CtrlK
BlogDocsLog inGet started
Tessl Logo

prp-meta-skill

Authors, refactors, and consolidates Agent Skills PRP-style. Use when the user wants to "create a skill", "write a new skill", "trim a SKILL.md", "split a skill into references", "consolidate workflow skills", "replace duplicated skill logic with composition", redesign a skill workflow, or invokes /prp-meta-skill.

73

Quality

92%

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

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 practices what it preaches: a lean, information-dense spine with mode dispatch, imperative steps, explicit validation gates, and well-signaled one-level-deep references. The one real defect is that the two template files it names (and instructs the agent to copy) are missing from the bundle, breaking both actionability and navigation.

Suggestions

Add the missing `templates/SKILL.template.md` and `templates/reference.template.md` files the body instructs the agent to copy, or remove those pointers from the Resources section, the Create spine (step 3), and references/refactoring-skills.md.

The 'Prescribe the craft, not the content' section spends ~10 lines on abstract doctrine ('Restrictions are not rigidity'); compress it to the two bullet lists and drop the aphorism.

The consolidate quick-spine is the least concrete of the three ('Trace before editing', 'Define the invariant'); consider one concrete artifact name per step (e.g., the inventory format the reference prescribes) so the spine is self-sufficient.

DimensionReasoningScore

Conciseness

The body is a lean spine (~79 lines) with no explanation of concepts Claude already knows; every section carries doctrine ("This skill is built the way it teaches: a lean body that defers detail to `references/`") and detail is deferred rather than restated. Matches the "every token earns its place" anchor.

5 / 5

Actionability

Each mode is a numbered quick-spine with concrete directives ("copy `templates/SKILL.template.md` into `.claude/skills/<name>/SKILL.md`", mandatory-read vs lazy-pointer wording given verbatim). It falls short of fully executable because the body instructs copying template files that are not present in the bundle, so the concrete instruction cannot be followed as written.

4 / 5

Workflow Clarity

Each mode has a clearly sequenced numbered spine ending in an explicit validation step ("Validate & iterate (`references/validation.md`): checklist → skill-reviewer → trigger test"; consolidate ends with "exercise the new workflow end-to-end"), and the refactor mode adds a behavior-preservation check plus a called-out biggest-risk feedback note. Validation is present even for the destructive consolidate path.

5 / 5

Progressive Disclosure

Structure is exemplary: Step 0 mode dispatch, a Resources section wiring every reference with a one-line scope, and references one level deep (verified on disk). Scored against the actual bundle, however, two pointers dangle — `templates/SKILL.template.md` and `templates/reference.template.md` are listed in Resources and referenced in the body and reference files, but no `templates/` directory exists.

4 / 5

Total

18

/

20

Passed

Description

95%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 description: third person, explicit Use-when clause, and an unusually rich set of quoted trigger phrases covering all three modes. The only weakness is the unexplained "PRP-style" modifier, which a user unfamiliar with the term cannot map to a capability.

DimensionReasoningScore

Specificity

"Authors, refactors, and consolidates Agent Skills PRP-style" names the domain and three specific actions in third person. It stays at 4 rather than 5 because "PRP-style" is unexplained jargon and sub-capabilities (validate, trim) surface only indirectly through the trigger phrases.

4 / 5

Completeness

It explicitly answers both questions: the "what" ("Authors, refactors, and consolidates Agent Skills PRP-style") and the "when" ("Use when the user wants to..." followed by concrete trigger phrases). Matches the 5-anchor example pattern exactly.

5 / 5

Trigger Term Quality

Quoted natural phrases a user would actually say — "create a skill", "write a new skill", "trim a SKILL.md", "split a skill into references", "consolidate workflow skills", "replace duplicated skill logic with composition" — plus the /prp-meta-skill invocation cover the full vocabulary including the command name.

5 / 5

Distinctiveness Conflict Risk

It occupies a clear meta-skill niche (authoring/refactoring skills themselves) with distinct triggers like "split a skill into references" that no ordinary domain skill would claim. Minimal conflict risk.

5 / 5

Total

19

/

20

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.

Validation — 15 / 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.