CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

onboard

Use when joining an unfamiliar codebase, starting on a new team, or needing to understand a project's architecture, conventions, and key modules quickly.

Quality

79%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/onboard/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

81%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 well-structured, actionable workflow for an instruction-only skill: concrete file targets, detection methods, an explicit verification checklist, and a complete output template. Its only real weaknesses are minor — slight redundancy across the Rules and Anti-Rationalization sections and a canned TypeScript-flavored example diagram.

DimensionReasoningScore

Conciseness

The body is efficient — terse tables, ASCII templates, and no explanations of concepts Claude already knows (it never explains what package.json or Redux is). Minor trimmable redundancy remains: the canned TypeScript-specific architecture example and Rules 1/4 repeating the Anti-Rationalization table, so it fits anchor 4 rather than 5.

4 / 5

Actionability

Concrete, executable guidance throughout: exact files to read ('package.json / pyproject.toml / go.mod / Cargo.toml'), a per-convention detection table, a module-analysis template, and a full output template. It stops short of anchor 5 because no literal commands are given and Step 5 ('Compile everything into an actionable guide') is a thin one-liner.

4 / 5

Workflow Clarity

Five explicitly sequenced steps plus a numbered Verification Protocol ('Before claiming onboarding is complete') that acts as an explicit validation checklist, with the Anti-Rationalization table preempting shortcut failure modes. This matches anchor 5's clear sequence with explicit validation steps and a checklist; the read-only nature of the task means no destructive-operation cap applies.

5 / 5

Progressive Disclosure

A single well-sectioned file with clear headers where no content clearly belongs in a separate file — everything is overview-level and no bundle files exist. The ~160-line body and the inlined example architecture diagram leave minor organization gaps, fitting anchor 4 ('good structure; most content appropriately placed') rather than 5.

4 / 5

Total

17

/

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.

A solid description with an explicit and well-phrased 'Use when...' trigger clause covering natural user language. Its main weakness is that the 'what' is implicit — it never states the concrete output (generating a developer guide with getting-started instructions) that the body delivers.

Suggestions

State the concrete action up front, e.g., 'Generates a developer guide covering architecture, conventions, key modules, and getting-started commands' before the 'Use when' clause.

Add natural trigger synonyms such as 'onboarding', 'ramping up on a project', or 'new codebase' to broaden keyword coverage.

DimensionReasoningScore

Specificity

Names the domain ('unfamiliar codebase', 'new team') and capability targets ('architecture, conventions, and key modules'), but lists no concrete actions or outputs — the developer-guide generation described in the body is absent. Matches anchor 3 (domain plus 1-2 concrete items, not comprehensive) rather than 4, which expects several specific actions.

3 / 5

Completeness

The 'when' is explicit with three concrete triggers ('Use when joining... starting on... or needing to understand...'), but the 'what' is only implicit — 'needing to understand' states a goal rather than what the skill does (e.g., generates a developer guide). Both are present with one weaker, matching anchor 4 rather than 5's fully explicit what-and-when.

4 / 5

Trigger Term Quality

'joining an unfamiliar codebase', 'starting on a new team', and 'understand a project's architecture' are phrases users would naturally say, giving good keyword coverage. It falls short of anchor 5 because common synonyms like 'onboarding', 'ramp up', or 'get up to speed' are missing.

4 / 5

Distinctiveness Conflict Risk

'Joining an unfamiliar codebase' and 'starting on a new team' carve a distinct onboarding niche with minimal conflict risk. Minor overlap remains with general code-exploration skills (the body itself defers quick checks to '@scout'), fitting anchor 4 rather than 5's fully distinct triggers.

4 / 5

Total

15

/

20

Passed

Validation

87%

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

CriteriaDescriptionResult

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

skills/onboard/SKILL.md

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.