a5c-ai
- 1.9k skills
- 0 followers
- 1.7k repo stars
- 2 weeks ago last updated
- ▌ Assimilate Popular Workflows · a5c-ai bundleThis skill should be used when the user asks to "find skills in the wild", "assimilate popular workflows", "discover SKILL.md files in repos", "research external skills", "find workflow patterns", "survey the skill landscape", "what skills exist out there", or wants to investigate public repositories for extractable processes, babysitter plugins, and reusable procedural insights. Searches GitHub for SKILL.md files, classifies repos by archetype, and maintains structured research under docs/reference-repos/.
- ▌
- ▌
- ▌ Anti Drift · a5c-ai bundleHierarchical coordination and drift detection with frequent checkpoints, shared memory coherence validation, role specialization enforcement, and short task cycles.
- ▌
- ▌ Atlas Graph Query · a5c-aiReference for querying the Atlas knowledge graph through its MCP tools — the SECONDARY enrichment/comparison layer that adds best-practice context to systems you have ALREADY scanned from your real sources (`az`, repos, dirs). Use when you need to look up nodes, edges, kinds, clusters, stats, or wiki pages in Atlas to compare against your real inventory. (atlas graph, query atlas, atlas mcp, search the graph, graph neighbors, atlas record, atlas kinds, enrichment layer)
- ▌ Code Review · a5c-ai bundleStructured code quality assessment with Conventional Comments format, scaled review depth, and soft-gating verdicts preserving user autonomy.
- ▌ Merge Queue · a5c-ai bundleProcess the Refinery merge queue - collect agent work, detect and resolve conflicts, merge in dependency order, and verify integration.
- ▌
- ▌ Plan Writing · a5c-ai bundleTransform research findings into actionable implementation plans with stakes-based rigor, test-first strategy, and granular task decomposition.
- ▌ Verification · a5c-ai bundleVerification-before-completion discipline ensuring all success criteria are met, tests pass, and reviews complete before declaring work done.
- ▌ Agent Booster · a5c-ai bundleWASM-based instant code transforms for simple tasks, achieving 352x speedup over LLM inference with zero cost.
- ▌ Smart Routing · a5c-ai bundleComplexity-based task routing with Q-Learning optimization, Agent Booster WASM fast-path, and Mixture-of-Experts model selection.
- ▌ Vector Memory · a5c-ai bundleHNSW vector search for pattern similarity retrieval and knowledge graph maintenance with PageRank scoring, community detection, and 3-tier memory management.
- ▌
- ▌ Retrospect External Babysitter Run · a5c-aiFor 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 effect design, breakpoint patterns -- mirroring the /babysitter:retrospect workflow but applied to an external repo. Invoke when asked to "retrospect on repo X's run", "analyze how someone else used babysitter", or "review an external babysitter run".
- ▌
- ▌
- ▌
- ▌
- ▌ Brainstorming · a5c-ai bundleClarify vague requirements through exploratory questioning and option generation before committing to research or implementation.
- ▌
- ▌
- ▌ Code Generation · a5c-ai bundleMinimal, pattern-matching code output. Write the least code that satisfies requirements. Match existing project patterns. Use Write/Edit tools only.
- ▌ Hotfix Triage · a5c-ai bundleUrgent issue classification, root cause analysis, and fast-path routing for production hotfixes
- ▌ Finishing Work · a5c-ai bundleFinal completion discipline including summary generation, plan document updates, and confirmation that all success criteria from the original plan are satisfied.
- ▌
- ▌
- ▌
- ▌ Lit · a5c-ai bundleWeb Components development with Lit including custom elements, reactive properties, shadow DOM, and interoperability.
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌ Issue Tracking · a5c-ai bundleTrack beads as git-backed issues with persistent attribution, supporting Gas Town's bead lifecycle and convoy progress monitoring.
- ▌ Roadmap Management · a5c-ai bundleRoadmap parsing, analysis, and mutation operations for ROADMAP.md. Handles phase and milestone lifecycle including add, insert (decimal), remove, complete, and requirements coverage analysis.
- ▌ Verification Suite · a5c-ai bundlePlan 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.
- ▌
- ▌ Security Review · a5c-ai bundleSecurity vulnerability assessment identifying OWASP risks, injection vectors, authentication issues, and data exposure with severity classification.
