CtrlK
BlogDocsLog inGet started
Tessl Logo

build-skill

Build or improve Agent Zero skills following the official SKILL.md standard. Use when the user asks to create, rename, move, audit, test, or refactor a skill, or when a workflow should be packaged as reusable skill instructions.

74

Quality

91%

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

90%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 content is a tight, actionable, well-structured overview that respects token budget and gives executable guidance and a validation command. It falls just short of perfect on workflow clarity (no explicit fix/retry loop) and progressive disclosure (no concrete reference files to navigate to).

Suggestions

Add an explicit validate→fix→re-run feedback loop in the Validation section so rename/move/refactor operations have a clear error-recovery path.

Either create a reference file (e.g. references/naming-conventions.md or references/validation-checklist.md) and link to it, or state explicitly that this skill intentionally has no bundle files, so progressive disclosure navigation is complete.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence — it gives the folder shape, naming rules, a numbered workflow, and a validation command without explaining what skills are or padding with background, so every token earns its place.

5 / 5

Actionability

Provides executable, copy-paste-ready artifacts: a concrete folder tree, a frontmatter template, naming examples, a runnable validation command (conda run -n a0 pytest ...), and a checklist of validation steps that cover the common cases.

5 / 5

Workflow Clarity

The Workflow section is a clearly sequenced 7-step process and the Validation section adds a concrete command plus a checkpoint-style live-path checklist, but it lacks an explicit validate→fix→retry feedback loop for the destructive/batch-style rename/move/refactor operations it covers.

4 / 5

Progressive Disclosure

The body is well organized into focused sections (Standard Shape, Workflow, Placement, Writing Rules, Validation) and explicitly instructs moving detail into one-level-deep references/scripts/assets, but it does not point to any actual reference files, so navigation signaling is partial.

4 / 5

Total

18

/

20

Passed

Description

92%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 strong: it states concrete actions, gives an explicit "Use when" trigger clause with natural user phrasings, and occupies a distinct niche with minimal conflict risk.

DimensionReasoningScore

Specificity

Lists multiple concrete actions in a series — "create, rename, move, audit, test, or refactor a skill" and "packaged as reusable skill instructions" — giving comprehensive coverage of the skill's capabilities.

5 / 5

Completeness

Explicitly states both the "what" ("Build or improve Agent Zero skills following the official SKILL.md standard") and the "when" ("Use when the user asks to create, rename, move, audit, test, or refactor a skill") with concrete trigger phrases.

5 / 5

Trigger Term Quality

Comprehensively covers the natural request phrasings users would actually say — "create, rename, move, audit, test, or refactor a skill" plus "packaged as reusable skill instructions" — spanning the full set of authoring verbs for this domain.

5 / 5

Distinctiveness Conflict Risk

Targets a clear niche — Agent Zero SKILL.md authoring — with distinct verb-led triggers unlikely to collide with other skills; minimal conflict risk.

5 / 5

Total

20

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
agent0ai/agent-zero
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.