init-workspace-rules

Create agent rules.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Risky

Do not use without reviewing

Quality

Content

100%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a lean, well-structured instruction-only skill with concrete domain-specific commands, a clearly sequenced multi-step workflow including explicit validation and HITL checkpoints, and clean self-contained organization. It earns top marks across all four content dimensions.

Dimension	Reasoning	Score
Conciseness	Terse tag-based sections (role/when_to_use/core_concepts/process/validation/pitfalls) with no over-explanation of concepts Claude already knows — every line is an instruction, matching the lean and efficient anchor.	3 / 3
Actionability	Concrete DSL commands with explicit args/formats (LIST/ACQUIRE with XML and TAG), specific paths (rules/local-files-mode.md, list-all-output.md), and a version marker (R2.0) — actionable guidance for an instruction-only skill.	3 / 3
Workflow Clarity	A clear 6-step sequence includes an explicit Step 6 verify/report step and a validation_checklist, with mandatory HITL confirmation for a batch file-creation operation — explicit validation and checklists as the anchor requires.	3 / 3
Progressive Disclosure	A self-contained, well-sectioned single file with no nested external references (no bundle files exist and none are needed), fitting clean organization for a self-contained process skill.	3 / 3
	Total	12 / 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 states a concrete action and domain but is extremely terse, with no "Use when…" trigger guidance and no breadth of actions or trigger terms. It is functional but scores uniformly at the midpoint across all dimensions.

Suggestions

Add a 'Use when…' clause stating the trigger conditions (e.g., 'Use when initializing a local workspace with Rosetta agent rules for a detected IDE or coding agent').

List the concrete capabilities beyond a single verb (e.g., 'acquire, adapt, and install Rosetta rules, skills, agents, workflows, and commands as local files').

Include natural trigger variations users would say, such as 'workspace rules', 'agent configuration', or 'local rule files', to improve distinctiveness and trigger-term quality.

Dimension	Reasoning	Score
Specificity	Names one concrete verb ("Create") and a domain ("agent rules"), but a single bare action with no detail is only just beyond vague — it matches score 2's "names domain and some actions, not comprehensive."	2 / 3
Completeness	It states what ("Create agent rules") but gives no "when" / "Use when…" clause, and the guideline caps completeness at 2 when explicit trigger guidance is missing.	2 / 3
Trigger Term Quality	"agent rules" is a relevant keyword a user might say, but there are no variations or natural trigger phrasing, matching score 2's "some relevant keywords but missing common variations."	2 / 3
Distinctiveness Conflict Risk	"agent rules" targets a niche, but the bare phrase could overlap with other rule/config-creation skills and lacks distinct triggers, matching score 2's "somewhat specific but could still overlap."	2 / 3
	Total	8 / 12 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
description_field	'description' is very short (19 chars), consider making it more detailed	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: griddynamics/rosetta
Commit: 1efa337

Reviewed: 1 day 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.