init-workspace-rules
Rosetta skill to create local cached agent rules configured for IDE/OS/project context.
37
35%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Risky
Do not use without reviewing
Optimize this skill with Tessl
npx tessl skill review --optimize ./instructions/r2/core/skills/init-workspace-rules/SKILL.mdQuality
Discovery
7%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This description is too vague and jargon-heavy to be effective for skill selection. It fails to explain what concrete actions the skill performs, uses no natural trigger terms a user would say, and lacks any explicit guidance on when Claude should select it.
Suggestions
Add a 'Use when...' clause with natural trigger terms users might say, such as 'agent configuration', 'setup rules', 'IDE settings', or 'project configuration'.
Replace jargon like 'local cached agent rules' with concrete actions, e.g., 'Creates and caches agent configuration rules tailored to the user's IDE, operating system, and project type'.
Include specific examples of what the skill produces or configures, such as 'generates .rules files, sets up editor-specific agent behavior, configures OS-aware defaults'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description uses vague language like 'local cached agent rules' and 'configured for IDE/OS/project context' without listing concrete actions. It doesn't specify what actions are performed beyond 'create'. | 1 / 3 |
Completeness | The 'what' is vaguely stated ('create local cached agent rules') and there is no 'when' clause or explicit trigger guidance at all. Missing a 'Use when...' clause would cap this at 2, but the 'what' is also weak, so it scores 1. | 1 / 3 |
Trigger Term Quality | The terms 'Rosetta', 'cached agent rules', and 'IDE/OS/project context' are technical jargon that users would not naturally say. There are no natural trigger terms a user would use when needing this skill. | 1 / 3 |
Distinctiveness Conflict Risk | The mention of 'Rosetta' and 'cached agent rules' gives it some specificity that reduces conflict with other skills, but the vague framing around 'IDE/OS/project context' could overlap with other configuration or setup skills. | 2 / 3 |
Total | 5 / 12 Passed |
Implementation
62%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides a well-structured multi-step workflow for creating local cached agent rules with clear sequencing and solid validation checkpoints. Its main weaknesses are the lack of concrete examples (e.g., sample file outputs, IDE-specific format examples) and moderate verbosity in framing sections. The workflow clarity is strong, but actionability suffers from abstract descriptions of adaptation logic without executable or copy-paste-ready examples.
Suggestions
Add a concrete example showing a sample Rosetta file being adapted to a specific IDE format (e.g., before/after with frontmatter transformation) to improve actionability.
Include a sample directory tree showing expected output structure for at least one IDE to make the file mapping in Step 5 more concrete.
Trim the 'when_to_use_skill' section which partially duplicates 'core_concepts' and remove the 'role' tag which adds no actionable information.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is moderately efficient but includes some redundant phrasing (e.g., 'Internal knowledge about IDE/agent configuration is obsolete') and the XML-style tags add structural overhead. The 'when_to_use_skill' section partially restates core_concepts. However, most content is functional and not overly padded. | 2 / 3 |
Actionability | Steps are clearly enumerated with specific commands (LIST, ACQUIRE) and concrete file paths (e.g., 'rules/local-files-mode.md', 'rules/bootstrap-*.md'), but there are no executable code examples, no concrete file format samples, and the configure/IDE adaptation logic is described abstractly rather than with concrete examples of input/output. | 2 / 3 |
Workflow Clarity | The 6-step process is clearly sequenced with explicit validation in Step 6 (count verification, no absolute paths, version marker check, bundled content merge check). There's a feedback loop via HITL confirmation, upgrade mode handles skip logic, and the validation checklist provides a final gate. Destructive operations are guarded by mode checks. | 3 / 3 |
Progressive Disclosure | The skill references external KB resources (configure files, rules, etc.) and mentions exclusion sets, but there are no bundle files provided and no explicit links to supporting documentation. The content is reasonably organized into sections but everything is inline in a single file with no clear pointers to deeper reference material. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- griddynamics/rosetta
- Commit
0f3002b
- Reviewed
Table of Contents
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.