Crash-resilient external agent loop with state persistence and CI/CD integration
Idioma do texto original: inglês
Menu
Skills neste repositório
O SkillsMP coletou 552 skills de jmagly/aiwg. Abra uma skill para revisar a origem e os detalhes.
jmagly/aiwgMostrando 40 de 552 skills coletadas.
Crash-resilient external agent loop with state persistence and CI/CD integration
Idioma do texto original: inglês
Infer measurable completion criteria for an agent-loop task from project docs, code, and AIWG standards when the user has not supplied --completion explicitly
Idioma do texto original: inglês
Abort a running agent loop and optionally revert changes
Idioma do texto original: inglês
Attach to a running agent loop's live output stream
Idioma do texto original: inglês
View and configure agent loop settings — show, set, reset, and apply named presets
Idioma do texto original: inglês
Crash-resilient external loop with state persistence and CI/CD integration
Idioma do texto original: inglês
Manage Al semantic memory entries — list, query, and clear lessons learned across loop iterations
Idioma do texto original: inglês
Resume an interrupted agent loop from last checkpoint
Idioma do texto original: inglês
Check status of current or previous agent loop
Idioma do texto original: inglês
Regenerate Codex context file (CODEX.md or ~/.codex/instructions.md) with AIWG framework content
Idioma do texto original: inglês
Regenerate OpenCode context file (.opencode/context.md) with AIWG framework content
Idioma do texto original: inglês
Create a well-formatted git commit and push to remote repository
Idioma do texto original: inglês
Verify configured secondary git mirrors are present and not drifting from the primary remote/default branch
Idioma do texto original: inglês
Disable the AIWG context hook without uninstalling AIWG or deleting hook files
Idioma do texto original: inglês
Enable the AIWG context hook in platform context files without re-deploying
Idioma do texto original: inglês
Rebuild AIWG hook files from currently installed framework manifests
Idioma do texto original: inglês
Show AIWG hook state across all installed providers
Idioma do texto original: inglês
Migrate existing CLAUDE.md full-injection to the AIWG.md hook file architecture
Idioma do texto original: inglês
Cross-framework project status aggregator — discovers contributors from installed frameworks, runs declarative detection, produces a unified status report.
Idioma do texto original: inglês
End-to-end SDLC ramp-up from idea to construction-ready with automated phase transitions
Idioma do texto original: inglês
Disable soul enforcement without deleting SOUL.md or soul files
Idioma do texto original: inglês
Enable soul enforcement by wiring SOUL.md into platform context files and deploying the enforcement rule
Idioma do texto original: inglês
Show SOUL.md enforcement state across all installed providers with quality check
Idioma do texto original: inglês
Generate an AIWG voice profile from an existing SOUL.md identity file
Idioma do texto original: inglês
Generate a SOUL.md from an existing AIWG voice profile
Idioma do texto original: inglês
Analyze LLM pipeline costs and generate concrete optimization recommendations with savings estimates
Idioma do texto original: inglês
Configure and run the isolated eval loop pattern — generate, evaluate, refine until pass threshold met
Idioma do texto original: inglês
Recommends the right LLM pipeline pattern for a use case — simple chain, embedded agent, state machine, RAG, eval loop, or dynamic prompt
Idioma do texto original: inglês
Interactive LLM inference pipeline design — elicits requirements, recommends pattern, scaffolds production-ready artifacts
Idioma do texto original: inglês
Show status overview of all LLM inference pipelines in the current project
Idioma do texto original: inglês
Production readiness review — strip prototype scaffolding, harden code, validate cost model, generate prod/ artifacts
Idioma do texto original: inglês
Production prompt engineering — write, iterate, and refine prompts with built-in eval loop feedback
Idioma do texto original: inglês
Parallel fan-out processing - spawn multiple sub-agents for chunked context processing
Idioma do texto original: inglês
Spawn sub-agent to process focused context and return structured result
Idioma do texto original: inglês
Execute a UAT plan against live MCP connections, tracking pass/fail per test and filing issues on failure
Idioma do texto original: inglês
Discover MCP tools and generate a phased UAT plan with agent-executable test specifications
Idioma do texto original: inglês
Generate UAT completion report with tool coverage matrix, pass/fail metrics, and regression detection
Idioma do texto original: inglês
Lint and health-check the knowledge base. Finds orphan pages, missing cross-references, stale claims, broken wiki-links, and regenerates the index.
Idioma do texto original: inglês
Ingest a source (URL, file, or freeform note) into the knowledge base. Creates a source summary and updates or creates relevant entity and concept pages.
Idioma do texto original: inglês
Download media from discovered sources with format selection and progress tracking
Idioma do texto original: inglês