CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

prompt-perfector

Refine or evaluate prompts, preserving intent, output controls and authority. Use for prompt refinement or assessment.

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Medium

Suggest reviewing before use

SKILL.md
Quality
Evals
Security

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.

The body is an exceptionally lean, directive overview with a clearly sequenced workflow, explicit user-control semantics, defined output contracts, and a well-signaled one-level reference to real bundle files. The only notable gap is the absence of a worked example showing what a 'Perfected prompt' or 'Evaluation' output looks like.

DimensionReasoningScore

Conciseness

The body is 27 lines of pure directives ("Refine only unless evaluation or execution is explicit", "Ask only about material ambiguity") with zero explanation of concepts Claude already knows; every token earns its place.

5 / 5

Actionability

Concrete output contracts ("return `Evaluation` with rubric, evidence, verdict, and unresolved risks", "return only `Perfected prompt`") and defined control flags make the guidance executable, but no worked example of either output format exists, short of anchor 5's 'specific examples cover the common cases'.

4 / 5

Workflow Clarity

The 7-step sequence is unambiguous with explicit checkpoints: an ambiguity gate (step 2), an authority gate (step 6), and user feedback loops ("`review first` or `approval`: wait after presenting it"). The destructive/batch cap does not apply since the skill prohibits rather than performs destructive operations.

5 / 5

Progressive Disclosure

Scored against the actual bundle: the body's single link to references/repository-workflow.md resolves to a real file gated by a clear trigger ('For repository-dependent work'), and that reference points to the real scripts/verify-repository-isolation.mjs — one level deep, appropriately split, easy to navigate.

5 / 5

Total

19

/

20

Passed

Description

70%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.

The description clearly states what the skill does and includes an explicit 'Use for' trigger clause, keeping it reasonably distinct within the prompt domain. It is held back by naming only two capability verbs and by missing natural trigger synonyms like 'improve' or 'optimize', leaving it just short of the top anchors.

Suggestions

Enumerate the concrete refinement actions in the description (e.g., 'rewrite for clarity, add schemas and examples, tighten output contracts') so capabilities extend beyond the two verbs 'refine or evaluate'.

Add natural trigger synonyms users actually say — 'improve', 'optimize', 'review a prompt' — to the 'Use for' clause to broaden trigger coverage.

DimensionReasoningScore

Specificity

"Refine or evaluate prompts" names the domain with two concrete actions, but "preserving intent, output controls and authority" states constraints rather than additional capabilities, so coverage is not comprehensive as anchor 4 requires.

3 / 5

Completeness

It answers both parts — what ("Refine or evaluate prompts, preserving intent, output controls and authority") and when ("Use for prompt refinement or assessment") — but the when-clause echoes the what rather than adding concrete trigger phrases, which anchor 5 requires.

4 / 5

Trigger Term Quality

"prompts", "refinement", "assessment", and "evaluate" give good keyword coverage in both verb and noun forms, matching anchor 4's density; common synonyms users say ("improve", "optimize", "rewrite") are missing, so it falls short of anchor 5.

4 / 5

Distinctiveness Conflict Risk

The prompt-refinement niche with intent and authority preservation is a clear, mostly distinct domain; it is not anchor 5 because the description does not differentiate it from closely related prompt skills (the body itself acknowledges an overlapping `prompt` skill).

4 / 5

Total

15

/

20

Passed

Validation

100%

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

BigSimmo/PsychSift

Path

.agents/skills/prompt-perfector/SKILL.md

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.