Skill rating

Reverse-engineer voice profiles from sample content by analyzing writing patterns

Render research-corpus markdown index views (by-topic, by-year, authors, citation-network, ...) from corpus state. As of

Integrate regression testing into CI/CD pipelines with baseline comparison and merge blocking on failure

Validate AIWG configuration files and project setup for correctness and completeness

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

Generate custom voice profiles from natural language descriptions by mapping tone, formality, and domain to voice dimensions

Decision aid for bootstrap and verification chains — forces the 'what authenticates the authenticator' question; patterns for signed bootstrap, measured boot, recovery.

Configure pnpm's minimumReleaseAge gate (7-day default, 10-day high-sensitivity) plus blockExoticSubdeps for workspace-scope dep-source enforcement. Includes Corepack detection and lockfile-caveat war

Configure Yarn's npmMinimalAgeGate (7-day default, 10-day high-sensitivity) for JavaScript projects on Yarn 4.x or later. Includes Corepack detection and lockfile-caveat warning.

Configure Bun's install.minimumReleaseAge gate (7-day default, 10-day high-sensitivity) for JavaScript projects on Bun. Includes Corepack-equivalent version detection and lockfile-caveat warning.

Scan tracked repository files for committed binary blobs and report reviewability/provenance exceptions

Build a vendor-neutral, source-linked public-technology procurement evidence and risk review without autonomous scoring or award recommendations.

Research, compare, sample, select, persist, adapt, rotate, and archive reusable visual themes and design templates

Research, draft, and track a jurisdiction-specific public-records request without legal conclusions or automated submission.

Config-driven release orchestration — reads .aiwg/release.config plus optional .aiwg/releases/<plan-id> sidecars and walks the selected release plan's gates

Shared Agent Skills duplicate-precedence fixture.

Orchestrates issue-driven agent loops that post cycle status to issue threads and incorporate human feedback in each cycle.

Display @-mention naming conventions and placement rules

Update existing ticket/issue with status changes, comments, or field updates

Scaffold a new behavior definition with BEHAVIOR.md and optional scripts inside an existing addon or framework

Detect requests for iterative autonomous agent loops and route to the appropriate loop executor

Evaluate source access, rights, robots, authorization, provenance, and freshness before automated acquisition or public reuse.

Induct acquired audio/video, transcript sidecars, and source metadata from media-curator into research-complete REF artifacts with timestamp citations and storage policy records

Regenerate CLAUDE.md for Claude Code with hook file architecture

Add structured comments to issues using templates for progress, feedback, or blockers

Pi-local duplicate-precedence fixture.

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

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

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

Resume an interrupted agent loop from last checkpoint

Improve an existing SOUL.md by identifying vague sections, suggesting missing content, and generating calibration examples

Abort a running agent loop and optionally revert changes

Exercise rule delivery.

Execute iterative task loop until completion criteria are met - iteration beats perfection

Decision aid for choosing AEAD, KDF, MAC, and signature primitives — flags anti-patterns (CBC-without-MAC, ad-hoc KDF, key reuse, PBKDF2-on-high-entropy).

Detect visual and UI regressions through screenshot comparison and pixel-diff analysis across browsers and viewports

Generate a `setup.manifest.yaml` file for a project using the `setup.aiwg.io/v1`

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

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

Query and manage the executable feedback debug memory

Orchestrate Elaboration→Construction phase transition with iteration planning, team scaling, and full-scale development kickoff

Orchestrate continuous performance optimization with baseline establishment, bottleneck identification, optimization implementation, load testing, and SLO validation

Demonstrates bounded context handling

Regenerate the canonical WORKSPACE.md-first context graph and provider adapters

Automatically detect and update linked issues based on commits, artifacts, and task events

Select and execute the canonical refresh, existing-project extraction, or legacy AIWG context regeneration branch

Search AIWG knowledge base for help, documentation, and troubleshooting

Global duplicate-precedence fixture.

Generate or complete marketing intake forms (campaign-intake, brand-profile, option-matrix) with interactive questioning and optional guidance

Audit CI workflow files for supply-chain risk — unpinned actions, unpinned container images, pull_request-triggered jobs with secret access, curl-pipe-shell installers, and bare :latest tags. Produces