convex-add

Add a capability to the CURRENT Convex app — consults the served Convex capability catalog for always-current procedures (billing, crons, auth, agent, search, …); falls back to built-in hosting or @convex-dev component search. TRIGGER when the user runs /add, or asks to add hosting/publishing or any backend capability to an existing Convex app.

Quality

79%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/convex-add/SKILL.md

Quality

Content

75%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 tight, well-sequenced instruction skill with concrete commands and a clear catalog-first/fallback structure. The main gaps are the absence of an explicit validation/feedback loop in the workflow and references to scripts/README with no bundle files to back them.

Suggestions

Add an explicit validation step to the workflow (e.g. after installing a component, verify it imports/compiles before confirming to the user) to create a validate→fix→retry feedback loop for the install-and-wire operation.

Provide a literal curl example for fetching the catalog (with the 4s timeout flag) so the first workflow step is copy-paste ready rather than implied.

Either bundle the referenced /add-hosting, /add-component scripts and README under scripts/ and references/ or note that they are sibling skills, so the in-body references resolve to real files.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence without explaining what Convex is, but the intro paragraph restates the fallback already covered in the Workflow, a minor trim opportunity that keeps it just below the 5 anchor.	4 / 5
Actionability	Concrete guidance is present — the exact catalog URL with a 4s timeout, /add-hosting and /add-component with ADD_TERM set, and the CANDIDATES output — but no literal curl command is shown, leaving a minor gap versus copy-paste-ready 5.	4 / 5
Workflow Clarity	A clear numbered sequence with a confirmation checkpoint in step 5; however the install-and-wire operation lacks an explicit validation/feedback loop, so it sits below the 5 anchor that requires explicit validation and error-recovery steps.	4 / 5
Progressive Disclosure	Well-organized into Workflow and Rules sections, but the body references /add-hosting, /add-component, and a README with no corresponding bundle files present, a minor organization gap below the 5 anchor.	4 / 5
	Total	16 / 20 Passed

Description

83%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 strong, third-person description that explicitly states both capability and trigger conditions with concrete, natural-language terms. Minor broadness in 'any backend capability' and lack of synonym coverage keep trigger quality and distinctiveness just below ceiling.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions — "consults the served Convex capability catalog", "falls back to built-in hosting or @convex-dev component search" — with only minor coverage gaps, fitting the 'lists several specific actions' anchor rather than the fully comprehensive 5.	4 / 5
Completeness	It explicitly answers both what ("Add a capability... consults the catalog... falls back") and when (concrete TRIGGER phrases), matching the anchor that requires clear answers to both with concrete triggers.	5 / 5
Trigger Term Quality	The explicit "TRIGGER when the user runs /add, or asks to add hosting/publishing or any backend capability" gives good natural keyword coverage; it stops short of the 5 anchor's synonym/extension comprehensiveness.	4 / 5
Distinctiveness Conflict Risk	Scoping to the "CURRENT Convex app" with /add and hosting/publishing triggers gives a clear niche; the broad "any backend capability" phrasing leaves minor overlap risk, so it sits just below the 5 anchor.	4 / 5
	Total	17 / 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-add/SKILL.md
Commit: 694ff71

Reviewed: 1 day 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.