CtrlK
BlogDocsLog inGet started
Tessl Logo

convex-explain-app

Explain an existing Convex app — data model + relationships, public vs internal functions, auth/ownership model, components, a request→data flow — read from the schema and function surface. Read-only.

64

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

78%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 well-structured, information-dense body: concrete file names, signals, and worked examples make the descriptive workflow highly actionable, and its short self-contained length suits progressive disclosure perfectly. Weakest points are the absence of an explicit validation/verification loop in the workflow and minor trimmable rationale prose and repetition between Workflow and Rules.

Suggestions

Add an explicit verify step after PRESENT, e.g. "re-read schema.ts and the function list and confirm every claim in the map is traceable to one of them".

Trim the motivational intro sentence and merge duplicated guidance (source-of-truth, authz handoff, next-verb pointers each appear in both Workflow and Rules) into one place.

Make the deployment-introspection path executable by naming the actual MCP tool calls for functionSpec/tables rather than just "via the official MCP".

DimensionReasoningScore

Conciseness

The body is dense with operational content and explains nothing Claude already knows, but includes minor trimmable padding — the motivational intro ("Before you can safely change an app you have to know what it is — and reading 15 function files top-to-bottom is slow and error-prone") and editorial asides like "the single most important thing a newcomer needs". It is not a 3 because none of this is concept explanation, just mild rationale prose with some repetition between Workflow steps and Rules.

4 / 5

Actionability

Concrete, specific guidance throughout — exact files (schema.ts, auth.config.ts, convex.config.ts, http.ts), exact signals (v.id("other") fields, indexes, functionSpec/tables via MCP), an example FK graph, and a worked flow — but it stops short of executable commands (e.g., how to actually fetch functionSpec via the MCP), so it sits at 4 rather than 5.

4 / 5

Workflow Clarity

The 7 DETECT→DATA MODEL→FUNCTION SURFACE→AUTH→COMPONENTS→FLOW→PRESENT steps are clearly sequenced with a branching detection step and an accuracy checkpoint ("if something is ambiguous, say so rather than guessing"), but there is no explicit verify/re-check loop, e.g. re-confirming the produced map against the source — so 4, not 5.

4 / 5

Progressive Disclosure

The body is under 50 lines, needs no external reference files (none exist in the bundle), and is cleanly organized into an intro, a numbered Workflow, and a Rules section — per the judging guidelines this earns a 5 for a self-contained short skill.

5 / 5

Total

17

/

20

Passed

Description

75%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 specific, well-scoped description with excellent distinctiveness, but it omits any "Use when..." trigger guidance, which caps its completeness and weakens trigger-term coverage. Adding an explicit use-when clause with natural user phrasings would lift the two weakest dimensions.

Suggestions

Append a trigger clause such as "Use when the user asks to explain, understand, or map an existing Convex app, its data model, or its auth model before changing it."

Add natural synonyms users would say ("understand", "overview", "architecture map") to improve trigger-term coverage beyond "explain".

Consider naming the typical entry points users mention ("schema.ts", "Convex functions") as concrete trigger terms.

DimensionReasoningScore

Specificity

The description enumerates multiple concrete capabilities — "data model + relationships", "public vs internal functions", "auth/ownership model", "components", "a request→data flow", "read from the schema and function surface" — giving comprehensive coverage of the domain, matching the score-5 anchor rather than 4 where gaps would remain.

5 / 5

Completeness

The "what" is clear and specific, but there is no "Use when..." clause or equivalent explicit trigger guidance, which per the judging guidelines caps completeness at 3; it is not a 4 because the "when" is entirely absent rather than merely implicit.

3 / 5

Trigger Term Quality

Good natural keyword coverage ("Explain", "Convex app", "data model", "auth/ownership", "Read-only") but common variations users would naturally say ("understand", "map", "overview", "architecture") are missing, so it falls between the 3 and 5 anchors — closer to 4.

4 / 5

Distinctiveness Conflict Risk

It carves a clear niche (explaining an existing Convex app, read-only) that is distinct from adjacent audit/fix capabilities and unlikely to trigger the wrong skill, matching the score-5 anchor.

5 / 5

Total

17

/

20

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.

Validation — 16 / 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.