prp-meta-skill

Author new Claude Code skills PRP-style, and refactor existing fat skills into a lean SKILL.md plus references/. Use when the user wants to "create a skill", "write a new skill", "turn a command into a skill", "split a skill into references", "trim a SKILL.md", "extract output templates from a skill", "make a skill leaner", or invokes $prp-meta-skill.

Quality

96%

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 1-3

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

A lean, information-dense, well-sequenced meta-skill body with explicit validation checkpoints and strong progressive-disclosure intent. The one concrete defect is that two referenced template files do not exist in the bundle, leaving dead pointers in the spine.

Suggestions

Create the missing `templates/SKILL.template.md` and `templates/reference.template.md` files referenced in the Create flow and Resources section, or remove/fix those references so every pointer in the body resolves to a real bundle file.

Verify each `references/` and `templates/` path mentioned in the body against the actual bundle listing before publishing, since broken pointers undercut the progressive-disclosure promise.

Consider adding a one-line note in the Resources section if a template is intentionally left for the author to generate, so the missing file reads as a deliberate instruction rather than a dead link.

Dimension	Reasoning	Score
Conciseness	The body is a lean, opinionated spine with no padding and no explanation of concepts Claude already knows (e.g. it never explains what a skill is). Every section earns its place and detail is deferred to references. It is not the 2-anchor because there is no unnecessary explanation to tighten.	3 / 3
Actionability	Concrete, executable guidance throughout: "copy `templates/SKILL.template.md` into `.agents/skills/<name>/SKILL.md`", "Classify each block: _spine_ vs _extractable_", "Extract verbatim ... Do not reword anything that affects behavior." Per the instruction-only scoring note, the absence of code is not penalized because the numbered steps are specific and copy-pasteable. It is not the 2-anchor because the steps are concrete, not pseudocode or vague direction.	3 / 3
Workflow Clarity	Both Create and Refactor flows are numbered with an explicit validation checkpoint (step 5 "Validate & iterate" / "Validate (references/validation.md)") and the refactor flow adds a behavior-preservation check plus a highlighted biggest-risk warning. It is not the 2-anchor because validation steps are explicit rather than implicit or missing.	3 / 3
Progressive Disclosure	The spine is well-structured with a clear Resources section and one-level-deep references, and all four `references/*.md` paths resolve to real files. However `templates/SKILL.template.md` and `templates/reference.template.md` are referenced in the body (Create step 3 and Resources) but no `templates/` directory exists, so two pointers are dead links that break navigation. It is not the 3-anchor because navigation is not fully easy when following a pointer leads to a missing file; it is not the 1-anchor because the structure itself is sound and shallow rather than monolithic or nested.	2 / 3
	Total	11 / 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.

A strong, third-person, trigger-rich description that clearly answers both what the skill does and when to invoke it, with concrete actions and a distinctive niche. No first/second-person voice issues.

Dimension	Reasoning	Score
Specificity	"Author new Claude Code skills PRP-style, and refactor existing fat skills into a lean SKILL.md plus references/" lists multiple specific concrete actions (author, refactor) tied to a concrete deliverable, matching the 3-anchor. It is not the 2-anchor because both actions are explicit and comprehensive rather than partial.	3 / 3
Completeness	It states what ("Author new Claude Code skills ... and refactor existing fat skills") and when ("Use when the user wants to ... or invokes $prp-meta-skill"), with explicit triggers. It is not the 2-anchor because the "when" is explicit, not merely implied.	3 / 3
Trigger Term Quality	Phrases like "create a skill", "write a new skill", "turn a command into a skill", "split a skill into references", "trim a SKILL.md", "extract output templates from a skill", "make a skill leaner" give good coverage of natural terms users would say. It is not the 2-anchor because it covers many common variations rather than just one.	3 / 3
Distinctiveness Conflict Risk	This is a clear meta-skill niche (authoring/refactoring skills) with distinct triggers unlikely to fire for ordinary coding skills. It is not the 2-anchor because the domain is narrowly scoped and the triggers are specific to this purpose.	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: Wirasm/prp
Path: .agents/skills/prp-meta-skill/SKILL.md
Commit: 1142738

Reviewed: 11 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.