map

Generate or update ARCHITECTURE.md — a living map of a project's structure, dependencies, and high-coupling zones. Polyglot-adaptive. Heavyweight (writes ARCHITECTURE.md, dispatches parallel agents). Use only when explicitly asked: /map, "generate ARCHITECTURE.md", "map this codebase", OR when another orchestrator skill (e.g. /feature step_refresh_map) needs to dispatch it programmatically.

Quality

85%

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

Quality

Content

71%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 heavyweight, highly actionable orchestrator skill with clear mode-based sequencing and concrete commands. Its main weaknesses are repeated hedging scaffolding across the inline agent prompts and a dangling reference to an absent 'spec' for diff-aware scoping.

Suggestions

Provide the referenced 'spec' (or inline the Diff-Aware Scoping Logic) so the 'see Diff-Aware Scoping Logic in spec' pointer resolves to an actual file.

Factor the repeated 'examples, not exhaustive ... for any other language specific to the detected language' phrasing out of the three agent prompts into a shared note to cut redundant tokens.

Add an explicit post-assembly validation checkpoint (e.g., verify section headers and metadata block are well-formed) to raise workflow clarity toward a 5.

Dimension	Reasoning	Score
Conciseness	Mostly efficient step lists and mode logic, but the three inline agent prompts repeat hedging scaffolding ('examples, not exhaustive', 'for any other language... specific to the detected language') about half a dozen times, adding tokens that could be factored out.	3 / 5
Actionability	Fully executable guidance throughout — exact git diff commands, parallel Agent dispatch with subagent_type, JSON extraction rules, and concrete thresholds (fan-in >= 3, tree 3 levels / ~30 entries).	5 / 5
Workflow Clarity	Clear multi-mode sequencing with explicit checkpoints (agent retry-then-skip, uncommitted-status precedence, stop-if-no-changes, metadata update); validation is present but a couple of assembly-level checks are implicit rather than checklist-form.	4 / 5
Progressive Disclosure	Body is well-sectioned by mode, but no bundle files exist and the inline three-agent prompts are not split out; moreover 'see Diff-Aware Scoping Logic in spec' references a spec that is not present in the bundle.	3 / 5
	Total	15 / 20 Passed

Description

100%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 specific, third-person, and explicitly answers both what the skill does and when to invoke it, with concrete trigger terms and a clearly bounded niche. It is a strong, well-scoped description.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Generate or update ARCHITECTURE.md', mapping 'structure, dependencies, and high-coupling zones', and 'dispatches parallel agents' — giving comprehensive, concrete coverage rather than minor-gaps.	5 / 5
Completeness	Clearly states what it does ('a living map of a project's structure, dependencies, and high-coupling zones') and an explicit 'Use only when...' clause with concrete trigger phrases, answering both what and when.	5 / 5
Trigger Term Quality	Explicit natural triggers a user would say — '/map', 'generate ARCHITECTURE.md', 'map this codebase' — plus a programmatic-dispatch case, covering synonyms and invocation styles.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (ARCHITECTURE.md generation) with a 'Heavyweight' caveat and programmatic-dispatch note, making overlap with other skills minimal.	5 / 5
	Total	20 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: belchman/claude-skills
Path: plugins/agentic-engineering/skills/map/SKILL.md
Commit: 77a9e6b

Reviewed: 11 days 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.