validate-connector

Validate an existing knowledge base connector against its service's API docs

Quality

65%

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/validate-connector/SKILL.md

Quality

Content

77%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.

The body is an exceptionally concrete, well-sequenced audit checklist with strong actionability and clear validation checkpoints. Its main weaknesses are token-efficiency (the same checks are restated across steps, the severity catalog, and a final checklist summary) and the absence of any progressive disclosure for a skill of this length.

Suggestions

Eliminate the triple repetition: drop the final Checklist Summary (it restates Steps 1-10) and have Step 11's severity catalog reference the step numbers instead of re-listing each check.

Move the long severity reference catalog (Step 11) and/or the per-domain deep checklists into a reference file (e.g. references/severity-catalog.md) and link to it from SKILL.md, giving the overview a leaner top-level shape.

Tighten a few explanatory passages in Steps 4-6 that restate the consequence of an issue already covered by the checkbox itself.

Dimension	Reasoning	Score
Conciseness	The body is dense and avoids explaining concepts Claude already knows, but it repeats the same checks three times — once in Steps 3-10, again in Step 11's severity groupings, and again in the final Checklist Summary — which is more than minor trimmable padding. It is not a 4 because the redundancy is substantial rather than minor, and not a 2 because the content itself is domain-specific and largely earns its place.	3 / 5
Actionability	Guidance is highly executable: exact file paths, function names, concrete escape patterns (e.g. `externalId.replace(/'/g, "''")`, `Buffer.byteLength(text, 'utf8')`), and verification commands (`bun run lint`, TypeScript compile). It is not a 4 because specific code and command examples thoroughly cover the common cases.	5 / 5
Workflow Clarity	An explicit 11-step sequence with per-step checklists and a final validation block (lint, TS compile, re-read modified files, report unverified schemas) provides clear checkpoints and a fix-then-verify feedback loop. It is not a 4 because validation steps are explicit and complete rather than having minor gaps.	5 / 5
Progressive Disclosure	The skill is ~390 lines with no bundle files and no references to separate files; all content (including the detailed severity catalog and full checklist) is inline. It is not a 4 because there are no signaled one-level-deep references and content that could plausibly be split (severity reference, per-domain checklists) is inlined; it is not a 2 because section structure is clear and navigable.	3 / 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 is clear and domain-specific but terse: it states one concrete action and the target, with no explicit "Use when..." trigger guidance and limited keyword variations. It clears the bar for a focused, third-person description but leaves trigger discovery under-specified.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks to validate, audit, or review an existing Sim knowledge base connector."

Broaden trigger terms to include natural synonyms users might say ("audit", "check", "review connector", "connector correctness").

Optionally name one or two more concrete actions (e.g. "...cross-references endpoints, OAuth scopes, and pagination against the docs") to lift specificity.

Dimension	Reasoning	Score
Specificity	"Validate an existing knowledge base connector against its service's API docs" names the domain (knowledge base connector) and one concrete action (validate against API docs), but only a single action rather than comprehensive coverage. It is not a 4 because no several specific actions are listed, and not a 2 because it does name a concrete action against a concrete target.	3 / 5
Completeness	The "what" is clear (validate a connector against API docs), but there is no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 3 per the rubric. It is not a 4 precisely because the "when" is absent rather than merely imprecise.	3 / 5
Trigger Term Quality	Terms like "validate", "connector", and "API docs" are relevant, but common variations/synonyms ("audit", "check", "review connector") are missing and there are no file extensions. It is not a 4 because keyword coverage is thin rather than merely missing a few natural terms.	3 / 5
Distinctiveness Conflict Risk	"knowledge base connector" + "API docs" carves a fairly specific niche with low conflict risk, though it could overlap with related connector skills (create/build connector). It is not a 5 because the trigger vocabulary is narrow (essentially one verb), leaving minor overlap risk with closely related skills.	4 / 5
	Total	13 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: simstudioai/sim
Path: .agents/skills/validate-connector/SKILL.md
Commit: 7945b29

Reviewed: 3 days 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.