CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

convex-seed

Seed or import data into the Convex database.

Quality

70%

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

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/convex-seed/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

71%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 guide for a simple single-purpose skill: both seeding paths are distinguished, idempotency and a safety rule about secrets/PII are called out, and a verification step exists. The main gap is that the primary workflow (write an internalMutation and run it) and the verification step remain at the hint level rather than copy-paste executable.

Suggestions

Add a minimal re-runnable internalMutation example with the exact `npx convex run <functionName>` invocation so the primary fixtures path is copy-paste executable.

Specify how to verify row counts (e.g., the Convex dashboard table view or a count function via `npx convex run`) and what to do when counts don't match.

DimensionReasoningScore

Conciseness

The body is very lean with no background on Convex or seeding concepts ("Populate tables via an internalMutation seed function (re-runnable) or `npx convex import`, matching the schema"), assuming Claude's competence. However, the Rules section duplicates the workflow — "Make seeding idempotent" restates step 3 verbatim and "Seed via internalMutation or convex import, matching validators" restates steps 1-2 — so a few tokens could be trimmed, keeping it below anchor 5.

4 / 5

Actionability

Real commands and mechanisms are named (`npx convex run`, `npx convex import`, internalMutation, "clear-then-insert or upsert"), but the primary path lacks executable detail: no example internalMutation seed function, no exact `npx convex run <functionName>` invocation syntax, and "Verify row counts" specifies no method (dashboard, count query, or CLI). Missing key details on the main path fits anchor 3 rather than anchor 4's mostly-executable guidance.

3 / 5

Workflow Clarity

A clear 4-step sequence distinguishes both paths ("For fixtures: write an internalMutation...", "For bulk import: shape the data to the schema and use `npx convex import`") and ends with an explicit validation checkpoint ("Verify row counts") plus a safety mechanism ("clear-then-insert or upsert so re-running is safe"), matching anchor 4. Not 5: there is no failure-handling feedback loop (what to do if counts are wrong) and the verification method is unspecified.

4 / 5

Progressive Disclosure

The skill is under 50 lines, single-purpose, and well organized into a summary line, Workflow, and Rules sections with no external references needed or referenced — and no bundle files (references/, scripts/, assets/) exist. Per the guideline for simple skills under 50 lines, well-organized sections alone merit a 5.

5 / 5

Total

16

/

20

Passed

Description

53%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 states a clear, specific niche (seeding/importing data into Convex) in appropriately concise third person, but it is a bare capability statement. It entirely lacks a 'Use when...' trigger clause and natural synonym coverage, which limits discoverability and caps completeness.

Suggestions

Add a 'Use when...' clause with concrete triggers, e.g. "Use when setting up dev fixtures, populating tables after schema changes, importing backfill data, or loading sample/seed data into Convex."

Include natural trigger synonyms users would say: populate, load data, sample data, fixtures, backfill, and import file formats like CSV/JSONL.

Consider mentioning idempotent/re-runnable seeding in the description itself, since it is the skill's defining behavior.

DimensionReasoningScore

Specificity

"Seed or import data into the Convex database" names the domain ("the Convex database") and exactly two actions ("Seed", "import data"), matching the anchor for domain plus 1-2 concrete actions that are not comprehensive. Not 4: it does not list several specific actions (no populate, backfill, or fixture loading); not 2: two named actions exceed 'minimal or generic'.

3 / 5

Completeness

The description answers 'what' clearly ("Seed or import data into the Convex database") but contains no 'when' or trigger guidance whatsoever, which caps completeness at 3 per the judging guideline. Not 4: the 'when' is not weakly implied or explicit — it is entirely absent.

3 / 5

Trigger Term Quality

"Seed", "import data", and "Convex" are phrases a user would naturally say when needing this skill, but common variations and synonyms are absent (populate, load data, fixtures, sample data, backfill, .csv/.jsonl). This fits 'some relevant keywords but missing common variations', below anchor 4's 'good keyword coverage'.

3 / 5

Distinctiveness Conflict Risk

"the Convex database" scopes the skill to a specific platform and the seed/import niche is fairly distinct, leaving only minor overlap risk with closely related skills (other Convex data skills, generic import tooling). Not 5: it lacks explicit distinct trigger phrases that would fully separate it from neighboring skills.

4 / 5

Total

13

/

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

Path

.agents/skills/convex-seed/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.