validate-connector

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

Quality

63%

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

73%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 dense, highly actionable audit checklist with a well-sequenced workflow and genuine validation/feedback loops. Its main costs are redundancy between the per-step checklists and the closing Checklist Summary, and a fully monolithic layout with no reference files to offload detail.

Suggestions

Cut the trailing 'Checklist Summary' section (it duplicates Steps 1–10 nearly item-for-item) or replace it with a 5-line pointer to the steps — the redundancy costs ~30 lines of context with little navigational gain.

Move the Step 11 severity example lists and the selector/attachment rules into references/ files (e.g., REPORTING.md, SELECTORS.md) and keep short pointers inline, turning the monolith into an overview plus one-level-deep references.

Add one or two copy-paste verification commands (e.g., a grep for raw fetch() in the connector directory, or a tsc invocation) so the most mechanical checks are executable rather than descriptive.

Dimension	Reasoning	Score
Conciseness	The body assumes Claude's competence — no basic-concept explanations — but contains real redundancy: the 29-item "Checklist Summary" restates the Step 1–10 checklists, and the severity lists in Step 11 repeat earlier rules. Mostly efficient but could be tightened, matching anchor 3 rather than 4, where only minor trimming would be needed.	3 / 5
Actionability	Guidance is concrete throughout: exact file paths (apps/sim/connectors/{service}/meta.ts, lib/oauth/oauth.ts), exact identifiers (computeContentHash, fetchWithRetry, VALIDATE_RETRY_OPTIONS, syncContext.listingCapped), runnable commands (bun run lint), and precise escape patterns (externalId.replace(/'/g, "''")). Not 5 because there is no copy-paste-ready executable example (e.g., a sample grep/verification command or a snippet of a correct connector pattern) — checks are stated as instructions rather than shown.	4 / 5
Workflow Clarity	Steps 1–11 are clearly sequenced (gather files → pull docs → validate each layer → report by severity → fix), with an explicit validation tail (bun run lint, TypeScript compiles clean, re-read modified files to verify fixes) and a feedback requirement to re-verify fixes and surface unknown schemas instead of guessing. This matches anchor 5's 'explicit validation steps; feedback loops; checklists'; the destructive/batch cap does not apply since validation checkpoints are present.	5 / 5
Progressive Disclosure	No bundle files exist, and the ~390-line body is well-structured into numbered steps, sub-sections, and per-step checklists that are easy to navigate. Minor gaps keep it at 4 rather than 5: no one-level-deep reference files for the bulky material (the severity example lists and the detailed selector-validation rules are natural candidates to offload), so everything lives inline in SKILL.md.	4 / 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 precise and distinctive about its niche, but terse to a fault: it states one action and gives no trigger guidance. Adding a 'Use when...' clause and natural trigger phrases would move it from adequate to strong.

Suggestions

Add a trigger clause, e.g., "Use when asked to validate, audit, or review a Sim knowledge base connector, its OAuth scopes, or its API integration against the service's documentation."

Enumerate 2-3 concrete validation areas (API endpoints, OAuth scopes, pagination, registry entries) so the 'what' is comprehensive rather than a single verb.

Include natural synonyms users would say — "audit", "check", "review the connector" — to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	The description names its domain concretely ("knowledge base connector") and one concrete action ("Validate ... against its service's API docs"), but does not enumerate what validation covers (endpoints, OAuth scopes, pagination, registries). This matches anchor 3 ('names domain and 1-2 concrete actions, but not comprehensive') rather than 4, which requires several specific actions.	3 / 5
Completeness	It has a clear 'what' ("Validate an existing knowledge base connector against its service's API docs") but no 'Use when...' or equivalent trigger clause, so per the rubric guideline a missing 'when' caps completeness at 3. Not 2 because the 'what' is specific, not vague.	3 / 5
Trigger Term Quality	"validate", "connector", "knowledge base", and "API docs" are natural terms for this domain, but common variations users would say — "audit", "review", "check the connector", service-specific names — are absent. Some relevant keywords, missing synonyms, fits anchor 3 and not 4's 'good keyword coverage'.	3 / 5
Distinctiveness Conflict Risk	"knowledge base connector" + "service's API docs" carves a distinct niche unlikely to trigger for unrelated skills; minor overlap risk remains with closely related validation skills in the same codebase (e.g., the 'validate-selector' skill the body references). Fits anchor 4 ('mostly distinct; minor overlap risk') rather than 5, which expects distinct triggers the description does not provide.	4 / 5
	Total	13 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 1 suspicious	Warning

	Total	14 / 16 Passed

Repository: simstudioai/sim
Path: .agents/skills/validate-connector/SKILL.md
Commit: 8725250

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.