teamharness-project-management

Use when a Leader maintains durable TeamHarness project state for Quick Task or Project Work: create_quick_project, create_project, plan_dag, plan_loop, ready_nodes, resolve_project, accept_task_result, project completion, and requester report state. Do not use to create Matrix task rooms or send messages.

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

100%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 a dense, executable reference: complete JSON payloads, explicit sequencing, and validation/notification checkpoints throughout, with negligible conceptual padding. It is an instruction-only skill and the guidance is highly actionable, so the absence of code is not penalized.

Dimension	Reasoning	Score
Conciseness	Lean, operational prose with almost no conceptual padding; it assumes Claude's competence and every section advances a concrete instruction.	3 / 3
Actionability	Each action ships a complete, executable JSON payload (e.g. create_project, plan_dag, accept_task_result) that is copy-paste ready with all required fields.	3 / 3
Workflow Clarity	Multi-step processes are explicitly sequenced with validation checkpoints and feedback loops (e.g. accept_task_result -> ready_nodes -> delegate, and the requester-report delivery protocol steps).	3 / 3
Progressive Disclosure	No bundle files exist, but the body is well-organized into clear single-purpose sections with one-level cross-skill references (teamharness-* siblings) rather than nested inline detail.	3 / 3
	Total	12 / 12 Passed

Description

85%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 specific, complete, and well-bounded with explicit trigger guidance and a negative-scope clause. Trigger terms are somewhat internal/jargon-heavy rather than natural user phrasing, which is the only meaningful weakness.

Suggestions

Add one or two natural-language trigger phrases (e.g. 'project planning' or 'track project progress') alongside the tool-action names so users who don't know the API names can still match this skill.

Soften the heavy reliance on internal action identifiers in the lead clause so the opening reads more like a user-facing capability than an API enumeration.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions explicitly ('create_quick_project, create_project, plan_dag, plan_loop, ready_nodes, resolve_project, accept_task_result, project completion, and requester report state').	3 / 3
Completeness	Explicitly answers what it does via the action list and when to use it with a 'Use when' clause, plus a 'Do not use' boundary.	3 / 3
Trigger Term Quality	Contains relevant action keywords, but they lean toward internal/technical jargon ('plan_dag', 'ready_nodes', 'resolve_project') rather than natural phrasings a user would commonly say.	2 / 3
Distinctiveness Conflict Risk	A clear TeamHarness project-state niche with an explicit 'Do not use to create Matrix task rooms or send messages' boundary reduces conflict with adjacent skills.	3 / 3
	Total	11 / 12 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
skill_md_line_count	SKILL.md is long (558 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: agentscope-ai/AgentTeams
Path: plugins/teamharness/skills/team/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.