multica-working-on-issues

Use when acting on a Multica issue beyond what the brief covers: PR linking vs close intent, reading a linked PR's real state, metadata keys, status-change side effects, sub-issue todo vs backlog.

Quality

89%

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

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.

A well-structured, highly actionable contracts skill that leans on concrete CLI commands and conditional validation guidance, with appropriate offloading of source citations to a single reference file. The main improvement vector is reducing repetition of the reference-only and PR-linking examples across sections.

Suggestions

State the reference-only rule once in its dedicated subsection and cross-reference it (e.g. 'see Reference-only links above') instead of re-explaining it in the PR-state and Incorrect→correct sections.

Consolidate the PR-title linking examples so they appear in one place rather than repeated across 'PR linking', 'Default for code-changing issue work', and 'Incorrect → correct'.

Consider a short table of contents or anchor links at the top so agents can jump to the relevant contract section quickly.

Dimension	Reasoning	Score
Conciseness	Dense, contract-focused prose that assumes Claude's competence and avoids explaining basics, but the reference-only rule and linking examples recur across several sections and could be trimmed slightly.	4 / 5
Actionability	Provides copy-paste-ready CLI commands with exact flags and JSON output shapes throughout — e.g. 'multica issue pull-requests <issue-id> --output json', 'multica issue create ... --stage 1 --status todo' — covering the common cases.	5 / 5
Workflow Clarity	Consequential operations carry explicit validation checkpoints (check comment history before self-assigning, read sub-issue descriptions before promoting, report blockers instead of pretending completion), though the contracts are distributed rather than one linear sequence.	4 / 5
Progressive Disclosure	Clear section structure with a single well-signaled, one-level-deep reference ('references/working-on-issues-source-map.md', confirmed present) for source mapping, while operational contracts stay inline; easy to navigate.	5 / 5
	Total	18 / 20 Passed

Description

92%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 tightly scoped, third-person description that explicitly pairs a trigger clause with a concrete enumeration of the contracts the skill governs. It is comprehensive and distinct, with only minor room for additional synonyms in its trigger terms.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete contracts — 'PR linking vs close intent, reading a linked PR's real state, metadata keys, status-change side effects, sub-issue todo vs backlog' — giving comprehensive coverage of the skill's scope rather than vague abstractions.	5 / 5
Completeness	Explicitly answers both: 'when' via 'Use when acting on a Multica issue beyond what the brief covers' and 'what' via the enumerated contract list, with concrete trigger phrasing.	5 / 5
Trigger Term Quality	Strong domain keyword coverage (Multica issue, PR linking, close intent, linked PR state, metadata, sub-issue) but lacks synonyms or variations; good but not exhaustive, fitting the 'a few natural terms missing' anchor.	4 / 5
Distinctiveness Conflict Risk	Scoped narrowly to Multica issue contracts 'beyond what the brief covers' and even redirects mention-linking to a sibling skill, establishing a clear niche with minimal conflict risk.	5 / 5
	Total	19 / 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-working-on-issues/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.