skill-creator

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/skill-creator/SKILL.md

Quality

Content

63%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 thorough, well-sequenced skill-authoring workflow with concrete schemas and commands, weakened by conversational verbosity and several references to bundle files (agents/*, eval-viewer/) that are not present in the skill directory.

Suggestions

Remove conversational filler ('Cool? Cool.', the plumbers/grandparents digression, 'billions a year in economic value') and delete the redundant 'Repeating one more time' section to get comfortably under the 500-line budget.

Fix dangling references: either add the referenced agents/grader.md, agents/comparator.md, agents/analyzer.md and eval-viewer/generate_review.py to the bundle, or update the body to point at paths that actually exist.

Tighten 'Communicating with the user' and the intro overview into a short bulleted summary; the substantive guidance is already covered later in 'Creating a skill' and 'Writing Style'.

Dimension	Reasoning	Score
Conciseness	At 486 lines it is near its own 500-line limit and carries noticeable conversational padding ('Cool? Cool.', the plumbers/grandparents digression, 'billions a year in economic value', and a redundant restated core loop) — more than minor over-explanation that could be trimmed.	3 / 5
Actionability	Provides executable commands (python -m scripts.aggregate_benchmark, nohup ... generate_review.py), exact JSON field names (text/passed/evidence), and filled placeholders; minor gaps keep it just short of fully copy-paste-ready across all cases.	4 / 5
Workflow Clarity	The create-test-evaluate-improve loop is clearly sequenced with checkpoints and feedback loops, but references to a non-existent agents/ directory and eval-viewer/generate_review.py in the bundle introduce minor reliability gaps.	4 / 5
Progressive Disclosure	Real bundle files (references/schemas.md, assets/eval_review.html, scripts/*.py) are well signaled one level deep, but the body also references agents/grader.md, agents/comparator.md, agents/analyzer.md and eval-viewer/generate_review.py that do not exist in the bundle — broken references hold it below good.	3 / 5
	Total	14 / 20 Passed

Description

88%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, specific description with a clear 'Use when' trigger clause and concrete actions spanning the full skill lifecycle. It is slightly below the top trigger-term anchor only because a few natural synonyms are absent.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Create new skills', 'modify and improve existing skills', 'measure skill performance', 'run evals', 'benchmark skill performance with variance analysis', "optimize a skill's description" — with comprehensive coverage.	5 / 5
Completeness	Explicitly answers both what (create/modify/measure skills) and when via the 'Use when users want to...' clause with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural phrases users say ('create a skill from scratch', 'edit, or optimize an existing skill', 'run evals', 'benchmark skill performance') with good coverage, though a few synonyms/variants are missing versus the comprehensive anchor at 5.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (skill creation and optimization) with specific triggers; mostly distinct with only minor overlap risk against general coding skills.	4 / 5
	Total	18 / 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: OpenBMB/PilotDeck
Path: skills/skill-creator/SKILL.md
Commit: 9a33f4d

Reviewed: 2 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.