CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

codemap

To generate, populate, and use a project codemap

Quality

68%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./instructions/r3/core/skills/codemap/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

78%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.

A lean, well-structured overview that provides concrete per-OS commands, a clear tool-precedence ladder, and appropriately splits all bulk content into one-level-deep asset files. The remaining gaps are minor: no explicit validation of script success, a couple of awkwardly phrased directives, and an undefined update cadence for CODEMAP.md.

DimensionReasoningScore

Conciseness

The body is lean and imperative with no explanation of concepts Claude already knows; every section carries operational content. Minor trimming remains: "Do not guess or try to figure out those above => if tools existed you would know that already => fallback to scripts and processes below" is awkward arrow-shorthand that partially restates the precedence line.

4 / 5

Actionability

Concrete invocations are given for both OSes ("codemap.sh [WORKSPACE_ROOT] [MAX_DEPTH]", "codemap.ps1 -WorkspaceRoot <path> -MaxDepth <n>") with defaults and output location, plus post-modification commands ("graphify update .", "npx gitnexus analyze --force"). Minor gaps: "make executable first" omits the actual chmod command, and there is no guidance on where to save the read script before executing it.

4 / 5

Workflow Clarity

A clear precedence ladder and a numbered three-step generation workflow (get generator → execute → read/incorporate output) sequence the process, with the read-back step acting as an implicit checkpoint. Not 5 because script success is never explicitly validated and the standing directive "Keep CODEMAP.md initialized and updated REGARDLESS" defines no update trigger.

4 / 5

Progressive Disclosure

The body is a structured overview that cleanly defers bulk material — 275-line scripts and the gitnexus guides — to five existing asset files, each explicitly signaled ("READ SKILL FILE assets/codemap.sh.txt", "MUST APPLY SKILL FILE assets/gitnexus-use.md"). Verified against the bundle: all referenced paths exist and references are one level deep, with no asset file pointing to further bundle files.

5 / 5

Total

17

/

20

Passed

Description

42%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 names a concrete artifact and three actions but is only nine words, with no trigger guidance and no natural synonyms — a user asking for a "project structure overview" or "codebase map" would not surface it. Completeness is capped at 3 by the missing "Use when" clause, and trigger term quality is the weakest dimension.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks for a project overview, codebase structure, architecture map, or needs to orient in an unfamiliar repository."

Include natural synonyms and artifact keywords — "project structure", "codebase map", "architecture overview", "CODEMAP.md" — so the description matches how users actually phrase the request.

Briefly state what the codemap contains (folder/module layout, entry points, file counts) to sharpen the "what" and distinguish it from symbol-level code exploration skills.

DimensionReasoningScore

Specificity

"To generate, populate, and use a project codemap" names the domain and one concrete deliverable-producing action, matching anchor 3 ("names domain and 1-2 concrete actions"). "Populate" and "use" are generic verbs, so it falls short of anchor 4's several specific actions.

3 / 5

Completeness

The "what" is stated (generate/populate/use a codemap) but no "when" or "Use when..." clause appears anywhere, matching anchor 3 and triggering the guideline cap of 3 for missing explicit trigger guidance. Not 4 because the "when" is wholly absent rather than merely implicit.

3 / 5

Trigger Term Quality

The only keyword is the coined term "project codemap"; natural user phrases like "project structure", "codebase overview", or "architecture map" are entirely absent. This matches anchor 2 ("one or two generic keywords; missing the natural phrases users say") rather than anchor 3's partial synonym coverage.

2 / 5

Distinctiveness Conflict Risk

"Project codemap" is a somewhat niche artifact, but the nine-word description could still overlap with code-exploration or project-structure skills and establishes no distinct triggers, matching anchor 3 ("somewhat specific but could still overlap").

3 / 5

Total

11

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

griddynamics/rosetta

Path

instructions/r3/core/skills/codemap/SKILL.md

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.