CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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

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-add/SKILL.md

The canonical home for this skill is convex-add in openclaw/clawhub

SKILL.md
Quality
Evals
Security

Quality

Content

63%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 compact, well-structured instruction skill with a clear fallback-oriented workflow, but it suffers from redundant restating of the same procedure three times and underspecified execution details (no example /add-component invocation, no matching criteria, scripts not present in the bundle). The workflow sequencing and simple-skill organization are solid.

Suggestions

Remove the introductory paragraph (or reduce it to one sentence) and fold the duplicate Rules bullets ("Always try the served capability catalog first", "Never hard-fail on catalog miss") into the Workflow steps, since they restate the same procedure three times.

Make execution concrete: show an example invocation of the /add-component search script with ADD_TERM (e.g. the actual command line) and define what a catalog "match" means (e.g. fuzzy match on title/summary/trigger keywords with a threshold).

Add a validation checkpoint after installing a component (e.g. verify the install succeeded in package.json / dev server output) before confirming to the user, so the final confirmation reflects a verified result rather than an assumption.

DimensionReasoningScore

Conciseness

The body is short (~25 lines) and free of concept explanations, but the intro paragraph fully restates the Workflow section ("Step 1: fetch the served capability catalog... falls back exactly to today's behavior") and two Rules bullets ("Always try the served capability catalog first", "Never hard-fail on catalog miss") restate workflow steps. This duplication is noticeable rather than minor, so it sits at 3 rather than 4.

3 / 5

Actionability

Some concrete guidance exists — the exact catalog URL with a 4s timeout and the /capability/<id>.md fetch pattern — but "run /add-component with ADD_TERM set" gives no example invocation, "Match the request against title/summary/trigger" gives no matching criteria, and the referenced scripts (/add-hosting, /add-component) are absent from the bundle. Gaps exceed the "minor" threshold for a score of 4.

3 / 5

Workflow Clarity

Five clearly numbered steps with explicit branching (catalog match vs. unreachable/no-match fallback) and a final confirmation step ("Confirm the addition to the user with the resulting URL (hosting) or component name"). Not 5 because there is no validation that the installed component actually works (no dev-server check or install-output verification); the operations are additive rather than destructive/batch, so the cap of 3 does not apply.

4 / 5

Progressive Disclosure

The skill is under 50 lines with no bundle files (no references/, scripts/, or assets/ directories exist) and no need for external references; content is self-contained and organized into clear Workflow and Rules sections, satisfying the simple-skill exception for a top score.

5 / 5

Total

15

/

20

Passed

Description

87%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 description: it names concrete actions (catalog consultation, hosting wiring, component-search fallback), scopes itself tightly to existing Convex apps, and includes an explicit TRIGGER clause with concrete trigger phrases. Minor room to improve keyword synonyms and unpack the compressed fallback phrasing.

DimensionReasoningScore

Specificity

Lists several concrete actions — "consults the served Convex capability catalog", "falls back to built-in hosting or @convex-dev component search" — plus a domain list ("billing, crons, auth, agent, search"). Not 5 because the fallback phrasing is compressed jargon with minor coverage gaps; not 3 because it goes well beyond 1-2 actions.

4 / 5

Completeness

Explicitly answers both: what ("Add a capability to the CURRENT Convex app — consults the served Convex capability catalog... falls back to built-in hosting or @convex-dev component search") and when ("TRIGGER when the user runs /add, or asks to add hosting/publishing or any backend capability to an existing Convex app") with concrete trigger phrases.

5 / 5

Trigger Term Quality

Natural trigger terms are present: "runs /add", "add hosting/publishing", "any backend capability", "existing Convex app", reinforced by capability keywords (billing, crons, auth, search). Not 5 because common synonyms like "deploy" or "schedule" are missing; not 3 because coverage is good, not partial.

4 / 5

Distinctiveness Conflict Risk

The description is firmly gated on the Convex niche ("CURRENT Convex app", "existing Convex app") with a distinct /add trigger and capability-specific domains, giving minimal conflict risk with non-Convex skills.

5 / 5

Total

18

/

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

FacundoLucci/autonomous-buyer

Path

.agents/skills/convex-add/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.