CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

teamharness-project-management

Use when you act as Leader and maintain 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

77%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./plugins/agentteams-teamharness/skills/team/project-management/SKILL.md

The canonical home for this skill is teamharness-project-management in agentscope-ai/AgentTeams

SKILL.md
Quality
Evals
Security

Quality

Content

71%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 highly actionable body with complete JSON payloads, explicit gating conditions, and precise state-machine rules for every operation. Its main weaknesses are a monolithic 650-line structure with no reference files and duplicated requester-report material that inflates token cost.

Suggestions

Move the Project Status Reports template, Post-Action Notification details, and Pause/Resume/Complete sections into reference files (e.g., references/report-template.md, references/notifications.md) and link them from SKILL.md.

Deduplicate the requester-report delivery and artifact-publish steps that appear in both "Accepting Worker Results" and "Project Status Reports"; state the protocol once and cross-reference it.

Add error-recovery guidance for tool failures (e.g., retry behavior when projectflow returns an error) to complete the workflow feedback loop.

Trim the localized-placeholder report envelope to one compact example instead of the fully elaborated template.

DimensionReasoningScore

Conciseness

Most content is TeamHarness-specific protocol Claude cannot know, but it could be tightened: the requester-report delivery and artifact-publish steps are duplicated across "Accepting Worker Results" and "Project Status Reports", "Use this skill when maintaining durable project state" is stated twice near the top, and the localized-placeholder report envelope is padded. This matches 'mostly efficient but could be tightened' rather than the noticeably-verbose anchor below.

3 / 5

Actionability

Fully executable throughout: complete copy-paste JSON payloads for every projectflow action, exact file paths ("shared/projects/{project-id}/meta.json"), a safe-ID regex, allowed loop decision enums, and precise submissionId fencing rules — matching the 'copy-paste ready; specific examples cover the common cases' anchor.

5 / 5

Workflow Clarity

Clear numbered sequences with explicit checkpoints ("send that message only after the tool returns ok: true", "After teamharness-task-delegation checks the task and returns effective: true"), but error-recovery feedback loops are largely absent — e.g., no guidance on what to do when a tool call itself fails — so it falls short of the anchor above.

4 / 5

Progressive Disclosure

Section headers are clear and well-organized, but the ~650-line body inlines everything — the full status-report template, post-action notification protocol, and pause/resume/complete lifecycle — with no bundle reference files to split content into. This matches 'some structure but content that should be separate is inline' rather than the minimal-structure anchor, since navigation within the file is good.

3 / 5

Total

15

/

20

Passed

Description

75%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 strong, highly distinctive description that explicitly states both what it does and when to use it, plus a useful negative boundary. Its weaknesses are the second-person voice and jargon-heavy trigger terms, which lower specificity and natural trigger quality.

Suggestions

Rewrite in third person (e.g., "Use when acting as Leader and maintaining durable TeamHarness project state...") to avoid the second-person voice penalty.

Add natural trigger phrases a user would actually say (e.g., "project status", "accept a worker result", "pause or resume a project") alongside the tool-action names.

Mention pause_project/resume_project and loop iteration recording to close the coverage gaps in the action list.

DimensionReasoningScore

Specificity

Lists many concrete actions ("create_quick_project, create_project, plan_dag, plan_loop, ready_nodes, resolve_project, accept_task_result") with only minor gaps (pause/resume, loop iteration recording), which is a 4; however the second-person phrasing "Use when you act as Leader" triggers the rubric's voice penalty, reducing the score to 3.

3 / 5

Completeness

Explicitly answers 'when' ("Use when you act as Leader and maintain durable TeamHarness project state for Quick Task or Project Work") with concrete trigger phrases, answers 'what' via the colon-separated action list, and adds a negative boundary ("Do not use to create Matrix task rooms or send messages").

5 / 5

Trigger Term Quality

"Quick Task", "Project Work", and "project state" are relevant keywords, but the triggers lean on tool-action jargon ("plan_dag", "ready_nodes", "resolve_project") rather than natural phrases a user would say, and common synonyms are missing — matching the 'some relevant keywords but missing variations' anchor rather than the good-coverage anchor above.

3 / 5

Distinctiveness Conflict Risk

Occupies a clear TeamHarness/Leader niche with distinct tool-action triggers and an explicit exclusion clause, making it unlikely to fire for the wrong skill — matching the 'clear niche with distinct triggers; minimal conflict risk' anchor.

5 / 5

Total

16

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (658 lines); consider splitting into references/ and linking

Warning

Total

15

/

16

Passed

Repository

agentscope-ai/AgentTeams

Path

plugins/agentteams-teamharness/skills/team/project-management/SKILL.md

Reviewed

Table of Contents

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.