convex-check-updates

Check the current app's pinned Convex components against recommended versions and upgrade them behind a build gate.

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/convex-check-updates/SKILL.md

Quality

Content

92%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 content is a tight, well-structured workflow with strong validation feedback loops and a copy-paste-ready entry command; the only gap is that mid-workflow steps rely on runtime script output fields without inline examples.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence: a one-line purpose summary, a numbered workflow, and a short rules list, with no padding or explanation of concepts Claude already knows.	5 / 5
Actionability	The opening curl-and-node command is copy-paste ready and output states (COMPONENTS_UP_TO_DATE, COMPONENTS_STALE) are concrete, but later steps like 'apply each migration.steps change' depend on script output structure without inline examples, leaving minor gaps.	4 / 5
Workflow Clarity	The seven-step sequence is explicit with validation checkpoints (per-component gates, revert on gate failure, smoke check after each upgrade) and a clear feedback loop, satisfying the destructive/batch validation requirement.	5 / 5
Progressive Disclosure	Under 50 lines with no need for external bundle files, it is well-organized into a purpose summary, numbered Workflow, and Rules list, meeting the simple-skill exception for a top score.	5 / 5
	Total	19 / 20 Passed

Description

57%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 is specific to a clear Convex niche and states concrete actions, but it omits an explicit 'when to use' trigger clause and relies on somewhat technical phrasing, which limits trigger term quality and completeness.

Suggestions

Add an explicit 'Use when...' clause naming natural trigger phrases, e.g. 'Use when the user wants to check or upgrade Convex components, or asks if their Convex dependencies are up to date.'

Broaden trigger terms with synonyms a user might actually say ('update Convex packages', 'bump Convex versions', 'check for stale Convex components').

Optionally list a couple more concrete actions (e.g. 'revert on gate failure', 'run a smoke check') to lift specificity toward score 4.

Dimension	Reasoning	Score
Specificity	Names the Convex domain and two concrete actions ('Check... against recommended versions' and 'upgrade them behind a build gate'), but does not enumerate several specific actions, fitting the 1-2 concrete actions anchor rather than the broader score 4.	3 / 5
Completeness	The 'what' is clear (check pinned components against recommended versions and upgrade behind a build gate), but there is no 'Use when...' clause or equivalent explicit trigger guidance, capping completeness at 3 per the rubric guideline.	3 / 5
Trigger Term Quality	Contains relevant terms a Convex user would say ('Convex components', 'upgrade', 'versions'), but lacks common synonyms or variations and leans on jargon like 'build gate' rather than natural phrasing.	3 / 5
Distinctiveness Conflict Risk	Targets a clear Convex-specific niche ('pinned Convex components', 'build gate') that is highly unlikely to trigger for unrelated skills, matching the clear-niche anchor.	5 / 5
	Total	14 / 20 Passed

Validation

100%

Warnings & errors only

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: openclaw/clawhub
Path: .agents/skills/convex-check-updates/SKILL.md
Commit: 0180b56

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

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.