roadmap-to-improve-plans

Use when turning a roadmap, repo priorities, architecture priorities, chosen opportunities, accepted feature outlines/plans, or “roadmap to plans” request into grouped improvement plan batches for future executors. Writes README.md indexes, 001-*.md/NNN-style plans, optional memo-*.md files, verification gates, drift checks, STOP conditions, rejected approaches, and executor handoff notes.

Quality

92%

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

92%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 well-structured, lean planning skill with concrete templates, explicit validation/STOP gates, and clean progressive disclosure via real reference files. Only minor conciseness redundancy between the workflow and the plan-requirements list.

Dimension	Reasoning	Score
Conciseness	The body is dense and assumes Claude's competence without explaining basic concepts, but the "Plan Requirements" list partially overlaps the decompose step in the Workflow, leaving minor redundancy that could be tightened.	4 / 5
Actionability	For an instruction-only skill the guidance is highly actionable: concrete destination path (`.agents/plans/improvements/<effort-slug>/`), exact template pointers, NNN-prefix convention, an explicit required-fields checklist, and precise STOP conditions.	5 / 5
Workflow Clarity	A clear five-step sequence is paired with explicit validation checkpoints (reconcile current state, verification baseline, drift checks, STOP conditions, Done Criteria) and feedback loops that route design forks to memos or deeper planning.	5 / 5
Progressive Disclosure	The SKILL.md body is an overview that points to three real, one-level-deep reference templates (index-template.md, plan-template.md, memo-template.md) via clearly signaled links, with detail appropriately split out.	5 / 5
	Total	19 / 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.

A strong, third-person description that clearly states both what it produces and when to invoke it, with concrete artifact names and trigger phrases. Trigger-term quality is good but slightly jargon-heavy and could add common synonyms.

Dimension	Reasoning	Score
Specificity	The description enumerates many concrete actions — "Writes README.md indexes, 001-.md/NNN-style plans, optional memo-.md files, verification gates, drift checks, STOP conditions, rejected approaches, and executor handoff notes" — giving comprehensive coverage of the skill's outputs.	5 / 5
Completeness	It explicitly answers both what ("Writes README.md indexes…" with a full artifact list) and when ("Use when turning a roadmap, repo priorities… into grouped improvement plan batches") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Natural terms like "roadmap", "repo priorities", "architecture priorities", "accepted feature outlines/plans", and "roadmap to plans" are present, but the list leans on internal jargon (e.g. "NNN-style plans", "executor handoff notes") and omits common synonyms or file extensions a user might naturally say.	4 / 5
Distinctiveness Conflict Risk	The niche is sharply defined — converting roadmap/opportunity artifacts into grouped NNN-style improvement plan batches with verification gates and STOP conditions — with distinct triggers and minimal overlap risk against adjacent planning skills.	5 / 5
	Total	19 / 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: joshuadavidthomas/agent-skills
Path: roadmap-to-improve-plans/SKILL.md
Commit: 516dee7

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.