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

83%

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

75%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.

The body is highly actionable with concrete JSON examples and well-sequenced workflows including validation checkpoints, but it is longer than necessary due to repeated route-preservation guidance and a large inlined status-report template that has no bundle file to offload it.

Suggestions

Consolidate the repeated "preserve source/requester/sourceRoomId/replyRoute, do not guess" guidance into one canonical section and reference it from create_project and create_quick_project.

Extract the detailed requester status-report envelope/template into a references/ file (e.g. REPORT_TEMPLATE.md) and keep only the marker table and a short shape example inline.

Add brief explicit error-recovery steps when a validation gate fails (e.g., what to do when accept_task_result returns ok:false or when effective is not true).

Dimension	Reasoning	Score
Conciseness	The body is mostly concrete and necessary for a multi-action skill, but guidance is repeated (route-preservation and "do not guess route values" appear in multiple sections) and the inlined status-report template could be tightened.	3 / 5
Actionability	Each action ships a complete, copy-paste-ready JSON payload (create_project, plan_dag, ready_nodes, plan_loop, accept_task_result, etc.) covering the common cases with real field values.	5 / 5
Workflow Clarity	Multi-step processes are clearly sequenced with numbered checklists and validation gates (effective:true, ok:true, mark_requester_report_sent after delivery), though explicit error-recovery guidance when a check fails is less detailed.	4 / 5
Progressive Disclosure	Well-organized into clear sections with clearly signaled references to sibling skills (teamharness-roomflow, teamharness-communication, teamharness-task-delegation) and TEAMS.md; no bundle files exist, and the large inlined report template is the main organization gap.	4 / 5
	Total	16 / 20 Passed

Description

92%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.

The description is specific, complete, and well-bounded, clearly stating both the capability set and the use conditions with an explicit negative scope. Its only weakness is moderately jargon-heavy trigger phrasing rather than natural user language.

Suggestions

Add a few natural user-facing phrasings (e.g., "create a project", "plan a multi-step task graph") alongside the tool-call names to broaden trigger coverage.

Consider trimming the long inline action enumeration slightly or grouping it (e.g., creation / planning / acceptance / reporting) for readability without losing specificity.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete named actions (create_quick_project, create_project, plan_dag, plan_loop, ready_nodes, resolve_project, accept_task_result, project completion, requester report state), giving comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	Explicitly answers both what (the enumerated actions) and when ("Use when a Leader maintains durable TeamHarness project state for Quick Task or Project Work"), plus an explicit exclusion clause.	5 / 5
Trigger Term Quality	Good keyword coverage with Quick Task, Project Work, project completion, and the named actions, but the terms are somewhat domain-jargon heavy (Leader, durable state, DAG) and miss a few natural user phrasings.	4 / 5
Distinctiveness Conflict Risk	Clear niche (TeamHarness Leader project-state maintenance) with distinct triggers and an explicit "Do not use to create Matrix task rooms or send messages" boundary that minimizes conflict with sibling skills.	5 / 5
	Total	19 / 20 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 (613 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: 223ddc2

Reviewed: 5 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.