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

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 ./manager/agent/skills/project-management/SKILL.md

Quality

Content

80%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 well-structured orchestration skill body that is concise, navigable, and properly split across one-level-deep reference files. Its main weakness is workflow clarity: the body holds validation guardrails as scattered gotchas rather than an explicit sequenced workflow with embedded checkpoints.

Suggestions

Add a short numbered end-to-end sequence in the body (e.g. create project -> assign tasks -> handle completion -> close project) with explicit validation checkpoints, so the workflow is legible without opening a reference.

Promote the scattered validation gotchas into the sequence as labeled checkpoint steps (e.g. 'Checkpoint: confirm REVISION_NEEDED resolved before next phase').

Consider one inline minimal code snippet per common operation so the body is actionable without a reference round-trip.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence: a compact directory tree, a dense Gotchas list with an executable shell snippet, and a routing table, with no over-explanation of concepts Claude already knows.	5 / 5
Actionability	Provides a concrete executable command ('[ "${AGENTTEAMS_YOLO:-}" = "1" ] \|\| [ -f ~/yolo-mode ]') and explicit reference paths, but most executable procedure is intentionally deferred to the reference files, leaving minor gaps in the body itself.	4 / 5
Workflow Clarity	Validation guardrails exist as gotchas ('Do NOT proceed to next phase while REVISION_NEEDED is pending', 'Check YOLO mode BEFORE drafting the plan'), but no explicitly sequenced multi-step workflow appears in the body — sequencing lives in the reference files.	3 / 5
Progressive Disclosure	A clear overview with well-signaled one-level-deep references via the situation-to-doc table, and all four referenced files (create-project.md, task-lifecycle.md, plan-format.md, plan-changes.md) exist in references/.	5 / 5
	Total	17 / 20 Passed

Description

70%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 trigger-focused description with strong, natural 'when' guidance and a clear distinct niche, weakened by the absence of an explicit 'what' statement of capabilities. Adding a leading capability clause ('Coordinates multi-worker projects: creates project rooms, tracks task lifecycle, updates plan.md') would lift completeness and specificity.

Suggestions

Prepend a concise 'what' clause stating the skill's capabilities (e.g. 'Coordinates multi-worker projects: creates project rooms, manages task lifecycle, and maintains plan.md') before the 'Use when' triggers.

Add a few natural trigger synonyms such as 'assign a task', 'headcount request', or 'onboard a worker mid-project' to broaden keyword coverage.

Keep the four existing concrete triggers — they are the description's strongest asset and should be preserved verbatim.

Dimension	Reasoning	Score
Specificity	Lists four concrete trigger situations ('start a multi-worker project', 'Worker @mentions you with task completion', 'project plan changes', 'blocked task needs resolution') rather than vague language, though it names triggering contexts more than the concrete capability actions the skill performs.	4 / 5
Completeness	The 'when' is explicit and strong with four concrete triggers, but the 'what' (the capabilities the skill performs) is only implied by the name 'project-management' and never stated, so it does not reach the both-what-and-when anchors.	3 / 5
Trigger Term Quality	Natural admin/worker phrases like 'start a multi-worker project', 'task completion', 'project plan changes', and 'blocked task' would plausibly be said, but a few natural synonyms (e.g. 'assign a task', 'headcount') are missing.	4 / 5
Distinctiveness Conflict Risk	The niche is distinct — multi-worker project rooms, Worker @mention task completion, and plan.md coordination — with triggers unlikely to fire for unrelated skills.	5 / 5
	Total	16 / 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: agentscope-ai/AgentTeams
Path: manager/agent/skills/project-management/SKILL.md
Commit: acaed25

Reviewed: 3 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.