onboard

Generates a contextual onboarding document for a new contributor or agent joining the project. Summarizes project state, architecture, conventions, and current priorities relevant to the specified role or area.

Quality

77%

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 ./.claude/skills/onboard/SKILL.md

Quality

Content

87%

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

The body is lean, actionable, and well-organized into a clear five-phase workflow with a concrete output template, but it lacks validation/verification steps and error-recovery guidance for missing inputs.

Suggestions

Add a verification checkpoint in Phase 3 or 4, e.g. confirm every template section is populated and role-relevant before presenting the document to the user.

Provide fallback handling for missing inputs — what to do when CLAUDE.md is absent or the repo is not a git project — instead of only 'git log if available'.

Tighten overlapping template sections (e.g. 'Current State of Your Area', 'Current Sprint Context', and 'First Tasks') to reduce redundancy in the output skeleton.

Dimension	Reasoning	Score
Conciseness	The directive phases are lean ("Read CLAUDE.md", "scan `src/`", "git log if available") with no padding or explanation of concepts Claude already knows; the Phase 3 template is a structural output spec rather than fluff, so every token earns its place.	3 / 3
Actionability	Guidance is concrete and instruction-ready: specific paths to read (`.claude/agents/`, `src/`, `design/narrative/`), a complete fill-in template, the literal approval question, an exact output path (`production/onboarding/onboard-[role]-[date].md`), and runnable commands (`/sprint-status`, `/help`).	3 / 3
Workflow Clarity	The five phases are clearly sequenced and the write has an explicit approval gate, but there are validation gaps: no verification that the generated document is complete/accurate, and no error-recovery guidance for missing inputs (absent CLAUDE.md, non-git repo), fitting 'sequence present but checkpoints missing or implicit' below the level-3 anchor that requires validation and feedback loops.	2 / 3
Progressive Disclosure	The skill is a self-contained, single-purpose workflow with no need for external references, organized into clearly headed phases and a fenced template; per the simple-skill guidance this earns a 3 with well-organized sections and no nested references.	3 / 3
	Total	11 / 12 Passed

Description

67%

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 specific and occupies a distinct niche, but it lacks an explicit 'Use when...' trigger clause and only implies when to invoke it, capping completeness and trigger-term coverage at 2.

Suggestions

Add an explicit trigger clause, e.g. 'Use when onboarding a new contributor or agent, or when the user asks to create a welcome/ramp-up document for someone joining the project.'

Include natural trigger variations users might say, such as 'onboard', 'ramp up', 'welcome a new team member', or 'create an onboarding doc'.

Reconsider whether the generic 'Summarizes project state, architecture, conventions, and current priorities' phrasing risks overlap with general project-summary skills; lead with the onboarding framing to reinforce distinctiveness.

Dimension	Reasoning	Score
Specificity	"Generates a contextual onboarding document" and "Summarizes project state, architecture, conventions, and current priorities" name multiple concrete actions (generates, summarizes) tied to specific targets, matching the anchor for listing several specific concrete actions.	3 / 3
Completeness	The 'what' is clearly stated, but there is no explicit 'Use when...' trigger clause; the 'when' is only implied by 'for a new contributor or agent joining the project', which per the guidelines caps completeness at 2.	2 / 3
Trigger Term Quality	It contains relevant natural terms ("onboarding document", "new contributor", "role or area") but offers only a single phrasing with no common variations or explicit trigger enumeration, fitting 'some relevant keywords but missing common variations' rather than the broad coverage of level 3.	2 / 3
Distinctiveness Conflict Risk	The onboarding-for-new-contributors niche is specific and distinct ("new contributor or agent joining the project" scoped to a "role or area"), making it unlikely to trigger for unrelated skills, matching the clear-niche anchor.	3 / 3
	Total	10 / 12 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: Donchitos/Claude-Code-Game-Studios
Path: .claude/skills/onboard/SKILL.md
Commit: 984023d

Reviewed: 3 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.