multica-projects-and-resources

Use when creating, inspecting, updating, or debugging Multica projects and their resources (github_repo, local_directory).

Quality

76%

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 ./server/internal/service/builtin_skills/multica-projects-and-resources/SKILL.md

Quality

Content

86%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.

The body is a dense, executable CLI reference with a clear model section, an explicit debugging workflow with verification, and a side-effects confirmation gate, all linked to a real one-level source map. It is slightly heavy on prose explanations in places but earns its tokens overall.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean, executable CLI reference with terse explanations of model semantics, though a few explanatory passages (e.g. the worktree capability gating paragraph and the comment-rendering prose) could be trimmed slightly.	4 / 5
Actionability	It provides fully executable, copy-paste-ready commands covering list/get/create/update/status and resource add/update/remove with concrete flag combinations, plus specific examples for the common cases.	5 / 5
Workflow Clarity	The 'Debugging wrong context' section is an explicitly numbered sequence with a verification checkpoint (step 4: 'After an update, listing the resource is the verification path'), and destructive side effects are flagged with a confirmation gate in 'Side effects'.	5 / 5
Progressive Disclosure	Structure is good with clear sections and a well-signaled one-level-deep reference to references/projects-and-resources-source-map.md (a real file), though most detail is inlined in SKILL.md rather than split into multiple focused files.	4 / 5
	Total	18 / 20 Passed

Description

66%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 specific, distinct, and explicitly answers both what it does and when to use it, using appropriate third-person voice with a clear 'Use when' trigger. Its main weakness is moderate trigger-term coverage that relies on domain nouns rather than a richer spread of synonyms.

Suggestions

Broaden trigger-term coverage with natural phrasings and synonyms a user might say, e.g. 'Use when adding a repo to a project, binding a local directory, or fixing wrong task context'.

Consider naming the concrete artifacts users interact with (e.g. project resources, .multica/project/resources.json) to make the 'what' even more tangible.

Dimension	Reasoning	Score
Specificity	Names the concrete action verbs (creating, inspecting, updating, debugging) and the specific resource types (github_repo, local_directory), giving several specific actions with only minor gaps in coverage.	4 / 5
Completeness	It has both a clear 'what' (manage projects and github_repo/local_directory resources) and an explicit 'when' ('Use when creating, inspecting, updating, or debugging'), though the 'when' could list more concrete trigger phrases.	4 / 5
Trigger Term Quality	It uses a 'Use when...' clause with the natural trigger nouns 'projects and their resources', but it lacks common synonyms or file extensions a user might say; the keyword coverage is relevant but somewhat narrow.	3 / 5
Distinctiveness Conflict Risk	The Multica-specific noun and enumerated resource types give it a clear niche with minimal overlap risk against other skills; the triggers are tightly scoped to Multica projects.	5 / 5
	Total	16 / 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
relative_links	Relative link issues: 1 suspicious	Warning

	Total	14 / 16 Passed

Repository: multica-ai/multica
Path: server/internal/service/builtin_skills/multica-projects-and-resources/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.