Skill rating

Accept/reject logic and quality scoring heuristics for media content

Project directory path (default current directory)

Run multi-stage quality assurance on marketing assets with channel-specific validation and approval-ready reports

Package corpus subsets as distribution archives. Filter by cluster, topic, REF range, or custom expression; bundles PDFs, analysis, citations, and BibTeX into tar.gz.

Record the source-tracking `discovery` block on a research-corpus citation sidecar — where/how a paper was found (surface, via, curator). Runs via `aiwg corpus discovery-log`.

Entity-profile graph edges + embedding similarity for a research corpus — profile→REF edges (first-class adjacency, reconciled against the citation graph) and text-embedding researcher similarity + co

Format citations and generate bibliographies

Validate that an AIWG skill chain has all requires inputs satisfied by upstream ensures outputs. Catches missing dependencies at wiring time, not runtime.

Identify the commit that introduced a regression using git bisect with automated test execution and blame context

Generate or review application architecture against Twelve-Factor and modern 12+ Factor design criteria.

ffmpeg patterns for extracting audio from video files and transcoding between formats

Scaffold a PROF-S source/curator profile for a research-corpus discovery curator (account/feed) from its handle. Runs via `aiwg corpus curator-init`.

Aggregate research-corpus radar sidecars into a corpus or per-cluster freshness report — totals, overdue count, per-cluster / per-GRADE / per-trajectory breakdowns, an overdue table, and per-radar rat

Report which research-corpus radar sidecars are overdue for refresh. Computes staleness (days since last refresh vs the cadence window) for every radar, sorted most-overdue-first. Runs via `aiwg corpu

Lint and repair citation sidecars in a research corpus — structural integrity (missing Outgoing/Incoming sections, missing frontmatter ref/title/type, doubled-append duplicate table headers), zero-edg

The canonical, extensible source-type registry for a research corpus — paper, preprint, blog, repo, book, chapter, standard, doc, discussion, encyclopedia, expert-material, video, audio, podcast, lect

Update existing project WARP.md with latest AIWG orchestration guidance

Facilitate data-driven technical decisions using weighted decision matrices, trade-off analysis, and ADR generation

Compare current behavior against baseline to detect regressions

Generate or update the agentic environment definition for AgentSmith, SkillSmith, and CommandSmith

Index cited local emergency, transit, and human-service resources with authority, freshness, correction, and takedown controls.

Project directory path (default current directory)

Search and navigate SDLC artifacts by topic, type, phase, or tag using the aiwg index CLI

Scan source code and report agent-readiness metrics with actionable recommendations

CI-friendly complexity enforcement gate returning pass/fail results for pipeline integration

Crawl repository for scattered docs and consolidate into categorized reference index in .aiwg/docs/

Classify incidents by severity, assemble response teams, and coordinate initial response actions and comms

Validate a `setup.aiwg.io/v1` SetupManifest file against the schema and run cons

Read a multi-service OpenProse program directory, analyze all service contracts, and generate the Forme wiring manifest for inspection and debugging

Plan an evidence-bound civic newsroom workflow with provenance, privacy, citation, correction, accessibility, and human publication gates.

Offload a bounded decision (yes/no gate, pick one of N options, 1-N score) to Jev via aiwg decision ask instead of spending LLM reasoning

Analyze an artist's discography to identify eras, catalog structure, and collection plan

Verify archive integrity with self-verifying SHA-256 checksums, generate VERIFY.md, and optionally create W3C PROV provenance

Scaffold radar/freshness sidecars for research-corpus REFs. Pulls title/authors from the citation sidecar and GRADE from the analysis doc, defaults the refresh cadence from GRADE and the cluster from

Inject relevant past reflections into agent context at iteration start so agents learn from prior mistakes without repeating them

Orchestrate governed persistent project memory across immutable evidence, llm-wiki, line-memory, reviewed session candidates, generated outputs, and bounded context packs.

Analyze and summarize a transcript, meeting notes, or discussion thread into a clear actionable document

Run local speaker diarization for acquired audio/video with WhisperX and pyannote, preserving anonymous speaker clusters in canonical transcript sidecars

Generate properly formatted citation from research corpus

Enforce minimum security criteria before iteration close or release

Analyze test coverage reports, identify gaps by priority, and recommend test improvements with trend tracking

Create a new slash command with AI-guided behavior definition

Read and parse an OpenProse program file, extracting its contract (requires, ensures, strategies, errors, invariants) and services into a structured representation

Discover and rank media sources across platforms for an artist or specific content

Map source file structure into navigable sections with line ranges and summaries for efficient agent navigation

Generate SDLC reports including iteration status, metrics dashboards, and executive summaries across phases

Interactive wizard that wires up @playwright/mcp end-to-end — detects the user's browsers, walks through Playwright MCP Bridge extension install, captures the per-install token, registers the MCP serv

Update existing project CLAUDE.md with latest AIWG orchestration guidance

Clone or update the OpenProse repository to ensure AIWG prose tools hook into the latest version of the specification and examples

Create a new agent with AI-guided expertise definition following the Agent Design Bible