All authors
Claude Skills by a5c-ai
github.com/a5c-ai2,120 skills40 installs3,476 views
- Specification GenerationConvert requirements into structured technical specifications with architecture decisionsVotes: 0GitHub stars: 1,760
- Story DecompositionBreak technical specifications into small, implementable stories with dependency orderingVotes: 0GitHub stars: 1,760
- Test EnforcementAutomated test validation, coverage checking, and quality metrics with aggressive defaultsVotes: 0GitHub stars: 1,760
- Adversarial ReviewFresh adversarial code review with binary PASS/FAIL verdicts, evidence citations, and anchoring bias prevention via fresh reviewer spawning.Votes: 0GitHub stars: 1,760
- Design Review GateParallel design review by 6 specialist agents (PM, Architect, Designer, Security Design, UX, CTO) with mandatory unanimous approval.Votes: 0GitHub stars: 1,760
- External Tool CoordinationCoordinate external AI tool integration (OpenAI Codex, Google Gemini) for cross-model adversarial review and delegated implementation.Votes: 0GitHub stars: 1,760
- Knowledge CurationContext priming before work (bd prime) and self-reflection after completion to extract patterns, gotchas, and decisions into the knowledge base.Votes: 0GitHub stars: 1,760
- Orchestrated ExecutionExecute work units through the rigorous 4-phase Metaswarm cycle (Implement -> Validate -> Adversarial Review -> Commit) with independent quality gate enforcement.Votes: 0GitHub stars: 1,760
- Plan Review GateAdversarial plan review by 3 independent reviewers (Feasibility, Completeness, Scope & Alignment) before presenting to user.Votes: 0GitHub stars: 1,760
- Pr ShepherdingMonitor PR lifecycle from creation through merge including CI monitoring, review comment handling, thread resolution, and merge readiness verification.Votes: 0GitHub stars: 1,760
- Work Unit DecompositionDecompose implementation plans into discrete work units with enumerated DoD items, file scope declarations, dependency mapping, and human checkpoint flags.Votes: 0GitHub stars: 1,760
- Behavior ContractBug condition/postcondition formalization as testable Behavior Contracts. Defines invariants that must be preserved across fixes.Votes: 0GitHub stars: 1,760
- Codebase SyncConvention discovery and rule generation from codebase analysis. Scans project structure, builds search indexes, identifies patterns, and generates enforceable rules.Votes: 0GitHub stars: 1,760
- Context PreservationState capture and restore across context window compactions. Monitors usage thresholds and serializes quality, task, and spec state for seamless continuation.Votes: 0GitHub stars: 1,760
- Persistent MemoryObservation capture and retrieval across sessions. Stores decisions, discoveries, and bugfix patterns. Searchable via tags and relevance scoring.Votes: 0GitHub stars: 1,760
- Quality HooksLanguage-specific auto-lint/format/typecheck pipeline. Supports Python (ruff+pyright), TypeScript (prettier+eslint+tsc), Go (gofmt+golangci-lint). Auto-fix and convergence loops.Votes: 0GitHub stars: 1,760
- Spec Driven DevelopmentSpecification creation and management for the Pilot Shell methodology. Covers semantic search, clarifying questions, structured spec generation, and iterative refinement.Votes: 0GitHub stars: 1,760
- Strict TddStrict RED->GREEN->REFACTOR test-driven development with enforcement. Never write production code before a failing test. Atomic commits per TDD cycle.Votes: 0GitHub stars: 1,760
- Completion VerificationVerify all phases are complete with weighted quality scoring before allowing session exit.Votes: 0GitHub stars: 1,760
- Error LoggingLog all errors with full context, detect patterns, and suggest approach mutations to avoid repeated failures.Votes: 0GitHub stars: 1,760
- Findings CaptureCapture and persist research findings, discoveries, and decision rationale to findings.md.Votes: 0GitHub stars: 1,760
- Plan CreationCreate a structured task_plan.md with phases, goals, and checkbox tracking for persistent planning.Votes: 0GitHub stars: 1,760
- Session RecoveryDetect and recover previous planning sessions, reconstructing lost context from persistent planning files.Votes: 0GitHub stars: 1,760
- BrainstormingClarify vague requirements through exploratory questioning and option generation before committing to research or implementation.Votes: 0GitHub stars: 1,760
- Codebase ResearchSystematic codebase exploration following the Iron Law - understand the problem before exploring code. Four phases with file-finder and web-researcher agents.Votes: 0GitHub stars: 1,760
- Decision DocumentationCreate Architecture Decision Records (ADRs) documenting significant technical choices with context, options, consequences, and sequential numbering.Votes: 0GitHub stars: 1,760
