validate-connector

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

Quality

69%

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

85%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 content is a highly actionable, well-sequenced audit workflow with concrete code, named helpers, and explicit validation feedback loops; its main weakness is that all ~370 lines live inline in SKILL.md with no progressive disclosure to reference files, and the report-format section duplicates the per-step checklists.

Suggestions

Move the per-area detailed checklists (Steps 3-10) into bundled reference files (e.g. references/endpoints.md, references/oauth.md, references/pagination.md) and keep SKILL.md as an overview that links to them, improving progressive disclosure.

Eliminate the duplication between the Step 3-10 checklist items and the 'Report Format' severity bullets by referencing the steps from the report section instead of restating them.

Consider trimming or relocating the long 'Report Format' severity catalog to a reference file so the main body stays lean.

Dimension	Reasoning	Score
Conciseness	The body is dense, operational checklists with no padding about concepts Claude already knows, but the 'Report Format' severity groupings restate the Step 3-10 checklist items, a minor redundancy that could be trimmed; this fits 'efficient; minor instances of over-explanation' and is not a 5 because of that duplication.	4 / 5
Actionability	It provides concrete file paths, named helpers (fetchWithRetry, htmlToPlainText, parseTagDate), copy-paste-ready code patterns (e.g. externalId.replace(/'/g, "''"), Buffer.byteLength(text, 'utf8'), Authorization: Bearer ${accessToken}), and specific commands (bun run lint), fitting 'fully executable; copy-paste ready'.	5 / 5
Workflow Clarity	An explicit 11-step sequence is paired with a validation checkpoint in Step 11 (lint passes, TypeScript compiles, re-read modified files) and a report -> fix -> validate feedback loop plus a closing checklist, fitting 'clear sequence with explicit validation steps; feedback loops; checklists'.	5 / 5
Progressive Disclosure	Headers give the ~370-line body good section structure, but everything is inlined in SKILL.md with no references to separate files and no bundle files present, fitting 'some structure but content that should be separate is inline'; not a 4 because there is no file-level disclosure or navigation.	3 / 5
	Total	17 / 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 specific and clearly distinct within its niche, but it only states a single action and omits any explicit 'when to use' trigger guidance, which caps completeness and trigger coverage at the midpoint.

Suggestions

Add an explicit trigger clause, e.g. 'Use when auditing or verifying an existing Sim knowledge base connector against its service's API documentation.'

Expand the action list beyond a single verb, e.g. 'Validates endpoints, OAuth scopes, pagination, and content handling against API docs and reports issues by severity.'

Include natural synonyms users might say such as 'audit', 'check', or 'review connector' to improve trigger term coverage.

Dimension	Reasoning	Score
Specificity	The description names a concrete action ("Validate an existing knowledge base connector against its service's API docs") and a specific domain, but covers only a single action, matching the anchor for '1-2 concrete actions, not comprehensive'; it is above a 2 because 'validate' is a concrete verb rather than generic language.	3 / 5
Completeness	The 'what' is clear but there is no 'Use when...' or equivalent trigger guidance, so completeness is capped at 3 per the judging guidelines; it is not a 4 because the 'when' is entirely absent rather than merely weak.	3 / 5
Trigger Term Quality	It includes relevant keywords a maintainer might say ('validate', 'connector', 'API docs') but offers no synonyms or variations, fitting 'some relevant keywords but missing common variations or synonyms'; it is not a 4 because coverage is thin rather than merely missing a few terms.	3 / 5
Distinctiveness Conflict Risk	The niche (validating knowledge-base connectors against API docs) is narrow with a distinct trigger and only minor overlap risk against sibling connector skills, fitting 'mostly distinct; minor overlap risk'; not a 5 because some overlap with related connector/build skills remains.	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: 417ae20

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.