context-map

Maps file dependencies, flags shared imports, groups files for safe parallel editing before code changes. Use when planning a refactoring, analyzing change impact, or understanding which files a modification will affect.

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

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.

The body is well-organized, concise, and actionable with a clear sequenced workflow and validation checkpoint. Its main weakness is a broken external reference (REFERENCE.md is cited but absent), which undermines progressive disclosure and leaves some workflow detail unreachable.

Suggestions

Add the missing ./REFERENCE.md file so the deferred "Full template, depth levels, partition derivation, Team Lead integration" content is actually reachable, or inline the essential parts and drop the reference.

Add an explicit inline feedback loop for the validation checkpoint (e.g. "If a hit does not open or typecheck fails, fix the map and re-run") rather than only describing the success state.

Tighten the commands so each grep_search/vscode_listCodeUsages snippet is directly runnable with its full arguments, removing any ambiguity about patterns or include patterns.

Dimension	Reasoning	Score
Conciseness	The body is lean and direct, using compact tables and concrete commands without explaining concepts Claude already knows; nearly every token earns its place.	5 / 5
Actionability	Concrete grep_search/vscode_listCodeUsages snippets and a copy-paste map template give mostly executable guidance, but the tool-call snippets are not fully self-contained runnable commands in all cases, keeping it just below a 5.	4 / 5
Workflow Clarity	A clear 4-step sequence includes an explicit validation checkpoint ("every grep_search hit lands in the map; all listed files open without errors"), but the inline error-recovery feedback loop (validate -> fix -> re-validate) is not spelled out, deferring it to REFERENCE.md.	4 / 5
Progressive Disclosure	Structure and one-level-deep reference signaling to REFERENCE.md are good, but the referenced REFERENCE.md file does not exist in the bundle, so the navigation path is broken and content that should be separate cannot actually be reached.	3 / 5
	Total	16 / 20 Passed

Description

92%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 strong, explicitly covering what the skill does and when to use it with concrete actions and natural trigger phrases. It is highly specific and distinct from other skills.

Dimension	Reasoning	Score
Specificity	"Maps file dependencies, flags shared imports, groups files for safe parallel editing" lists three concrete, distinct actions with comprehensive coverage of the skill's purpose.	5 / 5
Completeness	It explicitly states what the skill does (map dependencies, flag shared imports, group files) and when to use it ("Use when planning a refactoring, analyzing change impact..."), matching the anchor for clearly answering both.	5 / 5
Trigger Term Quality	"planning a refactoring, analyzing change impact, or understanding which files a modification will affect" gives good natural trigger coverage, but a few common phrasings (e.g. "refactor", "what files will this touch") are missing, so it is not a 5.	4 / 5
Distinctiveness Conflict Risk	The niche of pre-change file impact mapping for safe parallel editing is clearly bounded with distinct triggers and minimal overlap risk with other skills.	5 / 5
	Total	19 / 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: 1 missing	Warning

	Total	15 / 16 Passed

Repository: monkilabs/opencastle
Path: src/orchestrator/skills/context-map/SKILL.md
Commit: fa0c341

Reviewed: 5 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.