before any implementation begins.
- retrospect-external-babysitter-run
For a repository in the babysitter-users catalog, locate its babysitter processes and any committed runs (.a5c/runs/<runId>/) and perform a retrospective on a chosen run -- what went well, what failed, process suggestions, quality of effec…
- roadmap-management
Roadmap parsing, analysis, and mutation operations for ROADMAP.md. Handles phase and milestone lifecycle including add, insert (decimal), remove, complete, and requirements coverage analysis.
- rust-async-runtime
Work with Rust async runtimes — Tokio, async-std, executor internals, pinning, wakers, and building high-performance async Rust services.
- security-hardening
AIDefence security layer with prompt injection blocking, input validation, sandboxed execution, output sanitization, and STRIDE threat modeling.
- security-scanning
AgentShield security audit with 5 scanning categories, 102 static analysis rules, and optional red-team simulation.
- segment-tree-builder
Generate customized segment tree implementations
- self-optimization
SONA self-optimizing neural architecture with ReasoningBank trajectory learning, EWC++ anti-forgetting, and reinforcement learning feedback loops.
- semantic-kernel-setup
Microsoft Semantic Kernel planner and plugin setup for orchestrated AI
- session-management
Manage agent sessions including initialization, handoffs, revival (seance), and persistent identity for Polecats and Crew agents.
- setfit-few-shot
SetFit few-shot learning for efficient intent classification with minimal data
- single-file-bundling
Configure Vite with vite-plugin-singlefile for mandatory single-file HTML bundling of MCP Apps. All assets (JS, CSS, images, fonts) must be inlined into a single HTML file for sandboxed iframe compatibility.
- smart-routing
Complexity-based task routing with Q-Learning optimization, Agent Booster WASM fast-path, and Mixture-of-Experts model selection.
- solution-comparator
Compare multiple solutions for correctness and performance
- solution-explainer
Generate clear explanations of algorithm solutions
- spacy-ner
spaCy NER model training and entity extraction for conversational AI
- spec-creation
Feature specification creation from codebase research. Produces requirements, acceptance criteria, architecture decisions, implementation plans, and risk analysis.
- spec-driven-development
Specification creation and management for the Pilot Shell methodology. Covers semantic search, clarifying questions, structured spec generation, and iterative refinement.
- spec-execution
6-phase iterative specification execution workflow covering implementation, testing, review, improvement, commit, and progress tracking with quality-gated convergence.
- specification-generation
Convert requirements into structured technical specifications with architecture decisions
- specification-writing
Write feature specifications as requirements and user stories with acceptance criteria, focusing on business value and testable conditions.
- story-decomposition
Break technical specifications into small, implementable stories with dependency ordering
- string-algorithm-matcher
Match string problems to appropriate algorithms
- suffix-structure-builder
Build and query suffix arrays and related structures
- swarm-orchestration
Multi-agent swarm formation and coordinated execution with topology-aware agent deployment, consensus protocols, and anti-drift enforcement.
- tdd-enforcement
Red-Green-Refactor TDD methodology with mandatory failing tests, minimal implementation, quality refactoring, and 80% coverage gating.
- test-case-generator
Generate comprehensive test cases including edge cases, stress tests, and counter-examples for algorithm correctness verification. Supports random generation, constraint-based generation, and brute force oracle comparison.
- test-enforcement
Automated test validation, coverage checking, and quality metrics with aggressive defaults
- vector-memory
HNSW vector search for pattern similarity retrieval and knowledge graph maintenance with PageRank scoring, community detection, and 3-tier memory management.
- verification
Verification-before-completion discipline ensuring all success criteria are met, tests pass, and reviews complete before declaring work done.
- verification-suite
Plan structure validation, phase completeness checks, reference integrity verification, and artifact existence confirmation. Provides the structured verification layer ensuring GSD artifacts are well-formed and complete.
- visual-pattern-induction
Induce visual patterns from examples — few-shot visual reasoning, grid-based pattern recognition, and ARC-style inductive inference.
- weaviate-integration
Weaviate vector database setup with GraphQL queries and hybrid search
- webhook-verification
Implement secure webhook verification — HMAC signature validation, replay attack prevention, idempotency keys, and webhook payload processing.
- work-decomposition
Decompose goals into MEOWs (Molecular Expressions of Work) - trackable atomic units following Gas Town's bead-based work model.
- work-unit-decomposition
Decompose implementation plans into discrete work units with enumerated DoD items, file scope declarations, dependency mapping, and human checkpoint flags.
- zep-memory-integration
Zep memory server integration for long-term conversation memory and user profiling
- html
Create a self-contained HTML file for whatever the user is describing, in the effective HTML style. Use when the user wants an HTML artifact that isn't specifically a diagram or a plan — a report, explainer, comparison, deck, prototype, or…