init-workspace-discovery

Discover tech stack.

Quality

53%

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-discovery/SKILL.md

Quality

Content

68%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 well-structured, lean, and actionable with concrete commands and properly externalized large scripts. Its main weakness is the absence of validation/verification checkpoints in a workflow that performs batch file modifications.

Suggestions

Add an explicit validation/verification step to the process, e.g. 'Verify generated TECHSTACK/CODEMAP/DEPENDENCIES against source artifacts before finalizing' and a .gitignore sanity check, to lift the workflow-clarity cap.

Either inline a minimal executable CODEMAP-generation snippet or explicitly defer to the referenced script with a one-line usage example, so CODEMAP generation is concrete rather than prose-described.

Consider moving the per-file format specs (DEPENDENCIES.md, TECHSTACK.md, CODEMAP.md) into a short reference file or tightening them, to push progressive disclosure toward a clean overview-plus-references split.

Dimension	Reasoning	Score
Conciseness	The body uses lean bullets, imperatives, and tagged sections without explaining concepts Claude already knows; only minor instances could be trimmed, so it is above the midpoint at anchor 4 rather than the fully-lean anchor 5.	4 / 5
Actionability	It provides concrete commands (git ls-files --cached --others --exclude-standard), a real .gitignore block, and references executable bundled scripts, with only minor gaps where CODEMAP generation is described in prose.	4 / 5
Workflow Clarity	Eight clearly sequenced steps are present, but the workflow performs batch file writes and .gitignore modification with no validation/verification checkpoint, which caps workflow clarity at 3 per the destructive/batch guideline.	3 / 5
Progressive Disclosure	The overview references real one-level-deep bundle files (scripts/codemap.sh.txt, codemap.ps1.txt) that are clearly signaled and appropriately externalized; it falls just short of anchor 5 due to minor organization gaps in the inline file-format specs.	4 / 5
	Total	15 / 20 Passed

Description

37%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 extremely terse, conveying a clear but minimal purpose with no trigger guidance, synonyms, or concrete action list. It is barely adequate for invocation and would benefit from expansion.

Suggestions

Add a 'Use when...' clause with concrete triggers, e.g. 'Use during workspace initialization or when the tech stack, code map, or dependencies are missing or stale.'

Enumerate concrete actions to raise specificity, e.g. 'Detects languages, frameworks, build tools, and dependencies; generates TECHSTACK, CODEMAP, and DEPENDENCIES files.'

Include natural synonyms and file artifacts users might mention (technology stack, frameworks, code map, dependencies) to improve trigger-term coverage and distinctiveness.

Dimension	Reasoning	Score
Specificity	The description "Discover tech stack." names the domain (tech stack) but only a single minimal/generic action ("Discover"), matching anchor 2; it does not list concrete actions like anchor 3.	2 / 5
Completeness	It gives a clear "what" (discover the tech stack) but provides no "when"/trigger guidance, so per the missing-'Use when...' cap it cannot exceed 3; it sits above anchor 2 because the what is clear rather than vague.	3 / 5
Trigger Term Quality	"tech stack" is one relevant keyword a user might say, but there are no synonyms or variations (technology stack, frameworks, languages, dependencies), matching anchor 2's one-or-two-generic-keywords profile.	2 / 5
Distinctiveness Conflict Risk	Workspace tech-stack discovery is a somewhat specific niche, but the terse phrasing could still overlap with other init/discovery skills, matching anchor 3 rather than the clearly-distinct anchor 4.	3 / 5
	Total	10 / 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-discovery/SKILL.md
Commit: 044d86c

Reviewed: 20 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.