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

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a highly actionable, well-sequenced audit checklist with concrete patterns and explicit validation steps, though it is a long monolith with no progressive disclosure into reference files. Splitting the reusable severity lists and per-domain deep-dives into references would improve token efficiency and navigation.

Suggestions

Extract the Step 11 severity report-format lists (Critical/Warning/Suggestion) into a references file (e.g. REPORT_FORMAT.md) and link to it one level deep, removing the redundancy with the inline checklists.

Consider moving the per-domain deep-dives (OAuth scopes, pagination, content deferral) into reference files that the overview links to, reducing the monolithic inline volume.

Tighten remaining redundant phrasing between the per-step checks and the checklist summary to improve conciseness.

Dimension	Reasoning	Score
Conciseness	The body is dense and mostly free of concept explanations Claude already knows (the conventions around listingCapped, contentDeferred, VALIDATE_RETRY_OPTIONS, and the meta/runtime split are genuinely value-add), but at ~370 lines with some redundancy between the per-step checklists and the Step 11 report-format lists it could be tightened, matching 'mostly efficient but could be tightened' rather than the lean level above.	2 / 3
Actionability	Guidance is concrete and executable throughout — specific file paths, function names, and code patterns like externalId.replace(/'/g, "''"), Buffer.byteLength(text, 'utf8'), and Math.min(PAGE_SIZE, remaining) — matching 'fully executable code/commands; copy-paste ready'.	3 / 3
Workflow Clarity	A clear Step 1 through Step 11 sequence with an explicit validation checkpoint in Step 11 (bun run lint, TypeScript compiles, re-read modified files) and a final checklist summary, matching 'clear sequence with explicit validation steps ... checklists for complex processes'.	3 / 3
Progressive Disclosure	Sections are well-organized into discrete steps, but the file is monolithic — no references/scripts/assets bundle exists and content that could be split (e.g. the severity report-format lists) is inline — so it lands at 'some structure but content that should be separate is inline' rather than the well-signaled one-level-deep reference level.	2 / 3
	Total	10 / 12 Passed

Description

50%

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 niche-appropriate but tersely states only the what, with no 'Use when' trigger guidance or coverage of common keyword variations. Adding an explicit trigger clause would lift completeness and trigger-term quality.

Suggestions

Append a 'Use when...' clause naming natural triggers, e.g. 'Use when the user asks to audit or validate a Sim knowledge-base connector, or check a connector against its API documentation.'

Add common keyword variations users would say ('audit', 'check', 'review') to broaden trigger-term coverage.

Optionally name the concrete validation actions (endpoints, OAuth scopes, pagination, registry) to raise specificity to the multi-action level.

Dimension	Reasoning	Score
Specificity	Names the domain (knowledge base connector) and one concrete action ('Validate ... against its service's API docs'), but does not list multiple specific actions, so it sits at the anchor for 'names domain and some actions, but not comprehensive' rather than the level above.	2 / 3
Completeness	It clearly answers what the skill does but provides no 'Use when...' clause or equivalent trigger guidance, which per the judging guidelines caps completeness at 2; it is not a 1 because the 'what' is explicit.	2 / 3
Trigger Term Quality	'validate', 'connector', and 'API docs' are relevant terms a user might say, but coverage is thin with no common variations like 'audit', 'check', or 'review connector'; it is above the 'overly generic / no natural keywords' anchor but short of 'good coverage of natural terms'.	2 / 3
Distinctiveness Conflict Risk	The niche (Sim knowledge-base connectors validated against service API docs) is fairly specific, but the absence of explicit triggers means it could still overlap with generic 'audit/validate code' skills, matching 'somewhat specific but could still overlap' rather than the fully-disambiguated level.	2 / 3
	Total	8 / 12 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: 6f514c1

Reviewed: about 15 hours 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.