CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

nemoclaw-maintainer-release-notes

Draft a post-tag NemoClaw Announcement from the verified release range and shipped PRs. Use when summarizing a release.

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/nemoclaw-maintainer-release-notes/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

82%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A strong, execution-ready skill: concrete commands throughout, a clear step sequence with verification checkpoints, and disciplined scope (draft-only, no Discussion creation). The main improvement opportunities are deduplicating the Hard Rules against in-body rules and adding explicit failure-recovery guidance for tag/PR verification steps.

DimensionReasoningScore

Conciseness

The body is dense with task-specific guidance and explains nothing Claude already knows; the gh/git commands carry real weight. It loses a point to redundancy — the Hard Rules section restates several in-body rules nearly verbatim ("Never thank internal contributors by default", "Never mention contributor affiliation", "Never create or update a GitHub Discussion"), and the changelog-entry caveat appears twice in Prerequisites.

4 / 5

Actionability

The skill provides copy-paste-ready commands with exact flags and jq filters: the `git ls-remote` tag check, the `gh api repos/.../compare` invocation with a full `--jq` projection, `gh pr view` with a specific `--json` field list, and a runnable membership-check loop with 204/404 interpretation. A concrete example bullet and thank-you block show the expected output format.

5 / 5

Workflow Clarity

Steps 1-7 are clearly sequenced with verification checkpoints (confirm `<current-version>^{}` peels to the intended commit, verify the changelog entry against live compare data, interpret membership codes 204/404). It stops short of a 5 because there are no explicit error-recovery loops — e.g. what to do when the tag doesn't peel to the expected commit, a PR lacks metadata, or the previous-version tag is missing — only a routing note in Hard Rules.

4 / 5

Progressive Disclosure

The body is well-organized into numbered steps, prerequisites, output, and hard rules, with the one external reference ("[Documentation Writing and Review](../_shared/documentation-writing-review.md)") clearly signaled and one level deep. No bundle files exist to offload content into, and the content is appropriately self-contained. The minor gap keeping it from 5 is that the shared-contract path is repo-relative rather than resolvable from the skill directory, and the worked example block in Step 5 is borderline reference material inlined in the main flow.

4 / 5

Total

17

/

20

Passed

Description

66%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A solid, third-person description with a clear 'what' and an explicit 'Use when' trigger, scoped tightly to the NemoClaw release workflow. Its weaknesses are thin action coverage and missing common trigger synonyms such as 'release notes' or 'announce'.

Suggestions

Broaden the trigger clause to cover natural phrasings users would actually say, e.g. "Use when summarizing a release, writing release notes, or announcing a tagged release."

Add one or two more concrete capability verbs to the 'what' portion, e.g. "...verifies the release range, collects shipped PRs, and drafts a post-tag Announcement with categorized changes and contributor thanks."

Include 'release notes' and 'announcement' as explicit trigger terms so the skill fires for those common requests.

DimensionReasoningScore

Specificity

The description names the domain and inputs concretely ("Draft a post-tag NemoClaw Announcement from the verified release range and shipped PRs"), but 'draft' is the only verb, so coverage of the skill's actual actions (verify range, collect PRs, categorize, credit contributors) is partial. It fits the 'names domain and 1-2 concrete actions' anchor better than the 'several specific actions' anchor above.

3 / 5

Completeness

Both parts are present: the 'what' is clear ("Draft a post-tag NemoClaw Announcement from the verified release range and shipped PRs") and the 'when' is explicit ("Use when summarizing a release"). The trigger clause is somewhat narrow — it does not cover 'announce a release' or 'write release notes' phrasing — so it sits at 4 rather than the fully concrete 5.

4 / 5

Trigger Term Quality

Relevant keywords exist ("Announcement", "release", "shipped PRs", "post-tag", "summarizing a release"), but common natural variations are missing — notably "release notes" and "announce a release". This matches the 'some relevant keywords but missing common variations or synonyms' anchor rather than the fuller coverage of a 4.

3 / 5

Distinctiveness Conflict Risk

The description is tightly scoped to a named project and a post-tag workflow ("NemoClaw Announcement", "verified release range", "shipped PRs"), giving it a clear niche with minimal overlap against generic summarization or release-tagging skills. It clearly matches the 'clear niche with distinct triggers' anchor.

5 / 5

Total

15

/

20

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

relative_links

Relative link issues: 1 suspicious

Warning

Total

14

/

16

Passed

Repository

NVIDIA/NemoClaw

Path

.agents/skills/nemoclaw-maintainer-release-notes/SKILL.md

Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.