Tessl • The management layer for AI agent skills

The body is an excellent example of a lean, instruction-only skill: concrete discovery commands, an exact output template covering endpoints, routes, components, state, and data flow, plus a sharp attention-points checklist. The only minor gap is that some summary steps are given as hints ("grep in services") rather than concrete commands, and there is no handling for modules missing from the assumed directory layout. It is well-structured, self-contained, and appropriately sized.

Dimension	Reasoning	Score
Conciseness	The ~47-line body is lean and assumes Claude's competence: concrete find commands, a compact summary template, a terse data-flow diagram, and a checklist, with no padding or explanations of concepts Claude already knows. Even the parentheticals ("(client state)", "(server state via hooks)") carry information, matching anchor 5's "every token earns its place".	5 / 5
Actionability	Concrete executable find commands, an exact output template, and a specific checklist provide mostly executable guidance. Minor gaps remain: steps like "List the consumed endpoints (grep in services)" and "List the app/ routes and their types" are high-level hints without concrete commands, and there is no guidance for when a module exists in only one of the two searched paths, so it falls just short of anchor 5.	4 / 5
Workflow Clarity	The three-step sequence (map structure -> summarize in the given format -> output a 2-minute-readable summary) is clear, coherent, and unambiguous, with a well-defined end goal. This is a read-only single-purpose skill under 50 lines, so no validation checkpoints are required and the simple-skill exception applies.	5 / 5
Progressive Disclosure	The skill is a self-contained, well-organized single file with clear section headers and no bundle files (references/, scripts/, assets/ are absent, and none are needed at this size). The single external mention (ARCHITECTURE.md) is a clearly signaled repo-level pattern check, fitting the guideline that short skills with no external-reference needs score 5 with well-organized sections.	5 / 5
	Total	19 / 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 is concise and has an explicit, natural "Use when" trigger with a reasonable statement of deliverables (structure, patterns, key files). Its main weakness is specificity: it describes one generic summary action rather than the concrete analyses the skill actually performs, and it omits common trigger variations like "overview" or "understand". Overall a solid, appropriately scoped description with room to enumerate its capabilities more concretely.

Suggestions

State the concrete actions the skill performs, e.g., "Maps module file structure, lists endpoints, routes, and components, and summarizes state management (Zustand, React Query, Server Actions) and data flow" instead of the generic "quick summary".

Lead with a standalone capability statement before the trigger clause, e.g., "Creates a 2-minute onboarding summary of a module's structure, patterns, and key files. Use when onboarding onto a module...", so the "what" is explicit rather than embedded in the "when".

Add natural trigger variations such as "overview", "understand", or "familiarize" (e.g., "Use when onboarding onto a module, or when you need a quick overview or refresher of how a module is organized").

Dimension	Reasoning	Score
Specificity	"quick summary of its structure, patterns, and key files" names the domain and deliverable areas, but describes a single generic action (summarize) rather than several distinct concrete actions like mapping files, listing endpoints, or identifying state management. It is above anchor 2 (which has minimal/generic actions) but does not reach anchor 4's several specific actions.	3 / 5
Completeness	The "when" is explicit ("Use when onboarding onto a module") and the "what" is present ("quick summary of its structure, patterns, and key files"), but the what is folded into the when-clause rather than stated as a standalone capability. This matches anchor 4 (both present, one could be more explicit); it is not 5 because there is no distinct capability statement with concrete trigger phrases.	4 / 5
Trigger Term Quality	"onboarding onto a module" and "quick summary" are natural phrases users would actually say when needing this skill. A few common variations are missing (e.g., "overview", "understand", "familiarize"), which fits anchor 4 rather than anchor 5's comprehensive synonym coverage; it is above anchor 3 because the core triggers are natural and domain-specific rather than generic.	4 / 5
Distinctiveness Conflict Risk	"onboarding onto a module" defines a fairly clear niche with low conflict risk. There is minor overlap with generic code-explanation or summarization skills, matching anchor 4 (mostly distinct, minor overlap risk) rather than anchor 5's minimal-conflict clear niche.	4 / 5
	Total	15 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: fernandezbaptiste/specialist-agent
Path: packs/nextjs/skills/docs-onboard/SKILL.md
Revision: cd716d9

Reviewed: 8 days 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.

docs-onboard

Table of Contents

Is this your skill?