Crash-resilient external agent loop with state persistence and CI/CD integration
Skills in this repository
jmagly/aiwg - Page 4
SkillsMP has collected 552 skills from jmagly/aiwg. Open a skill to review its source and details.
jmagly/aiwgShowing 40 of 552 collected skills.
Infer measurable completion criteria for an agent-loop task from project docs, code, and AIWG standards when the user has not supplied --completion explicitly
Abort a running agent loop and optionally revert changes
Attach to a running agent loop's live output stream
View and configure agent loop settings — show, set, reset, and apply named presets
Crash-resilient external loop with state persistence and CI/CD integration
Manage Al semantic memory entries — list, query, and clear lessons learned across loop iterations
Resume an interrupted agent loop from last checkpoint
Check status of current or previous agent loop
Regenerate Codex context file (CODEX.md or ~/.codex/instructions.md) with AIWG framework content
Regenerate OpenCode context file (.opencode/context.md) with AIWG framework content
Create a well-formatted git commit and push to remote repository
Verify configured secondary git mirrors are present and not drifting from the primary remote/default branch
Disable the AIWG context hook without uninstalling AIWG or deleting hook files
Enable the AIWG context hook in platform context files without re-deploying
Rebuild AIWG hook files from currently installed framework manifests
Show AIWG hook state across all installed providers
Migrate existing CLAUDE.md full-injection to the AIWG.md hook file architecture
Cross-framework project status aggregator — discovers contributors from installed frameworks, runs declarative detection, produces a unified status report.
End-to-end SDLC ramp-up from idea to construction-ready with automated phase transitions
Disable soul enforcement without deleting SOUL.md or soul files
Enable soul enforcement by wiring SOUL.md into platform context files and deploying the enforcement rule
Show SOUL.md enforcement state across all installed providers with quality check
Generate an AIWG voice profile from an existing SOUL.md identity file
Generate a SOUL.md from an existing AIWG voice profile
Analyze LLM pipeline costs and generate concrete optimization recommendations with savings estimates
Configure and run the isolated eval loop pattern — generate, evaluate, refine until pass threshold met
Recommends the right LLM pipeline pattern for a use case — simple chain, embedded agent, state machine, RAG, eval loop, or dynamic prompt
Interactive LLM inference pipeline design — elicits requirements, recommends pattern, scaffolds production-ready artifacts
Show status overview of all LLM inference pipelines in the current project
Production readiness review — strip prototype scaffolding, harden code, validate cost model, generate prod/ artifacts
Production prompt engineering — write, iterate, and refine prompts with built-in eval loop feedback
Parallel fan-out processing - spawn multiple sub-agents for chunked context processing
Spawn sub-agent to process focused context and return structured result
Execute a UAT plan against live MCP connections, tracking pass/fail per test and filing issues on failure
Discover MCP tools and generate a phased UAT plan with agent-executable test specifications
Generate UAT completion report with tool coverage matrix, pass/fail metrics, and regression detection
Lint and health-check the knowledge base. Finds orphan pages, missing cross-references, stale claims, broken wiki-links, and regenerates the index.
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.
Download media from discovered sources with format selection and progress tracking