CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

76

Quality

96%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

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 well-crafted lean spine that exemplifies progressive disclosure and provides concrete, sequenced guidance for both authoring and refactoring skills. The main defect is that two referenced template files are missing from the bundle, undermining the otherwise excellent disclosure structure.

Suggestions

Create the missing templates/SKILL.template.md and templates/reference.template.md files referenced in the Create and Resources sections, or remove/redirect those pointers to files that actually exist.

Consider adding a one-line note in the Resources section clarifying that templates/ is created on demand during the Create flow if the templates are not shipped as static files.

Verify every path mentioned in the body resolves to a real bundle file so the disclosed reference graph has no dead links.

DimensionReasoningScore

Conciseness

The body is lean and information-dense, deferring detail to references and practicing the progressive disclosure it teaches; it does not restate concepts Claude already knows and most lines earn their place.

3 / 3

Actionability

Concrete, actionable guidance throughout — specific file paths (`.claude/skills/<name>/SKILL.md`), a classification taxonomy (spine vs extractable), and exact wording for the mandatory-read instruction — with instruction-style steps that are copy-paste ready for an instruction-only skill.

3 / 3

Workflow Clarity

Both Create and Refactor modes are sequenced as explicit numbered workflows with validation checkpoints ('Validate & iterate', 'Behavior-preservation check', step 5 'Validate') and a highlighted risk blockquote, giving clear error-recovery awareness.

3 / 3

Progressive Disclosure

The body is well-structured with a dedicated Resources section and one-level-deep references, but two referenced files — templates/SKILL.template.md and templates/reference.template.md — do not exist in the bundle, breaking navigation paths the skill relies on.

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 description that clearly conveys both the skill's purpose and a rich set of natural trigger phrases. It is concise, specific, and unlikely to conflict with other skills.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Author new Claude Code skills PRP-style' and 'refactor existing fat skills into a lean SKILL.md plus references/' — each tied to specific artifacts rather than vague verbs.

3 / 3

Completeness

Explicitly states what the skill does (author/refactor PRP-style) and when to use it via a 'Use when the user wants to...' clause with enumerated triggers, satisfying both what and when.

3 / 3

Trigger Term Quality

Enumerates natural phrases users would actually say ('create a skill', 'write a new skill', 'turn a command into a skill', 'split a skill into references', 'trim a SKILL.md', 'make a skill leaner') plus the /prp-meta-skill invocation, giving broad coverage.

3 / 3

Distinctiveness Conflict Risk

The niche — authoring and refactoring Claude Code skills PRP-style — is narrow and meta, with distinct trigger phrases unlikely to overlap with domain skills.

3 / 3

Total

12

/

12

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
Wirasm/prp
Reviewed

Table of Contents

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.