- Finishing WorkFinal completion discipline including summary generation, plan document updates, and confirmation that all success criteria from the original plan are satisfied.Votes: 0GitHub stars: 1,760
- Plan ImplementationDisciplined execution of approved plans with step-by-step verification, phase checkpoints, failure investigation, and mandatory code/security reviews.Votes: 0GitHub stars: 1,760
- Plan WritingTransform research findings into actionable implementation plans with stakes-based rigor, test-first strategy, and granular task decomposition.Votes: 0GitHub stars: 1,760
- Security ReviewSecurity vulnerability assessment identifying OWASP risks, injection vectors, authentication issues, and data exposure with severity classification.Votes: 0GitHub stars: 1,760
- Systematic DebuggingStructured debugging methodology using hypothesis-driven investigation, log analysis, and bisection to isolate and resolve defects.Votes: 0GitHub stars: 1,760
- VerificationVerification-before-completion discipline ensuring all success criteria are met, tests pass, and reviews complete before declaring work done.Votes: 0GitHub stars: 1,760
- Agent BoosterWASM-based instant code transforms for simple tasks, achieving 352x speedup over LLM inference with zero cost.Votes: 0GitHub stars: 1,760
- Anti DriftHierarchical coordination and drift detection with frequent checkpoints, shared memory coherence validation, role specialization enforcement, and short task cycles.Votes: 0GitHub stars: 1,760
- Consensus MechanismsMulti-protocol consensus for agent swarms supporting Raft leader election, Byzantine fault tolerance, Gossip state propagation, and CRDT conflict-free merging.Votes: 0GitHub stars: 1,760
- Security HardeningAIDefence security layer with prompt injection blocking, input validation, sandboxed execution, output sanitization, and STRIDE threat modeling.Votes: 0GitHub stars: 1,760
- Self OptimizationSONA self-optimizing neural architecture with ReasoningBank trajectory learning, EWC++ anti-forgetting, and reinforcement learning feedback loops.Votes: 0GitHub stars: 1,760
- Smart RoutingComplexity-based task routing with Q-Learning optimization, Agent Booster WASM fast-path, and Mixture-of-Experts model selection.Votes: 0GitHub stars: 1,760
- Swarm OrchestrationMulti-agent swarm formation and coordinated execution with topology-aware agent deployment, consensus protocols, and anti-drift enforcement.Votes: 0GitHub stars: 1,760
- Vector MemoryHNSW vector search for pattern similarity retrieval and knowledge graph maintenance with PageRank scoring, community detection, and 3-tier memory management.Votes: 0GitHub stars: 1,760
- Constitution CreationEstablish project governing principles including dev guidelines, code quality standards, testing policies, UX requirements, performance benchmarks, and security constraints.Votes: 0GitHub stars: 1,760
- Cross Artifact AnalysisPerform cross-artifact consistency and coverage analysis across constitution, specification, plan, and task artifacts to detect gaps, conflicts, and misalignments before implementation.Votes: 0GitHub stars: 1,760
- Implementation ExecutionExecute development tasks to build features, producing code, tests, and configuration artifacts that satisfy specification requirements and comply with constitution standards.Votes: 0GitHub stars: 1,760
- Planning DesignDesign technical architecture, select technology stack, and define implementation strategy from specifications and constitution constraints.Votes: 0GitHub stars: 1,760
- Quality ChecklistValidate implementation quality through custom checklists, scoring against constitution standards, specification coverage, and producing remediation recommendations.Votes: 0GitHub stars: 1,760
- Specification WritingWrite feature specifications as requirements and user stories with acceptance criteria, focusing on business value and testable conditions.Votes: 0GitHub stars: 1,760
- Dispatching Parallel AgentsUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies.Votes: 0GitHub stars: 1,760
- Executing PlansUse when you have a written implementation plan to execute in a separate session with review checkpoints between batches.Votes: 0GitHub stars: 1,760
- Finishing A Development BranchUse when implementation is complete, all tests pass, and you need to decide how to integrate the work.Votes: 0GitHub stars: 1,760
- Receiving Code ReviewUse when receiving code review feedback, before implementing suggestions. Requires technical rigor and verification, not blind implementation.Votes: 0GitHub stars: 1,760