validate-integration

Validate an existing Sim integration (tools, block, registry, and resolved-secret/model-input boundaries) against the service's API docs and Sim execution conventions

Quality

70%

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%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 highly actionable with a well-sequenced, validated workflow and concrete commands and examples, but it is a long monolithic file with redundant checklist repetition and dense inline sections that could be split into reference files for better progressive disclosure.

Suggestions

Move the dense 'Resolved-Secret Provenance and Model Input' rules (Step 3) into a dedicated reference file and summarize the boundary rules inline with a single link.

Remove or compress the 'Checklist Summary' section since it duplicates the per-step checkboxes, keeping token cost proportional to new information.

Split the per-domain checklists (tools, block, OAuth, deployment, pagination) into separate reference files referenced one level deep from the main steps.

Dimension	Reasoning	Score
Conciseness	The body is domain-specific with no basic-concept padding and assumes Claude's competence, but it is very long, the 'Checklist Summary' repeats many earlier line items, and the dense provenance rules could be tightened; mostly efficient with unnecessary repetition.	3 / 5
Actionability	Fully executable guidance throughout: concrete file paths, exact commands ('bun run tool-metadata:generate', 'bun run docs:check'), real ID examples ('x_create_tweet', 'slack_send_message'), and copy-paste-ready code/template-literal patterns covering common cases.	5 / 5
Workflow Clarity	A clear Step 1–10 sequence with explicit validation checkpoints (the Validation Output list, regen gates, 'revert it once and watch it go red') and feedback loops for the destructive/batch fix operations, so the missing-validation cap does not apply.	5 / 5
Progressive Disclosure	Sections are well-organized and there is one signaled external reference ('.agents/skills/memory-load-check/SKILL.md'), but no bundle files exist and the dense inline provenance rules and repeated checklist content that could live in separate reference files are inlined in a single long monolithic file.	3 / 5
	Total	16 / 20 Passed

Description

62%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, naming the audit domain and its component boundaries, but it omits any 'Use when...' trigger guidance and lacks natural synonym coverage, capping completeness and trigger-term quality at the midpoint.

Suggestions

Append an explicit trigger clause, e.g. 'Use when validating or auditing an existing Sim integration, or when a service integration's tools, block, or registry look out of sync with the API docs.'

Add natural synonyms users might say ('check', 'audit', 'review') alongside 'validate' to improve trigger-term coverage.

Soften or context-frame the jargon ('resolved-secret/model-input boundaries') so the description reads as a trigger a user would actually voice.

Dimension	Reasoning	Score
Specificity	Names the domain ('Sim integration') and multiple concrete validation targets ('tools, block, registry, and resolved-secret/model-input boundaries' against 'API docs and Sim execution conventions'); falls short of 5 because 'Validate' is a single action verb over scoped targets rather than a list of distinct concrete actions.	4 / 5
Completeness	A clear 'what' is present but there is no 'Use when...' clause or equivalent explicit trigger guidance, so per the rubric cap the 'when' is only weakly implied and completeness cannot exceed 3.	3 / 5
Trigger Term Quality	'validate' and 'integration' are natural terms a user would say, but common synonyms (check, audit, review) are absent and the remainder is technical jargon ('resolved-secret/model-input boundaries'), leaving relevant keywords without common variations.	3 / 5
Distinctiveness Conflict Risk	A clear niche (auditing existing Sim integrations against API docs and Sim execution conventions) with highly specific triggers and minimal overlap with other skills.	5 / 5
	Total	15 / 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
referenced_paths_exist	Referenced path issues: 2 missing, 1 deeper-than-1-level	Warning

	Total	14 / 16 Passed

Repository: simstudioai/sim
Path: .agents/skills/validate-integration/SKILL.md
Commit: 804a452

Reviewed: 3 minutes 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.