AC zenodo-skill
Use whenever the user mentions Zenodo, depositing or publishing research artifacts (datasets, software, papers, posters) to Zenodo, minting a DOI for a dataset/code release, uploading files to a Zenodo record, creating a new version of a Zenodo deposit, or searching Zenodo records. Covers the full Zenodo REST API workflow — create deposition, upload files via the bucket API, set metadata, publish, version, and search — for both production (zenodo.org) and sandbox (sandbox.zenodo.org).
As a process C 60/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice
How to improve
- For Hermes the description must be one sentence under 60 characters; move the conditions to a "When to Use" section.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 2
✓ No critical or high findings
Medium and low: 2
-
low Exfiltration
net-credential-usereferences/examples.md:61Credential used in a network call (verify the destination is the intended service) (test fixture / example file; documentation of a security skill)DRAFT=$(curl -sS "$DRAFT_URL" -H "Authorization: Bearer $ZENODO_TOKEN")
fixturesecurity skill -
low Exfiltration
net-credential-usereferences/examples.md:66Credential used in a network call (verify the destination is the intended service) (test fixture / example file; documentation of a security skill)curl -sS -X DELETE "$BUCKET/old-data.csv" -H "Authorization: Bearer $ZENODO_TOKEN"
fixturesecurity skill
Files scanned: 8. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-long-hermesdescription is 489 chars; the Hermes authoring standard requires ≤ 60 (one sentence, ending with a period) - note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 60/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 30Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 23 mutating operations with no state check
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 60Consistency. The Hermes dialect needs category and tags
- 70When it triggers. States when to use, but not when not to
- 100Steps. 15 steps
- 100Failures and branches. 1 branches, has a failure section
- 100Execution cost. Instruction body is 1569 tokens
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +3Description length 489: enough signal without eating the budget
- +4Structure: 13 headings
- +3Step-by-step instructions: 15 items
- +4Has examples (9 code blocks)
- +4Reference files are cited in the instructions (3 of 3)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 82.