code-history

Investigate the history, usage, and liveness of code using search and git blame/log. Use when determining if code is dead, understanding why something exists, finding all callers before refactoring, or deciding whether something is safe to remove. Also useful for answering "who added this and why" or "is anything still using this".

Quality

90%

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

86%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 tight, highly actionable investigation skill with executable commands and a concrete decision table. The only weakness is minor duplication between the inline technique commands and the trailing command reference.

Suggestions

Consolidate the 'Git commands reference' block with the commands already shown in 'Techniques' to remove duplication, or keep the reference only for commands not yet introduced.

Add a brief note in the output format to verify evidence sufficiency (e.g., confirm no transitive callers via re-exports) before finalizing the keep/remove recommendation.

Dimension	Reasoning	Score
Conciseness	Lean, assumes Claude's competence, and avoids explaining git/grep basics, but the 'Git commands reference' block duplicates several commands already shown inline in 'Techniques', which could be trimmed.	4 / 5
Actionability	Provides copy-paste-ready, fully executable commands (grep -rn, git log -S, git blame -L) plus a concrete evidence-to-verdict decision table covering the common cases.	5 / 5
Workflow Clarity	Offers a clear decision framework and a sequenced 5-step output format that functions as a checklist; no feedback loop is needed since this is read-only investigation, but explicit verification of evidence sufficiency is only implicit.	4 / 5
Progressive Disclosure	Under 50 lines with no external references needed, organized into clearly headed sections (Techniques, Decision framework, Output format, Git commands reference) that make navigation trivial.	5 / 5
	Total	18 / 20 Passed

Description

95%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.

A strong description that crisply defines a distinct niche and pairs a clear 'what' with rich, natural 'when' triggers. The only minor gap is that the technique inventory in the 'what' clause is slightly abbreviated relative to the full breadth shown in the body.

Dimension	Reasoning	Score
Specificity	Names several concrete techniques ('search', 'git blame/log') and the actions of determining liveness and finding callers, but stops short of an exhaustive inventory of techniques, leaving minor coverage gaps.	4 / 5
Completeness	Explicitly states both what it does ('Investigate the history, usage, and liveness of code...') and when to use it via a concrete 'Use when...' clause with multiple trigger scenarios.	5 / 5
Trigger Term Quality	Includes highly natural user phrases such as 'is code dead', 'finding all callers before refactoring', 'safe to remove', 'who added this and why', and 'is anything still using this', covering the common synonyms users would actually say.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (code history/liveness investigation) with distinct triggers like dead-code detection and pre-refactor caller enumeration, creating 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
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning

	Total	15 / 16 Passed

Repository: gitlabhq/orbit-knowledge-graph
Path: .claude/skills/code-history/SKILL.md
Commit: a2b60b1

Reviewed: 4 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.