init-workspace-rules

Create agent rules.

Quality

26%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./instructions/r2/core/skills/init-workspace-rules/SKILL.md

Quality

Content

52%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 content is a well-sequenced, concise multi-step process with solid verification checkpoints, but it is instruction-only with no concrete commands or executable examples and no bundle/reference files to offload detail. Actionability and progressive disclosure are the weakest dimensions.

Suggestions

Add concrete, copy-paste-ready commands or syntax for the LIST/ACQUIRE operations (e.g. the exact KB query format and an example call) so the steps are executable rather than descriptive.

Move the per-IDE configure specs and the bootstrap-rule details into references/ files (e.g. configure-specs.md, bootstrap-rules.md) and link to them one level deep to improve progressive disclosure.

Add an explicit validate -> fix -> retry loop in Step 6 for the batch file-generation and merge operations, since these are batch operations where feedback loops matter.

Dimension	Reasoning	Score
Conciseness	The body is tight and assumes Claude's competence (e.g. "Internal knowledge about IDE/agent configuration is obsolete — LIST and ACQUIRE from KB."), avoiding preamble; only minor phrasing could be trimmed, so it sits just below the lean/efficient 5 anchor.	4 / 5
Actionability	Steps are high-level directives ("LIST `configure` IN KB with XML format", "ACQUIRE <selected configs using TAG> FROM KB") with no concrete commands, code, or exact syntax, matching the minimal-concrete-guidance anchor; it instructs more than it makes execution copy-paste ready.	2 / 5
Workflow Clarity	The six steps are clearly sequenced and Step 6 provides explicit verification (count files, no absolute paths, version marker, merged bundles, explicit user confirmation), giving most checkpoints; minor gaps (no explicit re-run/fix loop) keep it below 5.	4 / 5
Progressive Disclosure	There is no bundle (references/, scripts/, assets/ are absent) and the body inlines the full process with no external references or navigation; structure is present via XML tags but content that could live in separate files is all inline, matching the minimal-structure anchor.	2 / 5
	Total	12 / 20 Passed

Description

0%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 a two-word generic phrase ("Create agent rules.") with no concrete actions, no natural trigger terms, and no 'Use when...' clause, so it scores at the floor on every dimension. It fails to communicate either what the skill concretely does or when to invoke it.

Suggestions

Rewrite the description to list concrete actions, e.g. "Copy Rosetta agent rules into the local workspace as full IDE-specific files, with a root entry point and bootstrap rules. Use when initializing or upgrading local agent rule sets for a detected IDE/CodingAgent."

Add an explicit 'Use when...' clause naming natural triggers such as 'set up workspace rules', 'init agent rules', or 'sync Rosetta rules locally'.

Include distinguishing terms (Rosetta, full-copy mode, IDE/CodingAgent, bootstrap) so the description does not collide with generic agent-configuration skills.

Dimension	Reasoning	Score
Specificity	The description is "Create agent rules." — an entirely generic phrase with no concrete actions or domain specifics, matching the 'Helps with documents' anchor for pure abstract language.	1 / 5
Completeness	The field answers only a vague 'what' ("Create agent rules") and provides no 'when' / 'Use when...' guidance at all; per the rubric a missing trigger clause caps completeness, and here even the 'what' is extremely vague.	1 / 5
Trigger Term Quality	"agent rules" is generic jargon and there are no natural trigger phrases a user would utter; nothing like 'set up workspace rules', 'configure agent', or 'init' appears in the description, matching the no-natural-keywords anchor.	1 / 5
Distinctiveness Conflict Risk	"Create agent rules" is entirely generic and would overlap with virtually any agent-configuration skill, matching the 'would conflict with virtually any skill' anchor.	1 / 5
	Total	4 / 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
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
Path: instructions/r2/core/skills/init-workspace-rules/SKILL.md
Commit: 70d401e

Reviewed: 2 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.