agentic/code/frameworks/sdlc-complete/templates/hermes/skills/aiwg-orchestrate/SKILL.md
Route structured artifact work to AIWG workflows via MCP with zero parent context cost
npx skillsauth add jmagly/aiwg aiwg-orchestrateInstall 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.
Use when the user asks for:
.aiwg/Do NOT use for one-off questions, short tasks, or conversational replies.
workflow-run with the appropriate workflow namedelegate_task to isolate the AIWG interaction:delegate_task(
goal="Run AIWG workflow: [workflow-name] for [description]. Save artifact to .aiwg/[category]/[filename].md",
context="Project: [project name]. Key constraint: [if any]."
)
Note: Child agents automatically exclude context files (AGENTS.md, SOUL.md) and memory
(MEMORY.md, USER.md) — this is hardcoded behavior, not configurable per-call.
The delegation model is set globally in ~/.hermes/config.yaml under delegation.model.
[date] Created [type] at [path]: [summary]| Approach | Parent context cost | |---|---| | Direct MCP calls | 3,000-8,000 tokens per workflow | | This skill (delegate_task) | ~150-250 tokens per workflow |
Over a session with 5 workflows: 1,250 tokens vs. 40,000 tokens.
Store in MEMORY.md:
[YYYY-MM-DD] Created [artifact-type] at [path]: [one-sentence summary]
Never store artifact body content in memory. The artifact lives in .aiwg/ — use artifact-read to access it.
After delegation returns:
.aiwg/artifact-read (not memory recall)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`.