validate-integration

Validate an existing Sim integration (tools, block, registry) against the 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

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/validate-integration/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 highly actionable with a well-sequenced, validated workflow, but it is long and monolithic with a redundant summary section. Tightening redundancy and splitting the detailed checklists into a reference file would improve conciseness and progressive disclosure.

Suggestions

Remove the redundant "Checklist Summary" section, which reiterates items already specified in Steps 1–9, to reclaim tokens without losing information.

Split the per-tool and per-block checklists into a separate reference file (e.g., references/validation-checklist.md) and summarize it in SKILL.md to improve progressive disclosure.

Tighten verbose bullets where the Sim convention is self-evident from the example, keeping only the distinguishing detail.

Dimension	Reasoning	Score
Conciseness	The body mostly conveys Sim-specific conventions Claude would not already know, but at ~320 lines it is padded with a redundant "Checklist Summary" that re-lists items already covered in Steps 1–9 and several verbose bullets that could be tightened.	2 / 3
Actionability	Checklist items give concrete, executable guidance throughout — exact file paths, snake_case ID patterns, `Authorization: Bearer ${params.accessToken}`, condition syntax variants, and template-literal URL examples — making it copy-paste ready.	3 / 3
Workflow Clarity	Steps 1–9 are explicitly sequenced with validation checkpoints in Step 9 (`bun run lint`, TypeScript compiles, re-read modified files) and a fix→revalidate feedback loop, plus a hard rule requiring user confirmation instead of guessed schemas.	3 / 3
Progressive Disclosure	No bundle files exist and the skill is a single ~320-line monolithic document; it is well-sectioned but content that could be split (per-tool vs per-block checklists) is inline, and the under-50-line exception does not apply.	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 concrete about its domain and scope but reads as a single technical action with no "Use when" trigger guidance, leaving every dimension at the mid-level. Adding explicit trigger terms and use-conditions would lift completeness and trigger quality.

Suggestions

Add an explicit "Use when..." clause, e.g. "Use when the user asks to audit, validate, or check an existing Sim integration for correctness against its API docs."

Include natural trigger-term variations users would actually say ("audit", "check", "verify", "review") to broaden trigger coverage.

Enumerate multiple concrete validation actions (e.g., "audit tool params, block↔tool alignment, OAuth scopes, and registry entries") to raise specificity beyond a single verb.

Dimension	Reasoning	Score
Specificity	Names the domain ("Sim integration") and concrete objects ("tools, block, registry") plus the reference ("API docs"), but relies on a single verb ("Validate") rather than listing multiple distinct concrete actions, so it falls short of the 3-anchor and above the vague 1-anchor.	2 / 3
Completeness	It clearly states what the skill does ("Validate an existing Sim integration ... against the service's API docs") but provides no explicit when-to-use trigger clause, which caps completeness at 2 per the judging guidelines.	2 / 3
Trigger Term Quality	"validate" and "integration" are terms a user might say, but the description is technical ("Sim integration", "tools, block, registry") with no "Use when" guidance and missing common variations like "audit", "check", or "verify".	2 / 3
Distinctiveness Conflict Risk	The Sim-integration niche is fairly specific, but without explicit distinct triggers it could still overlap with other Sim-related skills, matching the 2-anchor rather than the trigger-rich 3-anchor.	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-integration/SKILL.md
Commit: 6f514c1

Reviewed: about 16 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.