init-workspace-context

Classify workspace mode.

Quality

33%

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

Fix and improve this skill with Tessl

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

Quality

Content

50%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-structured, mostly lean instruction skill with a clear sequenced process, but it inlines a bulky template that should be a reference, leaves a key artifact (`bootstrap_rosetta_files`) undefined, and lacks an explicit validation checkpoint for its config-write step.

Suggestions

Move the full gain.json template into a references/ file (e.g. gain-json.template.json) and link to it, keeping only a brief schema sketch inline.

Enumerate the `bootstrap_rosetta_files` list inline or point to where it is defined so the scan step is directly executable.

Add an explicit validation checkpoint for gain.json (e.g. 'Confirm no existing confirmed values were overwritten; re-read gain.json and verify before returning updated').

Dimension	Reasoning	Score
Conciseness	The body is mostly terse and directive with XML-tagged sections, but the ~50-line inlined gain.json template and occasional explanatory asides (e.g. 'Non-obvious: ...') could be tightened or moved to a reference, matching anchor 3.	3 / 5
Actionability	The process and gain_json_generation steps give concrete, specific guidance, but key execution detail is underspecified — `bootstrap_rosetta_files` is referenced without being enumerated here, leaving a gap that keeps it at anchor 3 rather than 4.	3 / 5
Workflow Clarity	The 7-step process is clearly sequenced, but there is no explicit validation/verification checkpoint for the config-write (gain.json) sub-flow; per the destructive/batch cap guidance this caps the score at 3.	3 / 5
Progressive Disclosure	The body has reasonable section structure via XML tags, but the large inlined gain.json template is content that clearly belongs in a separate reference file, and there are no external references to signal, matching anchor 3.	3 / 5
	Total	12 / 20 Passed

Description

17%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 overly terse, providing only a vague action and domain with no trigger terms or 'when to use' guidance. It is unlikely to surface reliably when users need it and risks overlapping with sibling skills.

Suggestions

Expand the description to list the concrete actions performed, e.g. 'Detects whether a workspace is fresh, existing, or plugin mode and generates/updates gain.json with SDLC tooling config.'

Add an explicit trigger clause such as 'Use when initializing a workspace or before running other init-flow skills.'

Include natural user-facing terms (e.g. 'workspace setup', 'init', 'gain.json') to improve trigger matching.

Dimension	Reasoning	Score
Specificity	The description names the domain (workspace mode) and a single minimal action ("Classify"), matching the anchor 'Names the domain but actions are minimal or generic'; it does not reach 3 because there is no second concrete action and no comprehensiveness.	2 / 5
Completeness	It offers a vague 'what' (classify workspace mode) and no 'when'/trigger clause, matching anchor 2; it is not 3 because the 'when' is entirely absent rather than weakly implied.	2 / 5
Trigger Term Quality	"Classify workspace mode" contains no natural keywords a user would actually say, only technical jargon, matching the score-1 anchor 'No natural keywords; only technical jargon'.	1 / 5
Distinctiveness Conflict Risk	"Classify workspace mode" is very broad with high overlap risk against other workspace/init skills, matching anchor 2; not 3 because it lacks a clearly distinct niche trigger.	2 / 5
	Total	7 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: griddynamics/rosetta
Path: instructions/r2/core/skills/init-workspace-context/SKILL.md
Commit: 044d86c

Reviewed: 21 hours 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.