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

80%

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

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.

An exceptionally actionable, well-sequenced orchestration skill with real commands, paths, and validation feedback loops throughout. Its weaknesses are token bloat from checklist/step duplication and a monolithic single-file layout with no reference bundle despite section content that clearly warrants it.

Suggestions

Collapse the Complete Checklist to short unchecked item labels and stop restating the full rules from Steps 1–8 verbatim (e.g., the boundary rules appear in both 'Key Patterns' and the Tools checklist) — that alone would cut a large fraction of the file's tokens.

Move the File Handling deep-dive (UserFile definition, upload/download patterns, helpers table, wandConfig) into a references/file-handling.md and keep only a pointer plus the one or two rules that apply to every integration.

Extract the V2 Integration Pattern and the OAuth Scopes / Deployment Availability detail into separate reference files so SKILL.md stays a lean overview with clearly signaled one-level-deep references, matching how it already delegates to add-tools/add-block/add-trigger.

Dimension	Reasoning	Score
Conciseness	Nearly all content is project-specific (registries, checker commands, boundary rules) rather than explanations of known concepts, but the file is heavily padded by duplication: the Complete Checklist restates the step rules almost verbatim, and deep-dive sections (File Handling, V2 pattern, OAuth scopes) bloat what should be a lean orchestrating skill. Mostly efficient but clearly could be tightened — anchor 3, not 4, because the redundancy is pervasive rather than minor.	3 / 5
Actionability	Every step carries exact file paths, registry snippets, and copy-paste commands ('bun run check:bare-icons', 'bun run tool-metadata:generate', 'bun run apps/sim/scripts/check-canvas-sentences.ts --block={service}'), and even failure conditions are named ('fails `bun run check:tool-request-boundary`'). The `{service}`/`{action1}` placeholders are explicitly justified by the skill's templated purpose, so they don't drag it to anchor 4.	5 / 5
Workflow Clarity	Eight explicitly ordered steps, a hard stop-and-escalate rule for unknown response schemas ('you MUST stop and tell the user exactly which outputs are unknown' with four fallback options), per-step validation commands, and a final cross-check checklist — this is the anchor-5 pattern of clear sequence with explicit validation and error-recovery feedback loops.	5 / 5
Progressive Disclosure	Section structure is clear and the pointers to sibling skills (`.agents/skills/add-tools/SKILL.md` → 'Resolved Secrets and Provenance Boundaries', add-block, add-trigger) are well-signaled and one level deep. But no bundle files (references/, scripts/, assets/) exist, and ~630 lines are inlined monolithically — the File Handling, V2, and OAuth-scope sections are prime candidates for separate reference files. Some structure, but content that should be separate is inline — anchor 3.	3 / 5
	Total	16 / 20 Passed

Description

83%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 description that explicitly states what it does and when to use it, with concrete component coverage and distinctive path-based triggers. It loses a little on the trailing abstract terms and untested overlap with its own sibling sub-skills.

Dimension	Reasoning	Score
Specificity	The description lists concrete deliverables — 'tools, block, icon, optional triggers, registrations' — but tails off into generic abstractions ('resolved-secret/model-input safety, and integration conventions') that keep it short of the comprehensive, all-concrete anchor 5. It is clearly above the 1–2 concrete-actions level of anchor 3.	4 / 5
Completeness	It explicitly answers both questions: the 'what' ('Add a complete Sim integration from API docs, covering tools, block, icon, optional triggers, registrations…') and a concrete 'when' ('Use when introducing a new service under `apps/sim/tools`, `apps/sim/blocks`, and `apps/sim/triggers`). This matches the anchor-5 example structure exactly, and is clearly above anchor 4 where the 'when' is less specific.	5 / 5
Trigger Term Quality	'Add a complete Sim integration' and 'introducing a new service' are natural user phrasings, and the directory paths give strong keyword triggers, but common variations like 'connector' or plain service names ('add Slack') are not covered. Good coverage, a few natural terms missing — anchor 4.	4 / 5
Distinctiveness Conflict Risk	The Sim-specific niche and directory-path triggers make it mostly distinct with minimal generic overlap, but it sits in an ecosystem of closely related sibling skills (add-tools, add-block, add-trigger) that a partial request ('add a tool for X') could plausibly route here incorrectly. Fits anchor 4 better than 5.	4 / 5
	Total	17 / 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: 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.