improve

Survey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute. Strictly read-only on source code — never implements, fixes, or refactors anything itself. Use when asked to audit a codebase, find improvement opportunities (bugs, security, performance, test coverage, tech debt, migrations, DX), suggest features or where to take the project next (roadmap, product direction), or generate handoff plans for another agent to implement.

Quality

100%

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

100%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is a tightly written, highly actionable senior-advisor workflow with clear phased sequencing, explicit validation checkpoints, and well-structured one-level-deep references to real bundle files. It respects token budget while covering a complex orchestration task.

Dimension	Reasoning	Score
Conciseness	The body is information-dense and assumes Claude's competence — it never explains basic concepts (no 'what a PDF is' equivalents) and every section is actionable guidance; length is justified by a complex multi-phase orchestration workflow rather than padding.	3 / 3
Actionability	Provides concrete executable commands ('git rev-parse --short HEAD', 'tsc --noEmit', 'npm audit', 'gh repo view --json visibility', 'git diff --name-only $(git merge-base...)') and exact file/structure conventions ('plans/README.md', '001-<slug>.md'), matching the copy-paste-ready anchor.	3 / 3
Workflow Clarity	Four phases (Recon, Audit, Vet, Write) are clearly sequenced with an explicit validation checkpoint ('open the cited code yourself and confirm it'), drift detection, and machine-checkable done criteria, satisfying the feedback-loop and checkpoint anchor rather than listing steps without validation (score 2).	3 / 3
Progressive Disclosure	SKILL.md is an overview with three real, well-signaled one-level-deep references (audit-playbook.md, plan-template.md, closing-the-loop.md — all confirmed present in references/), each introduced with explicit 'read it now'/'before writing the first plan' cues; not a monolithic wall or nested references.	3 / 3
	Total	12 / 12 Passed

Description

100%Weight 40%Scale 1-3

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, trigger-rich, and complete, clearly stating both what the skill does and when to use it in a distinct niche. It uses third-person voice and avoids vague fluff.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions — 'audit a codebase, find improvement opportunities (bugs, security, performance, test coverage, tech debt, migrations, DX), suggest features... roadmap, product direction, generate handoff plans' — matching the top anchor rather than naming only a domain (score 2).	3 / 3
Completeness	Explicitly answers both what ('Survey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute') and when ('Use when asked to audit a codebase...'), with an explicit trigger clause, so it is not capped at 2.	3 / 3
Trigger Term Quality	Good coverage of natural terms users would say ('audit', 'bugs', 'security', 'performance', 'tech debt', 'roadmap', 'handoff plans'), not jargon-only; not below at 2 because common variations are well represented.	3 / 3
Distinctiveness Conflict Risk	Clear niche — a read-only advisor that 'never implements, fixes, or refactors anything itself' producing plans for other agents — with distinct triggers unlikely to fire for the wrong skill; third-person voice ('Survey', 'produce') is used throughout.	3 / 3
	Total	12 / 12 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: shadcn/improve
Path: skills/improve/SKILL.md
Commit: 03369ee

Reviewed: 25 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.