agentic/code/addons/aiwg-utils/skills/contribute-start/SKILL.md
Initialize an AIWG contribution workflow by creating a feature branch, configuring DCO, and linking a tracking issue
npx skillsauth add jmagly/aiwg contribute-startInstall 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 initialize a contribution workflow for AIWG itself: create a feature branch, configure DCO (Developer Certificate of Origin), link to a tracking issue, and set up a working directory for the contribution.
Alternate expressions and non-obvious activations (primary phrases are matched automatically from the skill description):
| Pattern | Example | Action |
|---------|---------|--------|
| Contribute start | "contribute start" | Run aiwg contribute-start |
| New contribution | "new contribution" | Run aiwg contribute-start |
| Init contribution | "init contribution" | Run aiwg contribute-start |
| Start contributing | "start contributing to aiwg" | Run aiwg contribute-start |
| With issue | "start contribution for issue #42" | Run aiwg contribute-start --issue 42 |
| With description | "start a contribution for adding voice support" | Run aiwg contribute-start --description "adding voice support" |
When triggered:
Extract intent:
Run the appropriate command:
# Default: interactive contribution initialization
aiwg contribute-start
# Link to a specific tracking issue
aiwg contribute-start --issue 42
# With branch description (slugified automatically)
aiwg contribute-start --description "add voice support to deploy command"
# Specify contribution type
aiwg contribute-start --type feat
aiwg contribute-start --type fix
aiwg contribute-start --type docs
Report the result — confirm the branch name, DCO status, and working directory path.
| Step | What Happens |
|------|-------------|
| Branch creation | feat/<slug> or fix/<slug> branch created from latest main |
| DCO config | .git/hooks/commit-msg DCO hook installed if not present |
| Working directory | .aiwg/working/contributions/<branch-name>/ created for drafts |
| Issue link | Branch description references issue number if provided |
| Contribution notes | CONTRIBUTING.md read and summarized for context |
AIWG contributions require a Developer Certificate of Origin sign-off on each commit:
Signed-off-by: Your Name <[email protected]>
The contribute-start command installs a commit-msg hook that reminds you to include this. Pass -s to git commit to sign off automatically.
User: "Start a contribution — I want to add cost tracking to the ralph command"
Extraction: Feature contribution, description provided
Action:
aiwg contribute-start --type feat --description "add cost tracking to ralph command"
Response: "Contribution initialized. Branch: feat/add-cost-tracking-to-ralph-command. DCO hook installed. Working directory: .aiwg/working/contributions/feat-add-cost-tracking-to-ralph-command/. Sign your commits with git commit -s."
User: "Start contribution for issue #312"
Extraction: Linked to issue 312
Action:
aiwg contribute-start --issue 312
Response: "Contribution initialized. Branch: feat/issue-312. Working directory created. Issue #312 linked in branch description."
User: "I'm going to fix the install-plugin path bug, set up my branch"
Extraction: Fix type, description from context
Action:
aiwg contribute-start --type fix --description "install-plugin path bug"
Response: "Contribution initialized. Branch: fix/install-plugin-path-bug. DCO hook installed. Ready to commit."
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`.