add-integration

Add a complete Sim integration from API docs, covering tools, block, icon, optional triggers, registrations, resolved-secret/model-input safety, and integration conventions. Use when introducing a new service under `apps/sim/tools`, `apps/sim/blocks`, and `apps/sim/triggers`.

Quality

90%

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

Quality

Content

88%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 thorough, highly actionable integration skill with a well-sequenced workflow and explicit validation gates. Main weaknesses are length/redundancy and inlining of detailed reference material that could be progressively disclosed into separate files.

Suggestions

Move the File Handling section and Key Helpers reference table into a separate references file (e.g. references/FILE-HANDLING.md) and link to it from the main body to reduce inline bulk.

De-duplicate OAuth scope guidance: keep it in one place (prose or checklist) rather than repeating across Step, checklist, and 'Common Gotchas' sections.

Consolidate the repeated critical-rules blocks (tool-request-boundary, selector, canonicalParamId) so each rule appears once with a pointer, trimming redundant restatements.

Dimension	Reasoning	Score
Conciseness	The body is dense and mostly assumes Claude's competence with specific rules, commands, and code templates, though it is long and has some redundancy (e.g., OAuth scope guidance repeated in both prose and checklist) that could be trimmed.	4 / 5
Actionability	Provides executable code templates, exact file paths, and concrete commands like `bun run tool-metadata:generate` and `bun run check:tool-request-boundary`, making guidance copy-paste ready across common cases.	5 / 5
Workflow Clarity	An explicit 8-step sequence is given with validation checkpoints and feedback loops (e.g., 'Only proceed when validation passes', `bun run ... :check` gates, regenerate-and-commit steps), covering destructive/generated operations thoroughly.	5 / 5
Progressive Disclosure	Structure is clear and sibling skills are referenced one level deep with explicit pointers (e.g., `.agents/skills/add-tools/SKILL.md`), but substantial reference-grade detail (full file-handling patterns, helper tables) is inlined rather than split into bundle files, and no local references/ directory exists.	4 / 5
	Total	18 / 20 Passed

Description

92%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.

A strong, specific description that names concrete deliverables, provides an explicit trigger clause, and is anchored to distinct repo paths. Only minor room to improve keyword synonym coverage.

Dimension	Reasoning	Score
Specificity	Enumerates multiple concrete components — 'tools, block, icon, optional triggers, registrations, resolved-secret/model-input safety, and integration conventions' — giving comprehensive coverage of the actions the skill performs.	5 / 5
Completeness	It clearly states what the skill does ('Add a complete Sim integration from API docs, covering ...') and gives an explicit 'Use when' clause with concrete trigger paths, satisfying both what and when.	5 / 5
Trigger Term Quality	The natural trigger 'Use when introducing a new service' plus concrete paths like `apps/sim/tools` gives good keyword coverage, though it lacks common synonyms or file-extension variants that would push it to a 5.	4 / 5
Distinctiveness Conflict Risk	The trigger is tied to specific Sim repo paths (`apps/sim/tools`, `apps/sim/blocks`, `apps/sim/triggers`), carving a clear niche with minimal overlap risk against other skills.	5 / 5
	Total	19 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (629 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 3 missing	Warning

	Total	13 / 16 Passed

Repository: simstudioai/sim
Path: .agents/skills/add-integration/SKILL.md
Commit: 7945b29

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.