create-skill

Authoritative guide on how to architect, format, and structure new Anthropic Progressive Disclosure skills. Triggers: Use before creating OR modifying any `.agents/skills/**/*.md` files — Progressive Disclosure architecture (Map vs World Atlas), YAML frontmatter, skill structure. Complementary to `turn-memory-pre-flight` (load-runtime-effect dimension vs skill-shape dimension).

Quality

72%

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

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/create-skill/SKILL.md

Quality

Content

70%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured router that exemplifies progressive disclosure: a lightweight overview pointing to a real one-level-deep reference. The weakest dimensions are conciseness and actionability, where jargon and fully-delegated guidance leave room to tighten.

Suggestions

Trim jargon ("graph-queryable canonical decision substrate", "procedural HOW-TO companion") to plain phrasing so every token earns its place.

Add one concrete inline cue (e.g. the required frontmatter fields or the scaffold folder shape) so the router is actionable before the reference is opened.

Dimension	Reasoning	Score
Conciseness	The body is short and mostly a lean pointer, but phrases like "graph-queryable canonical decision substrate" and "procedural HOW-TO companion" are jargon padding that could be tightened, so it is not fully level-3 lean.	2 / 3
Actionability	It gives a concrete instruction ("use the `view_file` tool to read" a specific path) but delegates all actual authoring guidance to the referenced file, leaving the inline actionability incomplete.	2 / 3
Workflow Clarity	This is a single-purpose router whose one action is unambiguous — read the named guide before creating any files — which meets the simple-skills allowance for a level-3 workflow clarity score.	3 / 3
Progressive Disclosure	The body is a clear overview with a well-signaled, one-level-deep pointer to the existing `references/skill-authoring-guide.md`, keeping heavy payload out of the router as the architecture intends.	3 / 3
	Total	10 / 12 Passed

Description

75%Weight 40%Scale 1-3

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 description with an explicit trigger clause and clear niche differentiation. Its main weakness is trigger-term quality, where several keywords are internal jargon rather than phrases a user would naturally say.

Suggestions

Replace internal jargon ("Map vs World Atlas", "skill-shape dimension", "load-runtime-effect dimension") with natural user-facing terms like "create a skill", "edit a skill", or "skill YAML frontmatter".

Add 1-2 more concrete authoring actions (e.g. "scaffold a skill folder", "write YAML frontmatter", "split content into references") to lift specificity toward the level-3 anchor.

Dimension	Reasoning	Score
Specificity	Names the domain ("Progressive Disclosure skills") and several actions ("architect, format, and structure"), but the verbs are abstract rather than a list of concrete operations, so it stops short of the level-3 anchor.	2 / 3
Completeness	It states what the skill does ("architect, format, and structure new ... skills") and gives an explicit when via "Triggers: Use before creating OR modifying any `.agents/skills/*/.md` files", satisfying both halves.	3 / 3
Trigger Term Quality	"creating OR modifying any `.agents/skills/*/.md` files" is a natural trigger phrase, but terms like "Map vs World Atlas" and "skill-shape dimension" are internal jargon rather than common user variations.	2 / 3
Distinctiveness Conflict Risk	It carves a clear niche (skill authoring) scoped to a specific file glob and explicitly differentiates itself from the complementary `turn-memory-pre-flight` skill, making misfires unlikely.	3 / 3
	Total	10 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 1 suspicious	Warning

	Total	15 / 16 Passed

Repository: neomjs/neo
Path: .agents/skills/create-skill/SKILL.md
Commit: c1ce853

Reviewed: 8 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.