CtrlK
BlogDocsLog inGet started
Tessl Logo

convex

Routes general Convex requests to the right project skill. Use when the user asks which Convex skill to use or gives an underspecified Convex app task.

67

Quality

80%

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/convex/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

85%

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

The body is a concise, actionable routing skill with a clear install-then-route workflow and well-organized sections. Its only weakness is mild verbosity in the Start Here install explanation, which could be trimmed without losing meaning.

Suggestions

Tighten the Start Here block by dropping the redundant sentence about it being the recommended starting point and the trailing restatement of preferring install over manual copying.

DimensionReasoningScore

Conciseness

The body is mostly lean, but the Start Here block contains padded phrasing ("It is the recommended starting point for getting the official Convex guidelines in place and following the current Convex AI setup described in the docs") and restates the install preference, so it could be tightened per the level-2 anchor.

2 / 3

Actionability

It provides an exact copy-paste command ("npx convex ai-files install"), concrete fallback and docs URLs, and a specific skill-to-scenario routing table, giving fully executable guidance.

3 / 3

Workflow Clarity

For a simple routing skill, the sequence is unambiguous: install/refresh guidance first, then route to the most specific skill, with a "When Not to Use" guardrail, and no destructive operations requiring validation.

3 / 3

Progressive Disclosure

The skill is under 50 lines with no need for bundle references, and it is organized into clear sections (Start Here, Route to the Right Skill, When Not to Use), meeting the simple-skill threshold for the top anchor.

3 / 3

Total

11

/

12

Passed

Description

75%

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 clearly defines a routing role with an explicit "Use when" trigger and a distinct niche, answering both what and when. It is slightly held back by a single named action and one somewhat technical trigger phrase rather than broader natural-term coverage.

Suggestions

Add a couple of natural trigger phrasings users would say (e.g., "when unsure which Convex skill fits") alongside "underspecified Convex app task".

Consider naming one or two additional concrete routing actions (e.g., "identifies, recommends, and hands off to") to strengthen specificity.

DimensionReasoningScore

Specificity

"Routes general Convex requests to the right project skill" names the domain and a concrete action, but lists only a single action (routing) rather than multiple specific capabilities, so it stops short of the level-3 anchor.

2 / 3

Completeness

It explicitly states what it does ("Routes general Convex requests to the right project skill") and when to use it via an explicit "Use when..." clause, satisfying both halves required for the top anchor.

3 / 3

Trigger Term Quality

"which Convex skill to use" is a natural user phrase, but "underspecified Convex app task" is more jargon than conversational, and only one trigger scenario is covered, leaving common variations missing per the level-2 anchor.

2 / 3

Distinctiveness Conflict Risk

The router niche is clear and the triggers (general or underspecified Convex requests, choosing a skill) are distinct from the specific task triggers of the skills it routes to, making false triggering unlikely.

3 / 3

Total

10

/

12

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
openclaw/clawhub
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.