multica-creating-agents

Use when creating, inspecting, or debugging a Multica agent definition via the `multica agent` CLI or POST /api/agents. Not for assigning issues to agents that already exist, and not for runtime task prompts.

Quality

78%

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-creating-agents/SKILL.md

Quality

Content

68%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 thorough, source-traced contract reference with highly actionable commands and clean structure. Its main weaknesses are redundancy in the thinking_level/service_tier treatment and the absence of explicit validation feedback loops for destructive operations.

Suggestions

Consolidate the thinking_level and service_tier material so it lives in either the field-contract table or the prose section, not both, to cut repetition.

Add an explicit validate-before-proceed checkpoint for destructive operations (e.g. run `agent get`/`agent skills list` after `skills set` or `env set` to confirm the resulting bindings/env).

Move the dense provider-level edge-case detail (hermes/reasonix/copilot catalog behavior) into the source-map reference, keeping the body to the contract-level facts.

Dimension	Reasoning	Score
Conciseness	The body is fact-dense and avoids explaining basics Claude already knows, but the thinking_level and service_tier material is stated twice (once in the field-contract table and again in long prose) and could be tightened.	3 / 5
Actionability	Provides copy-paste-ready CLI commands with real flags for create, get, copy, env, mcp, and skills, plus concrete HTTP bodies and error codes covering the common cases.	5 / 5
Workflow Clarity	Operations are well-categorized ("Side effects needing approval" separates read-only from state-changing, and destructive `skills set`/`env set` are flagged), but there is no explicit validate-then-proceed feedback loop for the destructive/batch operations, which caps this at 3.	3 / 5
Progressive Disclosure	Structure is clear with well-organized sections and a real, one-level-deep reference (`references/creating-agents-source-map.md`) that is explicitly signaled as backing every claim; the only gap is the length of inlined contract prose that could partly live in the reference.	4 / 5
	Total	15 / 20 Passed

Description

87%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 gives concrete actions, exact entry points, and explicit negative boundaries. It clearly answers both what and when and is highly distinguishable from neighboring skills.

Dimension	Reasoning	Score
Specificity	Names three concrete actions ("creating, inspecting, or debugging a Multica agent definition") and the exact entry points ("multica agent CLI" and "POST /api/agents"), but coverage of the broader agent lifecycle (copy, skill binding, env) is implied rather than enumerated.	4 / 5
Completeness	Explicitly answers both what (create/inspect/debug agent definitions) and when ("Use when...") with concrete trigger phrases, and adds negative boundary guidance ("Not for assigning issues... not for runtime task prompts").	5 / 5
Trigger Term Quality	Includes natural trigger phrasing ("Use when creating, inspecting, or debugging") plus the concrete CLI/HTTP surface users would name, though a few common variations (e.g. "copy an agent", "bind skills") are absent.	4 / 5
Distinctiveness Conflict Risk	Targets a clear niche (Multica agent definitions via specific CLI/HTTP paths) and the explicit out-of-scope clauses minimize overlap with runtime-prompt or issue-assignment skills.	5 / 5
	Total	18 / 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-creating-agents/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.