add-permission-group-item

Add a new governed item to Sim's enterprise permission groups — a boolean restriction, an allowlist, or a denylist — wired end-to-end from the field registry through the capability rule to the server gate that actually refuses. Use when adding a key to `PERMISSION_GROUP_FIELDS` or a capability to `CAPABILITY_RULES`.

Quality

90%

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

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 highly actionable, well-sequenced workflow with strong validation checkpoints and concrete code throughout; its only real gap is conciseness and the absence of progressive disclosure to external reference files for a document of this length.

Suggestions

Tighten the narrative motivation in the opening and the file-by-file descriptions in "Read the system first" so the body earns every token.

Consider extracting the helper-selection tables and the Traps catalog into a one-level-deep reference file (e.g. references/traps.md) and linking from the body, since no bundle files currently exist.

Trim the prose around each Step's rationale to the load-bearing rule, leaving the concrete code and tables to carry the instruction.

Dimension	Reasoning	Score
Conciseness	The body is dense and almost every paragraph carries load-bearing detail (traps, enforcement rationale) without explaining concepts Claude already knows, but a few narrative passages such as the "Twelve keys once shipped with a checkbox" anecdote and the lengthy file-by-file "Read the system first" blurbs could be tightened.	4 / 5
Actionability	Provides copy-paste-ready code for the field entry, capability rule, operation definition, picker, and call-site annotation, plus exact `bun run` verification commands and concrete helper-selection tables covering the common cases.	5 / 5
Workflow Clarity	A clearly sequenced Step 0 through Step 7 with an explicit Step 7 validation block (three audits + type-check + suite), a feedback loop ("if a self-check fires, teach the parsers the new form"), and a final checklist — validation is present for this security-sensitive change.	5 / 5
Progressive Disclosure	Well-organized into clearly headed sections (Read the system first, Steps 0–7, Traps, Checklist) for easy navigation, but no bundle files exist and reference-style material (helper tables, the trap catalog) is inlined in a 274-line document rather than split into one-level-deep references.	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 actions, gives explicit trigger guidance tied to named code symbols, and carves out a distinct niche. Its only weakness is a slight reliance on code-symbol triggers over natural-language synonyms.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions and the full scope — "a boolean restriction, an allowlist, or a denylist — wired end-to-end from the field registry through the capability rule to the server gate that actually refuses", giving comprehensive coverage of the domain.	5 / 5
Completeness	Clearly answers both what ("Add a new governed item ... wired end-to-end ... to the server gate that actually refuses") and when ("Use when adding a key to `PERMISSION_GROUP_FIELDS` or a capability to `CAPABILITY_RULES`") with concrete trigger phrases.	5 / 5
Trigger Term Quality	The "Use when adding a key to `PERMISSION_GROUP_FIELDS` or a capability to `CAPABILITY_RULES`" clause gives good, natural-in-context trigger phrases an engineer would actually say, though it leans on code symbols and misses a few plain-language synonyms like "restrict" or "permission".	4 / 5
Distinctiveness Conflict Risk	Targets a very specific niche (Sim's enterprise permission groups, named registries) with distinct triggers and minimal overlap risk with other skills.	5 / 5
	Total	19 / 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: 3 missing	Warning

	Total	14 / 16 Passed

Repository: simstudioai/sim
Path: .agents/skills/add-permission-group-item/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.