codemap

Generate comprehensive hierarchical codemaps for UNFAMILIAR repositories. Expensive operation - only use when explicitly asked for codebase documentation or initial repository mapping

Quality

65%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./src/skills/codemap/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 body is a well-sequenced, actionable workflow with concrete commands and a clear bundled-script integration. Its main weakness is the absence of explicit validation/verification steps for a batch, file-mutating operation, which caps workflow clarity.

Suggestions

Add an explicit validation checkpoint after the fixer agents run (e.g., verify each affected codemap.md exists and contains the required Responsibility/Design/Flow/Integration sections) before running codemap.mjs update.

Parametrize or note the hardcoded ~/.config/opencode/skills/codemap path so the commands are portable across installs.

Consider moving the full example codemaps into a references/ template file and signaling it from SKILL.md to tighten the overview.

Dimension	Reasoning	Score
Conciseness	The body is mostly procedural and assumes Claude's competence without explaining basic concepts; minor over-explanation in the Step 1 state-detection branching and the lengthy inline example codemaps keeps it just below a 5.	4 / 5
Actionability	It provides concrete, copy-paste-ready commands (codemap.mjs init/changes/update with flags) and specific include/exclude glob patterns, but the hardcoded ~/.config install path is environment-specific, leaving a minor gap versus fully portable executable guidance.	4 / 5
Workflow Clarity	Steps 1-5 are clearly sequenced with idempotency and change-detection logic, but this batch operation (multiple fixer agents writing codemap.md files and mutating AGENTS.md) has no explicit validation/verification checkpoint on the generated output, so the batch-operation cap of 3 applies.	3 / 5
Progressive Disclosure	The single SKILL.md is well-sectioned and the bundled script is referenced by explicit path in commands with no nested reference chains; the inline example codemaps and detailed content guidance are reasonable as templates, leaving only minor organization gaps.	4 / 5
	Total	15 / 20 Passed

Description

62%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 answers both what and when with an explicit trigger gate and a clear niche, using proper third-person voice. It is held back by a single-action "what" and a thin set of natural trigger terms.

Suggestions

Broaden the "what" with one or two more concrete actions (e.g., 'generate codemaps, detect changed files, and update AGENTS.md') to lift specificity.

Add common natural trigger phrases users would actually say, such as 'codebase map', 'repository overview', or 'understand a codebase', alongside the existing terms.

Dimension	Reasoning	Score
Specificity	"Generate comprehensive hierarchical codemaps" names the domain (repositories) plus one concrete action with useful qualifiers, but stops at a single action rather than a comprehensive action list, matching the score-3 anchor.	3 / 5
Completeness	It states a clear "what" ("Generate comprehensive hierarchical codemaps") and an explicit "when" ("only use when explicitly asked for codebase documentation or initial repository mapping"), satisfying both; the thin single-action "what" keeps it just below a 5.	4 / 5
Trigger Term Quality	Phrases like "codebase documentation", "initial repository mapping", and "UNFAMILIAR repositories" are relevant triggers, but the set is small and "UNFAMILIAR" is unusual framing, leaving common synonyms and variations missing per the score-3 anchor.	3 / 5
Distinctiveness Conflict Risk	The niche of hierarchical codemaps for unfamiliar repos with explicit-request gating is mostly distinct from peer skills, with only minor overlap risk against general documentation skills, fitting the score-4 anchor rather than the fully-niche 5.	4 / 5
	Total	14 / 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
relative_links	Relative link issues: 3 missing, 3 deeper-than-1-level	Warning

	Total	15 / 16 Passed

Repository: alvinunreal/oh-my-opencode-slim
Path: src/skills/codemap/SKILL.md
Commit: 3222930

Reviewed: 1 day 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.