multica-onboarding

Use when a product-authored kickoff starts or resumes Mika's interactive onboarding for a Multica workspace. The opening greeting has already been sent; carry the member from their first message to one real, confirmed, issue-based execution and a clear handoff.

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

75%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 onboarding playbook that respects token budget and gives concrete starter plays plus an explicit confirm gate. The main gap is that issue/project creation is described procedurally rather than with copy-paste multica commands, and there is no error-recovery loop after the creation step.

Suggestions

Add the exact `multica` commands for project, specialist, and issue creation (mirroring the concrete `autopilot trigger-add` example) so the start-work steps are copy-paste ready.

Add a short validation/recovery note for when issue creation or assignment fails (e.g., re-issue vs. surface the error), giving the workflow an explicit feedback loop.

Trim the philosophical framing sentences (e.g., 'the bureaucratic reflex this working model exists to avoid') to tighten conciseness without losing the working-model guidance.

Dimension	Reasoning	Score
Conciseness	Lean and assumes Claude's competence without explaining basics; every section addresses first-conversation specifics. A few philosophical asides ('the bureaucratic reflex this working model exists to avoid') could be trimmed, so just short of a 5.	4 / 5
Actionability	Provides concrete guidance — exact starter card prompts, an executable `multica autopilot trigger-add --timezone <IANA>` command, a decision tree, and numbered issue-creation steps; not a 5 because project/issue/specialist creation is described rather than given as exact commands.	4 / 5
Workflow Clarity	A clear sequenced flow (greet-already-sent → starter plays → shape → preview and confirm → start work → complete) with an explicit confirmation checkpoint and numbered creation steps; not a 5 because there is no explicit error-recovery feedback loop after creation.	4 / 5
Progressive Disclosure	Well-organized into clearly headed sections with no nested references and no bundle files needed for this self-contained behavioral skill; slightly long for a pure overview, so not a 5.	4 / 5
	Total	16 / 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 tight, well-constructed description that clearly states both the trigger condition and the end-to-end outcome, in third-person imperative voice. It is specific and distinctive; the only minor gap is that it describes the journey at a high level rather than naming the concrete starter operations.

Dimension	Reasoning	Score
Specificity	Names the domain (Multica onboarding) and several concrete actions — 'starts or resumes Mika's interactive onboarding', 'carry the member from their first message to one real, confirmed, issue-based execution and a clear handoff'; not a 5 because it stops short of enumerating the constituent operations (board/delegate/digest, issue creation).	4 / 5
Completeness	Explicitly answers both what ('carry the member from their first message to one real, confirmed, issue-based execution and a clear handoff') and when ('Use when a product-authored kickoff starts or resumes Mika's interactive onboarding') with a concrete trigger clause.	5 / 5
Trigger Term Quality	Includes natural trigger terms a product kickoff would use — 'product-authored kickoff', 'starts or resumes', 'interactive onboarding', 'Multica workspace'; good coverage with a few synonymous phrasings missing, so not a 5.	4 / 5
Distinctiveness Conflict Risk	A highly specific niche — Multica workspace onboarding triggered by a product-authored kickoff — with distinct triggers and minimal overlap risk with other skills.	5 / 5
	Total	18 / 20 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
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning

	Total	15 / 16 Passed

Repository: multica-ai/multica
Path: server/internal/service/builtin_skills/multica-onboarding/SKILL.md
Commit: ea94c7c

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.