skill-creator

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or iterate on skill quality. Triggers: "create a skill", "make a new skill", "build a skill for", "write a skill that", "skill for doing X", "I want a skill to", "new skill", "design a skill", "scaffold a skill", "improve this skill", "optimize this skill", "this skill isn't working well", "evaluate this skill", "score this skill", "how good is this skill", "run evals on", "benchmark this skill", "test this skill's quality", "skill quality", "skill performance". Also triggers when a user describes a repeatable workflow they want to automate, says "I keep doing X manually", "can you remember how to do X", or "turn this into a skill".

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

85%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 skill-creator workflow with clear routing, validation checkpoints, feedback loops, and excellent progressive disclosure through verified reference files. Slightly verbose in its illustrative example scorecard and benchmark sections, and some actionability is structural rather than executable, keeping conciseness and actionability at 4.

Suggestions

Tighten Step 7's illustrative scorecard and the benchmark table — they are example padding that could be condensed or moved to references/skill-examples.md to improve conciseness.

Replace structural meta-instructions ('Every skill should have...') in Steps 2-3 with a concrete minimal SKILL.md skeleton the model can copy, raising actionability.

Trim the 'Philosophy' and 'Core rule' editorial paragraphs to single-line imperatives; the rules they state are already enforced in the later checklists.

Dimension	Reasoning	Score
Conciseness	Mostly efficient — terse tables and prose that assume Claude's competence with no concept-explaining padding — but the illustrative example scorecard in Step 7 and the benchmark table add some bulk that could be trimmed; not a 5 because of those minor over-explanation instances.	4 / 5
Actionability	Provides concrete commands (`command -v tool`, `tool auth status`, `curl -s endpoint`), explicit decision-table patterns, and a numbered checklist, but much guidance is structural/meta rather than executable code for this skill's own task; as an instruction-only skill the concrete specific guidance is actionable with minor gaps.	4 / 5
Workflow Clarity	Clear 8-step sequence with an upfront intent-routing jump table, explicit validation checkpoints (Step 5 checklist with 'fix it before delivering'), and genuine feedback loops (Step 6 before/after scoring), matching the top anchor for sequenced validation with error-recovery loops.	5 / 5
Progressive Disclosure	Body is an overview pointing to six verified one-level-deep reference files, signaled with inline backtick paths and a dedicated '## Reference Files' section describing each; content is appropriately split and easy to navigate.	5 / 5
	Total	18 / 20 Passed

Description

100%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 is exemplary: it covers the full skill lifecycle with concrete actions, an explicit 'Use when' clause, an exhaustive list of natural trigger phrases including sideways entry points, and a distinctive niche that minimizes conflict risk.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions across the full lifecycle — 'Create new skills, modify and improve existing skills, and measure skill performance' plus 'run evals', 'benchmark skill performance with variance analysis', and 'iterate on skill quality' — giving comprehensive coverage with no real gaps.	5 / 5
Completeness	Explicitly answers both 'what' (create/modify/improve/measure skills) and 'when' with a clear 'Use when users want to...' clause and concrete trigger phrases, matching the top anchor exactly.	5 / 5
Trigger Term Quality	Exhaustive natural trigger phrases including synonyms and paraphrases ('create a skill', 'make a new skill', 'build a skill for', 'scaffold a skill', 'score this skill', 'benchmark this skill', 'turn this into a skill') plus sideways workflow-automation entries ('I keep doing X manually', 'can you remember how to do X').	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche — skill authoring and evaluation tooling — with highly specific triggers ('run evals on', 'benchmark skill performance with variance analysis', 'score this skill') that are unlikely to fire for unrelated skills.	5 / 5
	Total	20 / 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: himself65/finance-skills
Path: plugins/skill-creator/skills/skill-creator/SKILL.md
Commit: 81e1f50

Reviewed: 7 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.