waldronlab / waldronlab/agent-protocol-standard
Add a `validate-protocol` skill
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 3
- Forks
- 1
- Avg merge
- 14h 8m
- Merged PRs (30d)
- 23
Description
scripts/validate-protocol.R reports what's wrong. It doesn't say what to do about it, and most of the contributors arriving aren't R users.
A skill should run it, read the errors, and fix what's mechanically fixable: a missing ## Materials heading, a date that doesn't match the top History entry, a name that isn't kebab-case, a frontmatter field under a retired name. Where the fix is a judgement rather than a correction — which paper belongs in protocol_citation, whether the protocol originates a method at all — it should say what the choice is and stop, not guess.
Distinct from the test-protocol harness in #3: this checks that the document conforms to the standard, not that an agent executing it produces the right answer.
Lives at skills/validate-protocol. Pairs with #35 and #36.
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by reading scripts/validate-protocol.R and inspect the existing skills/validate-protocol directory. Add a skill that runs the validator, applies only mechanical corrections such as headings, dates, names, and retired frontmatter fields, and reports judgment calls without guessing. It is done when the skill distinguishes fixable errors from choices and remains distinct from the test-protocol harness in #3.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- r
- Domain
- tooling
- Issue type
- Feature
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Activity status
- Active
- Clarity
- Mostly clear
- Newbie friendliness
- 74/100