- ▌
- ▌
- ▌ Agent Generator · a5c-aiGenerate AGENT.md files with proper YAML frontmatter, role definitions, expertise areas, and prompt templates following Babysitter SDK conventions.
- ▌ Skill Generator · a5c-aiGenerate SKILL.md files with proper YAML frontmatter, capabilities documentation, and usage examples following Babysitter SDK conventions.
- ▌ Kip Librarian · a5c-ai bundleCanonical kip knowledge-store patterns for any process or agent: recall prior facts before work, assert decisions/gate outcomes/rejections as structured facts after work, resolve entities with explicit --model sonnet, and invoke the CLI Windows-safely via node packages/kip-sdk/dist/cli/kip.js when kip is not on PATH.
- ▌
- ▌
- ▌ Ngrx · a5c-ai bundleNgRx state management for Angular including store, effects, entity adapter, component store, and selectors.
- ▌ Nuxt · a5c-ai bundleNuxt 3 patterns including Nitro server, auto-imports, modules, hybrid rendering, and full-stack development.
- ▌ Rxjs · a5c-ai bundleRxJS reactive programming patterns including operators, error handling, multicasting, and Angular integration.
- ▌ Trpc · a5c-ai bundletRPC end-to-end type safety, procedures, routers, middleware, and React integration.
- ▌
- ▌
- ▌
- ▌ Planning Patterns · a5c-ai bundleStructured planning methodology with research, brainstorming, phased plan creation, risk assessment, and plan-to-build continuity.
- ▌
- ▌
- ▌ Spec Creation · a5c-ai bundleFeature specification creation from codebase research. Produces requirements, acceptance criteria, architecture decisions, implementation plans, and risk analysis.
- ▌ Context Engineering · a5c-ai bundleContext window monitoring and budget management. Keeps orchestrator at 15-30% context usage while subagents get full 200k tokens. Provides warnings at thresholds, context-aware summarization triggers, and wave-level budget planning.
- ▌ Frontmatter Parsing · a5c-ai bundleYAML frontmatter parsing and manipulation for .planning/ documents. Provides read, write, update, query, and validation operations on frontmatter blocks in GSD markdown artifacts.
- ▌ Self Optimization · a5c-ai bundleSONA self-optimizing neural architecture with ReasoningBank trajectory learning, EWC++ anti-forgetting, and reinforcement learning feedback loops.
- ▌
- ▌
- ▌
- ▌
- ▌ Process Analyzer · a5c-aiAnalyze processes, identify workflows, define boundaries and scope, and map process requirements for specialization creation.
- ▌
- ▌ Pinia · a5c-ai bundlePinia state management for Vue 3 including store creation, actions, getters, plugins, and DevTools integration.
- ▌ Redis · a5c-ai bundleRedis caching patterns, pub/sub, sessions, rate limiting, and data structures.
- ▌ Remix · a5c-ai bundleRemix patterns including loaders, actions, nested routing, progressive enhancement, and deployment strategies.
- ▌
- ▌
- ▌
- ▌ Spec Execution · a5c-ai bundle6-phase iterative specification execution workflow covering implementation, testing, review, improvement, commit, and progress tracking with quality-gated convergence.
- ▌
- ▌ Code Review Gate · a5c-ai bundleArchitect code review with DRY, YAGNI, abstraction, and test coverage principle enforcement
- ▌ Test Enforcement · a5c-ai bundleAutomated test validation, coverage checking, and quality metrics with aggressive defaults
- ▌ Pr Shepherding · a5c-ai bundleMonitor PR lifecycle from creation through merge including CI monitoring, review comment handling, thread resolution, and merge readiness verification.
- ▌ Codebase Research · a5c-ai bundleSystematic codebase exploration following the Iron Law - understand the problem before exploring code. Four phases with file-finder and web-researcher agents.
- ▌ Security Hardening · a5c-ai bundleAIDefence security layer with prompt injection blocking, input validation, sandboxed execution, output sanitization, and STRIDE threat modeling.
- ▌ Planning Design · a5c-ai bundleDesign technical architecture, select technology stack, and define implementation strategy from specifications and constitution constraints.
- ▌