multica-mentioning

Use when an issue comment needs to @mention someone — link to a person, trigger another agent, hand work to a squad, or broadcast with @all. Whether to mention at all is covered by the runtime brief, not here.

Quality

86%

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

78%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 high-quality, source-pinned skill body with executable commands, a clear lookup→emit workflow, and well-structured one-level-deep references. The main weakness is verbosity in the edge-case and automation-lineage passages, which explain runtime mechanics beyond what is needed to act.

Suggestions

Tighten the "What does NOT happen" section and the MUL-4857/MUL-6490 automation-lineage paragraph: summarize the contract in 2-3 lines and push the full mechanism detail into references/mentioning-source-map.md.

Consider a compact "Quick reference" table at the top condensing the four types, id source, and what enqueues — so the dense narrative below becomes optional depth.

Move the @all-suppression precedence detail (MUL-5411) into the source map, keeping only the one-line rule "explicit mentions win over @all" in SKILL.md.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and dense with source-pinned facts, but the "What does NOT happen" and automation-lineage sections are long and explain runtime mechanics (MUL-4857, MUL-6490) at length that could be trimmed without losing the actionable contract.	3 / 5
Actionability	Provides fully executable, copy-paste-ready guidance: exact `multica ... --output json` commands, the precise `[@Label](mention://<type>/<id>)` shapes, id sources per type, and an Incorrect→Correct walk-through pinned by a behavior test.	5 / 5
Workflow Clarity	Clear two-step sequence (look up UUID → emit the typed link) with explicit validation ("If the name is ambiguous or absent, do not guess — say so") and a result-reading checkpoint (`trigger_outcomes`); minor validation gaps in the deeper edge-case sections keep it just below 5.	4 / 5
Progressive Disclosure	SKILL.md is an overview that repeatedly and clearly signals a single one-level-deep reference (`references/mentioning-source-map.md`), which is a real file; the bulk of file:line evidence is correctly split into that reference rather than inlined.	5 / 5
	Total	17 / 20 Passed

Description

95%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 clearly states what the skill does and when to use it with natural trigger terms. It is third-person, concise, and avoids over-claiming.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ("link to a person, trigger another agent, hand work to a squad, or broadcast with @all") tied to specific backend types, with only minor gaps in coverage rather than a comprehensive enumeration of every interaction.	4 / 5
Completeness	Explicitly answers both what (link/trigger/hand/broadcast via @mention) and when ("Use when an issue comment needs to @mention someone") with concrete trigger phrases; it even scopes a boundary ("not here") cleanly.	5 / 5
Trigger Term Quality	Uses natural trigger phrasing users would actually say ("@mention someone", "link to a person", "trigger another agent", "broadcast with @all") with the literal @mention / @all tokens users invoke.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (Multica issue-comment @mention mechanics) with distinct, specific triggers unlikely to collide with other skills.	5 / 5
	Total	19 / 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: 9 suspicious	Warning

	Total	14 / 16 Passed

Repository: multica-ai/multica
Path: server/internal/service/builtin_skills/multica-mentioning/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.