human-management

Use when admin requests adding a human user to the system, changing human permissions, removing human access, or managing human accounts.

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Medium

Suggest reviewing before use

Quality

Content

72%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is well-organized and token-efficient with strong progressive disclosure, but its actionability and workflow clarity are undermined by a referenced --update flag that the bundled script does not implement and by missing verification steps for destructive operations.

Suggestions

Resolve the --update flag mismatch: either implement --update in scripts/create-human.sh or correct the Gotcha to describe the actual permission-change procedure.

Add an explicit verification checkpoint for destructive operations, e.g. confirm before `agt delete human <name>` and re-run `agt get humans <name>` to confirm removal.

Promote the create path into a short sequenced workflow in the body with a validation step (re-query the Human CR to confirm reconciliation) instead of only delegating to the reference.

Dimension	Reasoning	Score
Conciseness	The body is lean: a compact intro, a permission-level table, one executable Quick Create block, targeted Gotchas, and an operation table, with no padding or explanation of concepts Claude already knows.	3 / 3
Actionability	The Quick Create command and `agt get humans` / `agt delete human` references are concrete and executable, but the Gotchas direct the reader to a `--update` flag on create-human.sh that does not exist in the script, so the guidance is not fully complete and copy-paste ready.	2 / 3
Workflow Clarity	A sequence is implied and the referenced create-human.md does include an async-provisioning verification step, but the body presents destructive operations (e.g. `agt delete human`) with no validation checkpoint, and the permission-change guidance relies on the non-existent --update flag.	2 / 3
Progressive Disclosure	The SKILL.md is a clear overview with a well-signaled, one-level-deep pointer to references/create-human.md (confirmed to exist and not nest further into other docs), and the Operation Reference table maps tasks to files and scripts for easy navigation.	3 / 3
	Total	10 / 12 Passed

Description

100%Weight 40%Scale 1-3

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is concise, uses third person, and clearly states both the concrete capabilities and an explicit trigger clause. It is distinctive and free of vague fluff or over-claims.

Dimension	Reasoning	Score
Specificity	"adding a human user to the system, changing human permissions, removing human access, or managing human accounts" lists multiple specific concrete actions, matching the anchor 3 example.	3 / 3
Completeness	The explicit "Use when admin requests..." clause answers when, and the enumerated operations answer what, satisfying the anchor 3 bar for both.	3 / 3
Trigger Term Quality	Natural admin phrasings like "adding a human user", "changing human permissions", "removing human access", and "managing human accounts" give good coverage of terms a user would actually say.	3 / 3
Distinctiveness Conflict Risk	The repeated "human" qualifier and account-management niche give it a clear, distinctive trigger unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 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: agentscope-ai/AgentTeams
Path: manager/agent/skills/human-management/SKILL.md
Commit: 785c2db

Reviewed: 6 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.