skill-creator

Create or update GoClaw agent skills with eval-driven iteration. Use for new skills, skill scripts, references, benchmark optimization, description optimization, eval testing, extending agent capabilities.

Quality

72%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

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

Quality

Content

75%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 SKILL.md body is a concise, well-structured overview that points to a rich, real bundle of references and scripts with concrete executable commands and clear multi-step workflows. It lands at a strong-but-not-perfect band because a few sections carry inlinable detail and the workflows omit a couple of explicit validation checkpoints.

Suggestions

Add an explicit validation checkpoint inside the creation workflow (e.g., 'After writing resources: run scripts/quick_validate.py before publishing') to push workflow_clarity toward level 5.

Move the description-optimization example and the benchmark scoring formula into their existing reference files to tighten conciseness and deepen progressive disclosure.

Provide full argument signatures for key commands (e.g., run_loop.py train/test flags, aggregate_benchmark.py inputs) to make guidance fully copy-paste ready.

Dimension	Reasoning	Score
Conciseness	The body is lean throughout — tables for quick reference and scripts, terse imperative bullets, and a compact structure tree — and it avoids explaining concepts Claude already knows; only minor sections (the description-optimization example and the publishing tool bullet list) could be trimmed further, matching the 'efficient; minor instances of over-explanation' anchor.	4 / 5
Actionability	It gives concrete, real executable commands such as 'scripts/init_skill.py <name> --path <dir>', 'publish_skill(path: ...)', and 'scripts/aggregate_benchmark.py' (all verified to exist as bundle files), plus a numbered eval procedure; a few commands omit full argument signatures, leaving it just below the copy-paste-ready level-5 anchor.	4 / 5
Workflow Clarity	A clear 10-step creation workflow and 7-step eval workflow are explicitly sequenced, with a feedback loop (collect human feedback -> iterate) and validation references (quick_validate.py, validation-checklist); the creation workflow lacks explicit per-step validation checkpoints, so it sits at 'clear sequence with most checkpoints present' rather than level 5.	4 / 5
Progressive Disclosure	The body is a well-organized overview that signals one-level-deep references (e.g., 'Details: references/eval-infrastructure-guide.md', 'Full anatomy: references/skill-anatomy-and-requirements.md'), all of which exist as real bundle files, with content appropriately split; some detail (benchmark scoring formula, description-optimization example, publishing behavior) is inlined rather than pushed to references, keeping it just below the level-5 anchor.	4 / 5
	Total	16 / 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 a distinct capability and supplies explicit trigger guidance across several natural contexts, scoring solidly above average. It stops short of the top anchors because its actions are somewhat broad and its 'when' clause enumerates capability categories rather than vivid user-trigger scenarios.

Suggestions

Tighten the 'when' clause into user-scenario triggers (e.g., 'Use when the user wants to build, improve, or benchmark a GoClaw skill') to reach the level-5 completeness anchor.

Add 1-2 more concrete actions beyond 'Create or update' (e.g., 'optimize descriptions, run evals, package for distribution') to strengthen specificity.

Include common synonyms such as 'build a skill' or 'improve trigger accuracy' to broaden natural trigger-term coverage.

Dimension	Reasoning	Score
Specificity	It names the domain ('GoClaw agent skills') and concrete verbs ('Create or update ... with eval-driven iteration'), but the action set is broad and the rest of the description lists capability categories rather than additional concrete actions, matching the anchor that names the domain with 1-2 concrete actions but is not comprehensive.	3 / 5
Completeness	Both 'what' ('Create or update GoClaw agent skills with eval-driven iteration') and 'when' ('Use for new skills, skill scripts, references, benchmark optimization ...') are present with explicit trigger guidance ('Use for'), satisfying the anti-cap rule; the 'when' clause is a capability list rather than concrete user-scenario triggers, which keeps it just below the level-5 anchor.	4 / 5
Trigger Term Quality	Phrases like 'new skills', 'skill scripts', 'benchmark optimization', 'description optimization', and 'eval testing' are natural terms a user would say when needing this skill, giving good keyword coverage; a few natural synonyms (e.g. 'build a skill', 'improve trigger accuracy') are missing, so it sits just below the comprehensive anchor.	4 / 5
Distinctiveness Conflict Risk	The 'GoClaw agent skills' niche is distinct and the triggers are specific to skill authoring, leaving only minor overlap risk with generic 'extending agent capabilities' wording, matching the 'mostly distinct; minor overlap risk' anchor rather than the fully-distinct level-5 anchor.	4 / 5
	Total	15 / 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: nextlevelbuilder/goclaw
Path: skills/skill-creator/SKILL.md
Commit: 169e0ba

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.