agentic/code/addons/aiwg-utils/skills/steward-prep-delivery/SKILL.md
Steward-assisted prep for filing issues and PRs — environment capture, template selection, duplicate detection, delivery-policy compliance check
npx skillsauth add jmagly/aiwg steward-prep-deliveryInstall 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.
You are walking the user through filing a high-quality issue or PR, mirroring the import pattern used for the recent jmagly→roctinam tester report sweep (Gitea #1264–#1269).
Ask the user: "Is this one bug, or did you find multiple issues in a single session?"
bug-report.md (or feature-request.md if it's a proposal, not a defect)tester-report.md and split during triageimported-report.mdDon't make this decision for them — surface the templates and let them pick.
For bug-report.md, the operator needs to fill in environment info. Help them collect it:
aiwg version
aiwg doctor
node --version
uname -a # OS / kernel
If they're filing on behalf of an agent platform (Claude Code, hermes, Codex, …), make sure the platform name is captured — the same bug can manifest differently across providers.
Run the duplicate-detection helper. The skill's script: entrypoint
(find-duplicates.sh) searches the local aiwg discover index plus the Gitea
issue tracker for likely duplicates of the proposed title or keywords:
aiwg run skill steward-prep-delivery -- "<keywords from the issue title>"
Output: ranked list of existing open issues that match. If any look like duplicates, prefer commenting on them over filing a new one. If none match, proceed to filing.
Help the user fill out the chosen template. Specifically:
Before they click "Submit", confirm:
Delivery policy: read .aiwg/aiwg.config delivery.mode. If direct, the fix will land with Closes #N in the commit (no PR). If pr-required, they'll need a feature branch. If feature-branch, branch only. Tell them what to expect.
No AI attribution: if they're using an AI tool to help draft, the commit/PR must not include Co-Authored-By: <AI> lines or "Generated with" markers. This is the project's no-attribution rule, applied universally.
CI green before done: a commit isn't done until CI passes. Remind them to wait for the run on Gitea, and if it fails, fix it before declaring resolution.
For Gitea issues, use:
aiwg run skill issue-create -- "<title>" --provider gitea --labels "bug"
(Or invoke the relevant template manually via the Gitea web UI — both are fine.)
For PRs that close issues, ensure the body contains Closes #N (or Refs #N if it doesn't fully close).
type(scope): subject form (e.g., bug(steward): path resolution lands at dist/).issue-create — the actual filing surface (Gitea, GitHub, Jira, Linear, local)issue-auto-sync — detects commit ↔ issue links automaticallyaddress-issues — runs issue-driven agent loops to close issues with codeCONTRIBUTING.md — full contributor guide.gitea/ISSUE_TEMPLATE/ — issue templates.gitea/pull_request_template.md — PR templateagentic/code/addons/aiwg-utils/rules/delivery-policy.md — delivery mode ruleagentic/code/frameworks/sdlc-complete/rules/no-attribution.md — no-attribution ruledata-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`.