gitnexus-impact-analysis

Use when the user wants to know what will break if they change something, or needs safety analysis before editing code. Examples: "Is it safe to change X?", "What depends on this?", "What will break?"

Quality

79%

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

Fix and improve this skill with Tessl

tessl review fix ./gitnexus-cursor-integration/skills/gitnexus-impact-analysis/SKILL.md

Quality

Content

88%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 highly actionable with executable commands, a clear sequenced workflow, and thorough validation/feedback loops for a fragile destructive-adjacent operation; its main weakness is that all detail lives inline in one file with no progressive offloading.

Dimension	Reasoning	Score
Conciseness	Dense and almost entirely devoted to GitNexus-specific footguns Claude would not know (worktree mis-detection, silent default-repo resolution, stale/partial/truncated flags); a few prose passages such as the extended UNKNOWN rationale could be trimmed without loss.	4 / 5
Actionability	Provides copy-paste-ready MCP calls with real parameters and executable CLI fallbacks (e.g., `node .gitnexus/run.cjs impact "validateUser" --direction upstream --repo .`) plus concrete sample outputs covering the common cases.	5 / 5
Workflow Clarity	Numbered 0-4 workflow with an explicit checklist, validation checkpoints (staleness re-analyze, partial/truncated re-run, confirm-diffed-checkout), and an explicit risk gate that warns on HIGH/CRITICAL and stops on UNKNOWN.	5 / 5
Progressive Disclosure	Well-organized into clearly labeled sections with no nested references and easy navigation, but it is a single ~150-line file with no bundle files; some detail (risk semantics, riskSharedAxes rules) could be offloaded to a reference file.	4 / 5
	Total	18 / 20 Passed

Description

70%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 trigger-rich and clearly signals when to use the skill with natural user phrasings, but it leans on the "when" at the expense of a more comprehensive, explicit statement of capabilities.

Suggestions

Lead with a concise capability clause (e.g., "Computes the upstream blast radius of a code change and reports breakage risk") before the "Use when" triggers.

Add one or two more natural synonyms to the trigger examples (e.g., "blast radius", "who uses this?") to match the body's coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ("safety analysis before editing code", "know what will break") with 1-2 concrete actions, but does not enumerate a comprehensive capability list such as finding dependents or computing blast radius.	3 / 5
Completeness	Answers both what (determine breakage / safety analysis before editing) and when (explicit "Use when..." with concrete example triggers); the "what" is present but embedded rather than crisply listed as capabilities, keeping it just short of a 5.	4 / 5
Trigger Term Quality	Includes very natural user phrasings ("Is it safe to change X?", "What depends on this?", "What will break?") plus "safety analysis before editing code"; a few synonyms such as "blast radius" or "who uses this" appear only in the body, not the description.	4 / 5
Distinctiveness Conflict Risk	The safety/impact-analysis-before-editing niche has distinct triggers and minimal conflict risk, with only minor overlap against general code-editing or review skills.	4 / 5
	Total	15 / 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: abhigyanpatwari/GitNexus
Path: gitnexus-cursor-integration/skills/gitnexus-impact-analysis/SKILL.md
Commit: 5be80b1

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.