Menu
Skills dans ce dépôt
SkillsMP a collecté 2 079 skills depuis a5c-ai/babysitter. Ouvrez un skill pour examiner sa source et ses détails.
a5c-ai/babysitterAffichage de 40 skills collectés sur 2 079.
Convention discovery and rule generation from codebase analysis. Scans project structure, builds search indexes, identifies patterns, and generates enforceable rules.
Langue du texte source : anglais
State capture and restore across context window compactions. Monitors usage thresholds and serializes quality, task, and spec state for seamless continuation.
Langue du texte source : anglais
Observation capture and retrieval across sessions. Stores decisions, discoveries, and bugfix patterns. Searchable via tags and relevance scoring.
Langue du texte source : anglais
Language-specific auto-lint/format/typecheck pipeline. Supports Python (ruff+pyright), TypeScript (prettier+eslint+tsc), Go (gofmt+golangci-lint). Auto-fix and convergence loops.
Langue du texte source : anglais
Specification creation and management for the Pilot Shell methodology. Covers semantic search, clarifying questions, structured spec generation, and iterative refinement.
Langue du texte source : anglais
Strict RED->GREEN->REFACTOR test-driven development with enforcement. Never write production code before a failing test. Atomic commits per TDD cycle.
Langue du texte source : anglais
Git worktree management for safe, isolated feature development. Creates, manages, and cleans up worktrees with branch naming and dependency setup.
Langue du texte source : anglais
Clarify vague requirements through exploratory questioning and option generation before committing to research or implementation.
Langue du texte source : anglais
Structured code quality assessment with Conventional Comments format, scaled review depth, and soft-gating verdicts preserving user autonomy.
Langue du texte source : anglais
Systematic codebase exploration following the Iron Law - understand the problem before exploring code. Four phases with file-finder and web-researcher agents.
Langue du texte source : anglais
Create Architecture Decision Records (ADRs) documenting significant technical choices with context, options, consequences, and sequential numbering.
Langue du texte source : anglais
Final completion discipline including summary generation, plan document updates, and confirmation that all success criteria from the original plan are satisfied.
Langue du texte source : anglais
Disciplined execution of approved plans with step-by-step verification, phase checkpoints, failure investigation, and mandatory code/security reviews.
Langue du texte source : anglais
Transform research findings into actionable implementation plans with stakes-based rigor, test-first strategy, and granular task decomposition.
Langue du texte source : anglais
Security vulnerability assessment identifying OWASP risks, injection vectors, authentication issues, and data exposure with severity classification.
Langue du texte source : anglais
Test-first development practice where test specifications are written before production code, integrated into plan tasks as mandatory first sub-steps.
Langue du texte source : anglais
Verification-before-completion discipline ensuring all success criteria are met, tests pass, and reviews complete before declaring work done.
Langue du texte source : anglais
WASM-based instant code transforms for simple tasks, achieving 352x speedup over LLM inference with zero cost.
Langue du texte source : anglais
Hierarchical coordination and drift detection with frequent checkpoints, shared memory coherence validation, role specialization enforcement, and short task cycles.
Langue du texte source : anglais
Multi-protocol consensus for agent swarms supporting Raft leader election, Byzantine fault tolerance, Gossip state propagation, and CRDT conflict-free merging.
Langue du texte source : anglais
AIDefence security layer with prompt injection blocking, input validation, sandboxed execution, output sanitization, and STRIDE threat modeling.
Langue du texte source : anglais
SONA self-optimizing neural architecture with ReasoningBank trajectory learning, EWC++ anti-forgetting, and reinforcement learning feedback loops.
Langue du texte source : anglais
Complexity-based task routing with Q-Learning optimization, Agent Booster WASM fast-path, and Mixture-of-Experts model selection.
Langue du texte source : anglais
Multi-agent swarm formation and coordinated execution with topology-aware agent deployment, consensus protocols, and anti-drift enforcement.
Langue du texte source : anglais
HNSW vector search for pattern similarity retrieval and knowledge graph maintenance with PageRank scoring, community detection, and 3-tier memory management.
Langue du texte source : anglais
Establish project governing principles including dev guidelines, code quality standards, testing policies, UX requirements, performance benchmarks, and security constraints.
Langue du texte source : anglais
Perform cross-artifact consistency and coverage analysis across constitution, specification, plan, and task artifacts to detect gaps, conflicts, and misalignments before implementation.
Langue du texte source : anglais
Execute development tasks to build features, producing code, tests, and configuration artifacts that satisfy specification requirements and comply with constitution standards.
Langue du texte source : anglais
Design technical architecture, select technology stack, and define implementation strategy from specifications and constitution constraints.
Langue du texte source : anglais
Validate implementation quality through custom checklists, scoring against constitution standards, specification coverage, and producing remediation recommendations.
Langue du texte source : anglais
Write feature specifications as requirements and user stories with acceptance criteria, focusing on business value and testable conditions.
Langue du texte source : anglais
Convert technical plans into actionable development tasks with dependency graphs, effort estimates, and parallelization opportunities.
Langue du texte source : anglais
Use when starting any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
Langue du texte source : anglais
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies.
Langue du texte source : anglais
Use when you have a written implementation plan to execute in a separate session with review checkpoints between batches.
Langue du texte source : anglais
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work.
Langue du texte source : anglais
Use when receiving code review feedback, before implementing suggestions. Requires technical rigor and verification, not blind implementation.
Langue du texte source : anglais
Use when completing tasks, implementing major features, or before merging to verify work meets requirements.
Langue du texte source : anglais
Use when executing implementation plans with independent tasks in the current session. Dispatches fresh subagent per task.
Langue du texte source : anglais
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes. Requires root cause investigation first.
Langue du texte source : anglais