project-management

Use when admin asks to start a multi-worker project, when a Worker @mentions you with task completion in a project room, when project plan changes are needed, or when a blocked task needs resolution.

Quality

85%

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

87%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 concise, actionable, and well-structured with proper one-level-deep progressive disclosure, but it routes full step sequences to reference files and omits an inline validate→fix→retry feedback loop for the batch/destructive operations it orchestrates, capping workflow clarity at 2.

Suggestions

Add a short inline numbered workflow for the core project lifecycle (create → assign → track → complete) with an explicit validate→fix→retry checkpoint, deferring only the deep details to references.

Make the revision feedback loop explicit in the body (REVISION_NEEDED → fix → re-validate → only then proceed to next phase) rather than only forbidding progression.

Consider a one-line checklist for the mandatory "all tasks complete" step (update meta.json, sync plan.md to MinIO, notify admin) so the terminal workflow is unambiguous without opening a reference.

Dimension	Reasoning	Score
Conciseness	The body is lean and dense — compact directory layout, a gotchas list of high-signal bullets, and a small routing table — with no explanation of concepts Claude already knows and no padding; every line earns its place.	3 / 3
Actionability	It gives concrete executable guidance: a copy-paste shell check (`[ "${AGENTTEAMS_YOLO:-}" = "1" ] \|\| [ -f ~/yolo-mode ]`), exact file paths, and a situation→document routing table mapping each case to a specific reference file.	3 / 3
Workflow Clarity	Sequencing and validation checkpoints exist as rules ("Do NOT proceed to next phase while REVISION_NEEDED is pending", mandatory "all tasks complete" step, YOLO auto-confirm), but the actual numbered step sequences and validate→fix→retry loops live in the referenced docs rather than inline; for batch/destructive project operations the inline workflow lacks an explicit feedback loop, capping this at 2.	2 / 3
Progressive Disclosure	The body is a clear overview that points one level deep to four real reference files (create-project.md, task-lifecycle.md, plan-format.md, plan-changes.md) via a well-signaled routing table ("Read the relevant doc before executing"), with content appropriately split and easy to navigate.	3 / 3
	Total	11 / 12 Passed

Description

82%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 has strong, natural trigger terms and a clearly distinctive niche, but it leans entirely on "Use when…" triggers without an explicit statement of what the skill does, capping completeness at 2.

Suggestions

Add a leading capability clause stating what the skill does, e.g. "Coordinates multi-worker projects via Matrix project rooms: creates projects, assigns tasks, tracks a plan.md, and resolves blockers."

Keep the existing "Use when…" triggers but pair them with the explicit capability verb so both what and when are stated.

Optionally surface a couple more natural user phrasings (e.g. "onboard a worker mid-project", "request more headcount") to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	Names multiple concrete trigger scenarios — "start a multi-worker project", "Worker @mentions you with task completion in a project room", "project plan changes are needed", "blocked task needs resolution" — matching the anchor for several specific actions rather than vague language.	3 / 3
Completeness	It has an explicit "Use when…" clause covering when to invoke the skill, but never states what the skill does (no capability verb like "Coordinates/Manages multi-worker projects"); the what is only implied through triggers, so it does not reach the anchor requiring both explicit what and when.	2 / 3
Trigger Term Quality	Uses natural phrases an admin or worker would actually say ("start a multi-worker project", "task completion", "plan changes", "blocked task"), giving good coverage of realistic trigger terms.	3 / 3
Distinctiveness Conflict Risk	The niche is specific (multi-worker project coordination in Matrix project rooms with plan.md/meta.json) and its triggers are distinct, making it unlikely to fire for an unrelated skill.	3 / 3
	Total	11 / 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/project-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.