multica-skill-importing

Use when asked to import or install a specific skill into this Multica workspace from a URL or slug. Not for choosing which skill the user needs; never treat a local installer such as `npx skills add` as the final install.

Quality

85%

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

88%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 concrete, well-sequenced operational skill with executable commands, explicit validation checkpoints, and a properly signaled one-level reference layer. Its main weakness is mild redundancy in the scope-setting prose and repeated installer warnings.

Suggestions

Consolidate the 'do not finish with npx skills add' guidance into one place rather than restating it in the intro, the invariant section, and the Incorrect→correct section.

Move the legacy 409 compatibility shapes and the older-server string-body recovery into the source-map reference file, keeping SKILL.md focused on the current structured flow.

Trim the opening two paragraphs that restate the description's trigger and scope, since the frontmatter already carries that information.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean, concrete CLI/JSON guidance that earns its tokens, but the scope-setting intro repeats the description and the 'do not finish with npx skills add' warning recurs in multiple sections, leaving minor trimmable padding.	4 / 5
Actionability	Copy-paste-ready `multica skill import`/`agent skills add`/`refresh` commands with `--output json` appear throughout, alongside concrete request/response JSON envelopes and per-strategy conflict examples covering the common cases.	5 / 5
Workflow Clarity	The 'Direct URL flow' is a numbered sequence with an explicit validation checkpoint ('verify the target skill id is present before claiming the skill is available') and conflict feedback loops (list/get to recover, 'do not retry in a loop') for a potentially destructive import/binding operation.	5 / 5
Progressive Disclosure	Clear section headers give easy navigation and the single external reference (`references/skill-importing-source-map.md`) is real, one level deep, and well-signaled; however the body is a fairly dense monolith where some legacy/edge-case material could be offloaded.	4 / 5
	Total	18 / 20 Passed

Description

82%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-scoped description that answers what and when with an explicit trigger clause and clear conflict-avoidance boundaries. It is slightly light on action variety, relying on a single import/install verb qualified by source forms.

Dimension	Reasoning	Score
Specificity	Names the domain (importing a skill into the Multica workspace) and the concrete input forms ('from a URL or slug'), but the action vocabulary is essentially a single import/install operation rather than several distinct actions.	3 / 5
Completeness	An explicit 'Use when asked to import or install a specific skill ... from a URL or slug' clause states both what the skill does and when to trigger it, with concrete trigger phrasing and negative scope.	5 / 5
Trigger Term Quality	Includes natural terms a user would say ('import or install a specific skill', 'URL or slug') plus the contrastive 'npx skills add'; good coverage with a few synonyms, though not exhaustive.	4 / 5
Distinctiveness Conflict Risk	The niche is narrow (import into this Multica workspace from a URL/slug) and explicit exclusion language ('Not for choosing which skill the user needs'; 'never treat ... npx skills add as the final install') minimizes overlap with sibling skills.	5 / 5
	Total	17 / 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-skill-importing/SKILL.md
Commit: 11ab949

Reviewed: 2 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.