CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

claw-release

Release automation for Claw skills and website. Guides through version bumping, tagging, and release verification.

Quality

72%

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 ./skills/claw-release/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

77%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.

The body delivers a highly actionable, well-validated release workflow with concrete commands, checklists, undo guidance, and troubleshooting — top-tier on actionability and workflow clarity. Its weaknesses are structural: a large inline verification script and a stale-prone catalog table bloat the file, and the skill ships no bundle files despite referencing one.

Suggestions

Move the ~70-line signed-manifest verification script into a reference file (e.g., scripts/verify-release.sh or references/verification.md) and keep a one-line pointer plus the trust note in SKILL.md.

Drop or relocate the 'Existing Skills' catalog table — it is time-sensitive data that will drift out of date and can be read from the repository itself.

Ship the referenced ./scripts/release-skill.sh in the bundle (or note its source location) so the Quick Reference and workflow commands point at a real file.

DimensionReasoningScore

Conciseness

Most operational content is efficient (commands, tables, short step lists), but there is notable slack: a ~70-line inline signature-verification bash script, a stale-prone 'Existing Skills' catalog table, an install section, and branding/license boilerplate that do not serve the release workflow. This matches 'mostly efficient but includes some unnecessary explanation or could be tightened' — below 4 because the inline script block and catalog table are substantial trimming targets, above 2 because the core is command-dense rather than padded prose.

3 / 5

Actionability

Guidance is copy-paste ready throughout: exact pre-flight commands ('jq -r '.version' skills/<skill-name>/skill.json'), the release command ('./scripts/release-skill.sh <name> <version>'), push/undo commands, pre-release examples with concrete versions (1.2.0-beta1/alpha1/rc1), and a Common Issues table with specific fixes. It matches the 'fully executable' anchor; the workflow and edge cases (pre-release, undo, troubleshooting) are all covered with runnable commands.

5 / 5

Workflow Clarity

A clear five-step sequence with pre-flight validation (git status, skill.json existence, current version), script-internal validation (semver format, tag-existence check), post-push CI verification URLs, a verification checklist, an explicit undo path, and a feedback-oriented troubleshooting table. This is a destructive/batch operation (commits, tags, pushes, publishes releases), and validation checkpoints are present at every phase, matching the top anchor.

5 / 5

Progressive Disclosure

The body has good section structure, but no bundle files exist (no references/, scripts/, assets/), so the referenced './scripts/release-skill.sh' is not shipped, and the 70-line artifact-verification script is inlined where a one-level-deep reference file would be appropriate. This matches 'some structure but could be better organized; content that should be separate is inline' — not 4 because the inlined verification script and unshipped script reference are real organization gaps, not minor ones.

3 / 5

Total

16

/

20

Passed

Description

58%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.

The description has a clear, specific 'what' with three concrete capability statements, but completely lacks a 'when to use' clause, which caps both completeness and trigger-term quality. Adding an explicit 'Use when...' sentence with natural trigger phrases (e.g., 'publishing a skill release', 'cutting a release', 'version bump for the ClawSec catalog') would lift it substantially.

Suggestions

Add an explicit trigger clause, e.g. 'Use when releasing or publishing a ClawSec skill, bumping skill versions, or creating release tags.'

Include natural user phrasings and synonyms such as 'publish', 'cut a release', 'tag a release', and 'pre-release (beta/rc)' to improve trigger-term coverage.

Mention the full scope of capabilities (commit + tag + push + GitHub Release verification) so the specificity coverage is comprehensive rather than partial.

DimensionReasoningScore

Specificity

The description names the domain ('Release automation for Claw skills and website') and lists three concrete actions ('version bumping, tagging, and release verification'), matching the anchor for several specific actions with minor gaps (e.g., pushing and GitHub Release publishing are not mentioned). It falls short of 5 because coverage is not comprehensive — several parts of the actual release workflow (commit, push, checksum/SBOM generation) are omitted — and clearly above 3, which expects only 1-2 concrete actions.

4 / 5

Completeness

The 'what' is clear and concrete ('Release automation for Claw skills and website. Guides through version bumping, tagging, and release verification.'), but there is no 'when' — no 'Use when...' clause or equivalent trigger guidance, which caps completeness at 3 per the judging guidelines. It is not 4 because 'when' is entirely absent rather than merely under-specified, and not 2 because the 'what' is clear, not vague.

3 / 5

Trigger Term Quality

Phrases like 'release', 'version bumping', 'tagging', and 'release verification' are relevant keywords, but there are no natural trigger phrasings or synonyms a user would say ('publish a skill', 'cut a release', 'semver bump', 'create a GitHub release'). This matches the anchor 'some relevant keywords but missing common variations or synonyms' — not 4, which requires good coverage with only a few natural terms missing.

3 / 5

Distinctiveness Conflict Risk

The 'Claw skills and website' framing carves out a fairly distinct niche with domain-specific triggers ('Claw', 'skill release', 'version bumping'), with only minor overlap risk against generic release/CI or git-tagging skills. It is not 5 because the action words themselves ('release automation', 'version bumping', 'tagging') are generic and could collide with general release-tooling skills absent the Claw qualifier.

4 / 5

Total

14

/

20

Passed

Validation

81%

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

Validation — 13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

frontmatter_unknown_keys

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

Warning

Total

13

/

16

Passed

Repository

prompt-security/clawsec

Path

skills/claw-release/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.