multica-runtimes-and-repos

Use when a Multica runtime or daemon misbehaves: agent not running, task not claimed, runtime offline, workdir or session reuse, repository checkout.

Quality

75%

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-runtimes-and-repos/SKILL.md

Quality

Content

76%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 highly actionable, well-structured troubleshooting skill with executable commands and a clear diagnostic sequence. Its weak point is workflow clarity: destructive operations lack explicit validation/verification checkpoints and the diagnostic flow has no feedback loop.

Suggestions

Add explicit validation/verification checkpoints around destructive commands — e.g. before `runtime delete --cascade`, verify bound agents via `multica runtime usage`, and after any fix, verify the task was claimed with `multica runtime activity`.

Close the debugging workflow with a feedback loop: after applying a fix, re-run `multica runtime list --output json` / check task status to confirm the agent claimed and ran, then iterate if still pending.

Split the long runtime update/delete/cascade paragraph into a short table or bulleted list so the permission, cascade, and unbinding rules are scannable instead of buried in prose.

Dimension	Reasoning	Score
Conciseness	The body is dense and almost entirely Multica-proprietary detail that Claude would not already know, with no padding about general concepts; a few long prose paragraphs (e.g. the runtime update/delete/cascade paragraph) could be split for scannability.	4 / 5
Actionability	It provides copy-paste-ready CLI commands with flags and JSON output ("multica agent get <agent-id> --output json", "multica runtime list --output json", the full runtime/repo command block) plus a concrete numbered diagnostic checklist covering the common cases.	5 / 5
Workflow Clarity	The "Debugging an agent that did not run" section is a clear ordered 1-7 sequence, but there is no validate-then-verify feedback loop, and the skill covers destructive operations (runtime delete --cascade, daemon stop) without explicit pre/post validation checkpoints, invoking the destructive-ops cap.	3 / 5
Progressive Disclosure	Sections are well organized (Quick start, Core model, CLI, Task CLI boundary, Debugging, Repos) and there is a single clearly signaled one-level-deep reference to the real file references/runtimes-and-repos-source-map.md; most detail lives inline in SKILL.md rather than being split out.	4 / 5
	Total	16 / 20 Passed

Description

73%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 strong, niche-scoped description with an explicit trigger clause and natural symptom keywords. Its main weakness is that the skill's actual actions are implied rather than named, which keeps specificity and completeness just below the top anchors.

Dimension	Reasoning	Score
Specificity	The description lists concrete trigger symptoms ("agent not running, task not claimed, runtime offline, workdir or session reuse, repository checkout") but never names the concrete actions the skill performs, leaving its capability implicit.	3 / 5
Completeness	It has an explicit "Use when..." clause with concrete triggers, and the "what" is present but only weakly implied ("a Multica runtime or daemon misbehaves") rather than stated as an explicit action verb.	4 / 5
Trigger Term Quality	Phrases like "agent not running", "task not claimed", "runtime offline", and "repository checkout" are natural language an operator would say, giving good keyword coverage with a few synonyms missing.	4 / 5
Distinctiveness Conflict Risk	"Multica runtime or daemon" carves out a clear, narrow niche with distinct triggers that are unlikely to fire for unrelated skills.	5 / 5
	Total	16 / 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-runtimes-and-repos/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.