Tessl • The management layer for AI agent skills

SkillPublic

write-guide

Generates technical guides that teach real-world use cases through progressive examples. **Auto-activation:** User asks to write, create, or draft a guide or tutorial. Also use when converting feature documentation, API references, or skill knowledge into step-by-step learning content. **Input sources:** Feature skills, API documentation, existing code examples, or user-provided specifications. **Output type:** A markdown guide with YAML frontmatter, introduction, 2-4 progressive steps, and next steps section.

Quality

86%

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

82%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 highly actionable, well-structured instruction skill whose body is lean and free of padding. Its main weaknesses are mild redundancy in restating the guide arc and step counts (with inconsistent values), and references to example files that are not part of the bundle.

Suggestions

Reconcile the step-count guidance: the frontmatter description says "2-4 progressive steps", the Structure section says "2-5 progressive steps", and Section rules say "2-4 steps". Pick one range and state it once.

State the guide arc (working code, new requirement, friction, explanation, resolution, proof) once, in either the Structure section or Rule 1, rather than fully restating it in both, to trim redundant tokens.

Either bundle the example guides (public-static-pages.mdx, forms.mdx) under references/ or clarify in the References section that they live in the target repository's docs tree, so the cited paths are actually navigable.

Dimension	Reasoning	Score
Conciseness	Dense, prescriptive, and free of concept explanations Claude already knows, but the guide arc is restated three times (Structure section, template placeholders, Rule 1's full loop) and step-count guidance is inconsistent across places ("2-4 progressive steps" in Structure vs "2-5 progressive steps" in the frontmatter description vs "2-4 steps" in Section rules), so minor trimming and reconciliation is possible.	4 / 5
Actionability	Fully actionable for an instruction-only skill: a complete copy-paste markdown template with exact frontmatter fields and section headings, concrete Don't/Do tables with real example phrases, and an explicit per-step pattern (context, code, explain, friction, resolution, proof).	5 / 5
Workflow Clarity	The four-step workflow (Research, Plan, Write, Review) is clearly sequenced with verification checkpoints in Plan ("Verify scope (one problem, 2-4 steps)") and Review ("Re-read the rules, verify, then present"), but there is no explicit error-recovery loop describing what to do when Review finds problems, keeping it below the top anchor.	4 / 5
Progressive Disclosure	Sections are well organized and the template is appropriately inline, and the References section signals one-level-deep example files with per-file descriptions, but the cited files ("docs/01-app/02-guides/public-static-pages.mdx", "forms.mdx") are not present in the skill bundle, leaving a navigation gap.	4 / 5
	Total	17 / 20 Passed

Description

87%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 description that clearly and explicitly states both capability and activation triggers in third person, with a well-structured breakdown of input sources and output type. Trigger coverage is good but could add a few more natural synonyms.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions (generates guides through progressive examples, converts feature documentation/API references/skill knowledge into step-by-step content) plus a specific output shape ("A markdown guide with YAML frontmatter, introduction, 2-4 progressive steps, and next steps section"), but the core capability rests on a single verb, leaving minor coverage gaps.	4 / 5
Completeness	Explicitly answers both what ("Generates technical guides that teach real-world use cases through progressive examples" plus a concrete output type) and when ("Auto-activation: User asks to write, create, or draft a guide or tutorial. Also use when converting feature documentation, API references, or skill knowledge...") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Natural user phrasing is present with verb variants ("User asks to write, create, or draft a guide or tutorial") plus synonyms like "tutorial" and "step-by-step learning content", but common variants such as "how-to" or "walkthrough" are missing.	4 / 5
Distinctiveness Conflict Risk	Guide/tutorial authoring is a clear niche with distinct triggers; "converting feature documentation, API references, or skill knowledge into step-by-step learning content" is unlikely to fire for unrelated skills, leaving only minimal conflict risk.	5 / 5
	Total	18 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: vercel/next.js
Path: .agents/skills/write-guide/SKILL.md
Revision: ec8ddcd

Reviewed: 1 month ago

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.

write-guide

Table of Contents

Is this your skill?