agent-management

AI DevKit · Manage running AI agents with ai-devkit agent commands. Use when an agent needs to identify itself, list agents, start workers, inspect agent detail, assign work, group agents, resume sessions, stop agents, or delegate work to other agents.

Quality

94%

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 tight, command-first skill body: fully executable CLI guidance, sensible assignment rules, and a clear workflow with verification. Its only weaknesses are small actionability gaps (group creation, agent types, $agent-communication) and the absence of an explicit error-recovery loop after verification.

Suggestions

Show how a group is created or clarified before relying on `agent send --group <group>`, since no command in the skill establishes group membership.

Enumerate the valid `--type` values for `agent start` (only `codex` appears) and briefly say what `$agent-communication` is or how to invoke it.

Add a short error-recovery step to the workflow, e.g., what to do when step 6 verification fails (resend with corrections, inspect `detail --tail`, or stop the agent).

Dimension	Reasoning	Score
Conciseness	The body is lean with zero padding — every line is a command, a rule, or a caveat that earns its place (e.g., "Partial matches are convenient but risk sending work to the wrong agent"), and it explains nothing Claude already knows.	5 / 5
Actionability	The Commands block is copy-paste ready and the example send instruction is concrete, but there are minor gaps: no command shows how to create a group before using `send --group`, only one `--type` value (codex) is shown, and `$agent-communication` is referenced without explanation.	4 / 5
Workflow Clarity	A clear six-step sequence with a verification checkpoint ("Verify completed work before reporting it done") and a destructive-action guard ("Ask before killing agents you did not start") avoids the cap, but there is no error-recovery feedback loop for what to do when verification fails.	4 / 5
Progressive Disclosure	The skill is under 50 lines with no need for external references, and its content is cleanly split into Workflow, Commands, and Assignment Rules sections, meeting the rubric's exception for well-organized simple skills.	5 / 5
	Total	18 / 20 Passed

Description

100%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 description: it states the tool and purpose concisely, then provides an explicit 'Use when' clause with a comprehensive, naturally-phrased list of trigger actions. It is lean, specific, and clearly distinguishable from neighboring skills.

Dimension	Reasoning	Score
Specificity	Enumerates nine concrete actions ("identify itself, list agents, start workers, inspect agent detail, assign work, group agents, resume sessions, stop agents, or delegate work"), giving comprehensive coverage of the skill's capabilities rather than the minor gaps of the anchor-4 example.	5 / 5
Completeness	Explicitly answers both questions: the 'what' ("Manage running AI agents with ai-devkit agent commands") and a concrete 'when' ("Use when an agent needs to identify itself, list agents, ... delegate work"), matching the anchor-5 example structure.	5 / 5
Trigger Term Quality	Phrases like "list agents", "start workers", "stop agents", and "delegate work to other agents" are exactly what a user would naturally say, with synonym coverage (workers/agents); no common variation is obviously missing.	5 / 5
Distinctiveness Conflict Risk	It carves out a clear niche — managing running agents via the ai-devkit CLI — with trigger verbs (inspect agent detail, assign work, resume sessions) unlikely to fire for unrelated skills, so conflict risk is minimal.	5 / 5
	Total	20 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: codeaholicguy/ai-devkit
Path: skills/agent-management/SKILL.md
Commit: 7ef0cd5

Reviewed: 8 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.