jmagly/aiwg - 第 4 页

agent-loop-ext

Crash-resilient external agent loop with state persistence and CI/CD integration

原文语言：英语

infer-completion-criteria

Infer measurable completion criteria for an agent-loop task from project docs, code, and AIWG standards when the user has not supplied --completion explicitly

原文语言：英语

ralph-abort

Abort a running agent loop and optionally revert changes

原文语言：英语

ralph-attach

Attach to a running agent loop's live output stream

原文语言：英语

ralph-config

View and configure agent loop settings — show, set, reset, and apply named presets

原文语言：英语

ralph-external

Crash-resilient external loop with state persistence and CI/CD integration

原文语言：英语

ralph-memory

Manage Al semantic memory entries — list, query, and clear lessons learned across loop iterations

原文语言：英语

ralph-resume

Resume an interrupted agent loop from last checkpoint

原文语言：英语

ralph-status

Check status of current or previous agent loop

原文语言：英语

aiwg-regenerate-codex

Regenerate Codex context file (CODEX.md or ~/.codex/instructions.md) with AIWG framework content

原文语言：英语

aiwg-regenerate-opencode

Regenerate OpenCode context file (.opencode/context.md) with AIWG framework content

原文语言：英语

commit-and-push

Create a well-formatted git commit and push to remote repository

原文语言：英语

git-mirror-audit

Verify configured secondary git mirrors are present and not drifting from the primary remote/default branch

原文语言：英语

hook-disable

Disable the AIWG context hook without uninstalling AIWG or deleting hook files

原文语言：英语

hook-enable

Enable the AIWG context hook in platform context files without re-deploying

原文语言：英语

hook-regenerate

Rebuild AIWG hook files from currently installed framework manifests

原文语言：英语

hook-status

Show AIWG hook state across all installed providers

原文语言：英语

migrate-hook

Migrate existing CLAUDE.md full-injection to the AIWG.md hook file architecture

原文语言：英语

project-status

Cross-framework project status aggregator — discovers contributors from installed frameworks, runs declarative detection, produces a unified status report.

原文语言：英语

sdlc-accelerate

End-to-end SDLC ramp-up from idea to construction-ready with automated phase transitions

原文语言：英语

soul-disable

Disable soul enforcement without deleting SOUL.md or soul files

原文语言：英语

soul-enable

Enable soul enforcement by wiring SOUL.md into platform context files and deploying the enforcement rule

原文语言：英语

soul-status

Show SOUL.md enforcement state across all installed providers with quality check

原文语言：英语

soul-to-voice

Generate an AIWG voice profile from an existing SOUL.md identity file

原文语言：英语

voice-to-soul

Generate a SOUL.md from an existing AIWG voice profile

原文语言：英语

cost-optimizer

Analyze LLM pipeline costs and generate concrete optimization recommendations with savings estimates

原文语言：英语

eval-loop

Configure and run the isolated eval loop pattern — generate, evaluate, refine until pass threshold met

原文语言：英语

pattern-selector

Recommends the right LLM pipeline pattern for a use case — simple chain, embedded agent, state machine, RAG, eval loop, or dynamic prompt

原文语言：英语

pipeline-design

Interactive LLM inference pipeline design — elicits requirements, recommends pattern, scaffolds production-ready artifacts

原文语言：英语

pipeline-status

Show status overview of all LLM inference pipelines in the current project

原文语言：英语

productionize

Production readiness review — strip prototype scaffolding, harden code, validate cost model, generate prod/ artifacts

原文语言：英语

prompt-engineer

Production prompt engineering — write, iterate, and refine prompts with built-in eval loop feedback

原文语言：英语

rlm-batch

Parallel fan-out processing - spawn multiple sub-agents for chunked context processing

原文语言：英语

rlm-query

Spawn sub-agent to process focused context and return structured result

原文语言：英语

uat-execute

Execute a UAT plan against live MCP connections, tracking pass/fail per test and filing issues on failure

原文语言：英语

uat-generate

Discover MCP tools and generate a phased UAT plan with agent-executable test specifications

原文语言：英语

uat-report

Generate UAT completion report with tool coverage matrix, pass/fail metrics, and regression detection

原文语言：英语

kb-health

Lint and health-check the knowledge base. Finds orphan pages, missing cross-references, stale claims, broken wiki-links, and regenerates the index.

原文语言：英语

kb-ingest

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.

原文语言：英语

acquire

Download media from discovered sources with format selection and progress tracking

原文语言：英语