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

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

100%

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 tight, actionable reference with concrete git/grep commands, a decision table, and a reporting checklist, organized into clean sections with no redundant concept explanation.

Dimension	Reasoning	Score
Conciseness	Lean and token-efficient — no explaining of concepts Claude already knows; every line is a concrete command, classification rule, or decision entry, with each token earning its place.	3 / 3
Actionability	Provides fully executable, copy-paste-ready commands (grep, git log, git blame, git show) plus a concrete decision table and output checklist.	3 / 3
Workflow Clarity	Techniques are organized, the decision framework table acts as an evidence-to-verdict checkpoint, and the numbered output format is an explicit checklist — clear structure for an investigation task.	3 / 3
Progressive Disclosure	Under 50 lines with no external references needed; content is split into well-organized sections (Techniques, Decision framework, Output format, Git commands reference) that match the simple-skill allowance.	3 / 3
	Total	12 / 12 Passed

Description

100%

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 concrete, well-triggered, and clearly scoped to code-history investigation; it answers both what and when in third person without padding.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "Investigate the history, usage, and liveness of code using search and git blame/log" — naming specific techniques rather than vague abstractions.	3 / 3
Completeness	Explicitly answers both what (investigate history/usage/liveness via search and git) and when ("Use when determining if code is dead..."), with an explicit trigger clause.	3 / 3
Trigger Term Quality	Captures natural phrasings users would say — "is code is dead", "finding all callers before refactoring", "who added this and why", "is anything still using this".	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (code history/liveness via git blame/log) with distinct triggers unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 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
Commit: 00ca361

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.