rampstackco/claude-skills / skills/oss-contribution-research
oss-contribution-research
VerifiedResearch and prepare an outside contribution to an open-source repo, then stop at a queue item for a human to approve: policy check, intake, duplicate check, reproduction, patch, the repo's own checks, an independent critic rerun, and a disclosed, hashed draft of the exact text to post. Use this skill whenever the user wants to contribute to someone else's repo, fix an upstream bug, pick up a good-first-issue, draft an AI-assisted pull request for an outside project, follow up on their own outside PR, or run a gated contribution pipeline. Triggers on open source contribution, contribute to this repo, upstream fix, outside PR, external PR, good first issue, fix this issue in their repo, contribution research, AI-assisted PR, disclose AI in PR, reply to review on my PR. Also triggers when the user names an issue in a repo they do not maintain and asks for a fix, even if they do not say contribute.
| File | Kind | Size |
|---|---|---|
| README.md | markdown | 366 B |
| SKILL.md | skill md | 18.8 KB |
| references/example-intake-item.md | markdown | 3.3 KB |
| references/policy-classification.md | markdown | 5.0 KB |
| references/pr-description-template.md | markdown | 5.3 KB |
| references/queue-item-template.md | markdown | 6.6 KB |
| references/repro-record-template.md | markdown | 4.9 KB |
references/example-intake-item.md
View on GitHub# Example: intake queue item
A fictional repo, `example-org/feedparse`, has an open issue #412: parsing an RSS feed with an empty `<pubDate/>` raises an exception instead of returning no date. Its CONTRIBUTING file asks outside contributors to comment on an issue and wait for a maintainer before opening a pull request. Gates 1 to 5 pass. Gate 6 has no go-ahead yet, so the output is an intake item, not a patch.
The registry entry for `example-org/feedparse` has:
- status `active`
- review mode `summary`
- cadence cap `1 open PR at a time`
- no prior submission
- `issue_comment` disclosure rule: "Say in the comment that it was drafted by an AI agent and reviewed by the user before posting."
- `issue_comment` disclosure template: `This comment was drafted by an AI agent and reviewed by me before posting.`
````markdown
Title: [intake] example-org/feedparse#412 ask to fix empty pubDate exception
## Target
- item_id: feedparse-412-intake-empty-pubdate
- repo: example-org/feedparse
- url: https://github.com/example-org/feedparse/issues/412
- action: intake
## Policy
allows: CONTRIBUTING.md:41 "AI-assisted contributions are welcome if disclosed" (https://github.com/example-org/feedparse/blob/main/CONTRIBUTING.md). Disclosure for issue_comment: say the comment was drafted by an AI agent and reviewed by the user before posting.
## Gates
- intake: N/A | this item is the intake request (CONTRIBUTING.md:18 asks for a comment first)
- duplicate: PASS | no open PR body names `example-org/feedparse#412`, no assignee, no claim in 6 comments; open PRs listed 2026-10-17
- cadence: PASS | last submission none in the posted ledger; cap 1 open PR at a time
- repro: N/A | no patch yet (issue reproduced locally on main at a1b2c3d with the feed in the issue)
- checks: N/A | no patch yet
- size: PASS | comment only
- critic: N/A | no patch yet
## Disclosure
- format: issue_comment
- text: This comment was drafted by an AI agent and reviewed by me before posting.
## Summary
The feed parser crashes when a feed item has an empty publication date tag, instead of treating the date as missing. The issue is open, confirmed by two users, and nobody has claimed it. The repo asks outside contributors to check in before opening a pull request, so this comment asks whether a fix is welcome. No code has been written yet.
Files touched: none. Lines: +0 / -0. Branch: none yet.
## Exact text to post
```text
Reproduced on main (a1b2c3d) with the feed attached above: an empty <pubDate/> raises ValueError in parse_date instead of returning None.
A fix would treat an empty or whitespace-only date as missing, with a test for this feed.
Would a pull request for this be welcome?
This comment was drafted by an AI agent and reviewed by me before posting.
```
## Hash
af8a741e1fee86268cc1e637f27ca75e03c531de6b9a9dbfc3ad70e7a8811aa5
````
What happens next:
- Before filing, the item is run through the poster's fixture dry-run with the local registry. It reports one planned comment on `example-org/feedparse#412` with the exact text, and the hash matches.
- The user reads the Summary and the exact text on their phone and comments `approve`. The queue's poster then posts the comment.
- When a maintainer replies with a go-ahead, the skill runs again from gate 6. It then produces a `pr` item with a patch, the critic result, and a pull request body.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| writing-skillsobra/superpowersUse when creating new skills, editing existing skills, or verifying skills work before deployment | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| xlsxanthropics/skillsUse this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| shipping-and-launchaddyosmani/agent-skillsPrepares production launches. Use when preparing to deploy to production, or when asking what needs to be in place before shipping. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy. | Stars: 119k | Updated | Claude CodeCodex | Verified | Install |
| childhoodthedotmack/claude-memBabysit a shipped release after merge, publication, or deployment. Verify published packages, production behavior, installed plugins, and late CI or user reports until the observation window is clean; use babysit for PR readiness before release. | Stars: 118k | Updated | Claude CodeCodex | Verified | Install |