plugins/utils/skills/aiwg-utils-quickref/SKILL.md
AIWG core utilities quick reference — capability domains and curated discovery phrases for the always-on framing, steward, index, and meta operations
npx skillsauth add jmagly/aiwg aiwg-utils-quickrefInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
This is your always-loaded core directory for AIWG. It does not list every utility skill. Instead, it teaches the cross-cutting domains and gives you curated search phrases that map to aiwg discover lookups, plus a list of which framework-specific quickrefs are loaded.
aiwg discover "<phrase>" and surface the top match to the useraiwg show <type> <name> — never find / ls / ReadDo not enumerate skills from memory. AIWG ships hundreds of skills; you only see the kernel set in your context.
discover → showMost AIWG skills (~385 of 400) are not in your context and are not in <provider>/skills/ either — they stay at $AIWG_ROOT (no per-project copy by default, #1217). Two commands close the loop:
# 1. Find — returns ranked candidates with absolute paths
aiwg discover "<the user's need, paraphrased>"
# 2. Fetch — streams the SKILL.md body for the chosen candidate
aiwg show skill <name> # or: agent | command | rule
discover and show are designed to compose. You should never need to navigate the filesystem to read AIWG content. That's the whole point of the CLI.
Most AIWG skills aren't kernel-listed, so the platform's Skill tool will reject them. This is expected behavior, not a bug. The fallback hierarchy:
aiwg show <type> <name> — primary fetch. Always works regardless of kernel status.aiwg show <type> <name> --json — same fetch with { path, content } envelope, useful for forwarding to a sub-agent.$AIWG_ROOT/agentic/code/ — last-resort fallback. Only if the aiwg CLI itself is broken. The corpus at $AIWG_ROOT/agentic/code/frameworks/<name>/skills/<skill>/SKILL.md and $AIWG_ROOT/agentic/code/addons/<name>/skills/<skill>/SKILL.md is the canonical source — it is always present at the install root and survives any deploy-state corruption.Forbidden after discover returns a path: running find, ls, Glob, or Read on a <provider>/skills/ directory. Those reflect the kernel-pivot deploy state, not the full surface. Use aiwg show.
This is mandated by the skill-discovery HIGH rule. Surface the top match (or top-3) to the user — the search is auditable.
If a user asks about a specific framework's surface, the corresponding quickref is your first stop. These are kernel-resident, so they're already in your context:
sdlc-quickref — software-development-lifecycle workflowsforensics-quickref — incident response and digital forensicsresearch-quickref — research corpus and citation workflowsmedia-curator-quickref — media archive managementmarketing-quickref — marketing operations and campaignsops-quickref — operational infrastructure and runbookssecurity-engineering-quickref — applied security and crypto decisionsknowledge-base-quickref — wiki and documentation workflowsIf a quickref isn't loaded, the framework isn't installed in this project. Use aiwg list to confirm.
These ops skills are kernel-resident — already in your context regardless of aiwg discover. If discovery breaks, you still have the surfaces to repair the install:
steward — provider capability awareness + command routingaiwg-doctor — installation health check with remediation stepsaiwg-refresh — update CLI + redeploy frameworks (alias: aiwg sync)aiwg-status — workspace status dashboardaiwg-help — list every CLI command, args, and examplesuse — deploy a framework or addonPair with the aiwg-steward agent (always-deployed) for orchestrated repair: health check → refresh → re-doctor.
| Domain | Covers | |---|---| | Workspace status & health | Project status, doctor, version, runtime info | | Lookup & query | Capability discovery, KB query, artifact lookup, AIWG help | | Maintenance | Refresh, deploy, hooks, regenerate context files | | Mentions & traceability | @-mention validation, lint, wiring across files | | Activity & provenance | Activity log, provenance records | | Steward & policy | Provider capability awareness, delivery policy |
aiwg discover "aiwg status" # → aiwg-status
aiwg discover "aiwg doctor" # → aiwg-doctor
aiwg discover "version" # → version
aiwg discover "runtime info" # → runtime-info
aiwg discover "project status" # → project-status
aiwg discover "project health check" # → project-health-check
aiwg discover "workspace health" # → workspace-health
aiwg discover "<capability phrase>" # itself — discovery is the entry surface
aiwg discover "aiwg help" # → aiwg-help
aiwg discover "search aiwg knowledge base" # → aiwg-kb
aiwg discover "artifact lookup" # → artifact-lookup
aiwg discover "intake wizard" # → intake-wizard
aiwg discover "aiwg refresh" # → update / refresh
aiwg discover "deploy framework" # → use
aiwg discover "regenerate claude.md" # → aiwg-regenerate-claude
aiwg discover "regenerate AGENTS.md" # → aiwg-regenerate-agents
aiwg discover "hook enable" # → hook-enable
aiwg discover "hook disable" # → hook-disable
aiwg discover "hook status" # → hook-status
aiwg discover "mention validate" # → mention-validate
aiwg discover "mention lint" # → mention-lint
aiwg discover "mention wire traceability" # → mention-wire
aiwg discover "mention conventions" # → mention-conventions
aiwg discover "mention report" # → mention-report
aiwg discover "activity log" # → activity-log
aiwg discover "create provenance record" # → provenance-create
aiwg discover "auto provenance" # → auto-provenance
aiwg discover "aiwg steward" # → steward (agent + policy router)
aiwg discover "delivery policy" # → delivery-policy rule (and related skills)
agentic/code/ ← framework + addon source (NOT deployed; read-only reference)
.aiwg/ ← project artifacts (use cases, ADRs, test plans, etc.)
.claude/skills/ ← always-loaded "kernel" skills (this skill is here)
.claude/.aiwg/skills/ ← bulk AIWG skills (index-discoverable, not flat-listed)
.claude/agents/ ← AIWG agents (platform-native)
.claude/commands/ ← Generated command stubs for tab completion
.claude/rules/ ← AIWG rules
Same shape on every supported provider — see docs/discovery-and-kernel-skills.md for the full per-provider table.
| Situation | Action |
|---|---|
| User asks "what can AIWG do?" generically | Skim the framework quickrefs above; offer the top 3 most-relevant. |
| User asks "find me a skill that does X" | aiwg discover "X" — return ranked candidates. |
| User asks "is there a skill for Y?" and it's not in any quickref | aiwg discover "Y" — don't say "no" without checking. |
| User asks about a specific framework's catalog | Direct them to that framework's quickref + invite a discover query. |
| User asks for AIWG version / config / status | aiwg version, aiwg-status, aiwg doctor. |
aiwg discover "<your need, paraphrased>" --limit 5
If the top-3 results all score below ~0.20, the framework genuinely may not have a curated skill. Then improvise — but always check first.
agentic/code/ are read-only references; project work happens in .aiwg/ and any src/ directories the project owns.aiwg discover doesn't return a match, the skill genuinely may not exist — say so.aiwg help # full CLI surface
aiwg discover "<your need>" # find the right skill
aiwg-kb "<question>" # conceptual help
If still stuck, ask the user — but ask narrowly, with options drawn from the index, not blank.
data-ai
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 corpus radar-status`.
data-ai
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 rationale snippets. Runs via `aiwg corpus radar-report`.
testing
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 a corpus-local map, and stamps documentation/radar/REF-XXX-radar.md. Runs via `aiwg corpus radar-init`.
data-ai
Compute an entity's publication trajectory — per-year paper counts, topic drift, hot-streak detection (≥3 consecutive A-grade years), and career phase. Runs via `aiwg corpus profile-temporal`.