CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

project-management

Use before any projectflow call or Team Leader workflow involving Project state, Project lifecycle, DAG planning, Loop planning, ready node checks, pause/resume/complete, project recovery, heartbeat project checks, or project-level result aggregation. Always use team-coordination first when the question is how to organize the work.

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

82%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, well-structured skill: every projectflow action has a concrete payload, ID and assignment rules are mechanical with worked examples, and workflows carry explicit stop/check conditions. Weaknesses are moderate: repetition across lifecycle sections, inlined time-sensitive heartbeat rules, and a long report template that belongs in a reference file.

Suggestions

Move the Project Status Reports envelope and DAG/Loop progress templates into a references/status-reports.md file and keep only the decision rules inline, tightening both conciseness and progressive disclosure.

Isolate the temporary heartbeat/runtime-probe rules into a clearly labeled 'Temporarily disabled' or deprecated section so stale time-sensitive instructions are cheap to spot and remove.

Define how to verify 'delivery criteria are satisfied' in the Complete workflow (e.g., check every plan node is accepted [x] and result.md is non-empty) to close the last validation gap.

DimensionReasoningScore

Conciseness

The body is dense, imperative, and assumes Claude's competence (no concept tutorials), but it repeats pull/publish steps across lifecycle sections, reiterates 'Delegate returned nodes with task-management' twice, and inlines time-sensitive material ('Team Leader heartbeat is temporarily disabled', 'Do not call check_active_tasks for now') outside any deprecated/old-patterns section.

4 / 5

Actionability

Fully executable guidance throughout: complete JSON payloads for create_project, plan_dag, plan_loop, and record_loop_iteration; the exact command 'agt get workers --team "$TEAM_CR" -o json'; a strict ID regex with concrete ID formats; and a worked example table for extracting the Matrix localpart. Common cases are covered copy-paste ready.

5 / 5

Workflow Clarity

Numbered pause/resume/complete sequences with explicit preconditions ('Confirm the requester explicitly wants scheduling to continue'), a 5-step Result Gate with an explicit paused-stop checkpoint, and mandatory pre-call lookup steps. Minor gaps remain: 'Confirm delivery criteria are satisfied' names no verification method, and 'plan refresh if needed' is loose.

4 / 5

Progressive Disclosure

Well-organized sections with one clearly signaled, verified one-level-deep reference (references/dag-execution.md, listed under 'Read only when needed'). However, the ~90-line Project Status Reports template is inlined in SKILL.md where a reference file would fit, and only one reference serves a skill of this size.

4 / 5

Total

17

/

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, trigger-oriented description with explicit use-before guidance, explicit disambiguation against team-coordination, and a comprehensive enumeration of domain actions. Its main weakness is that what the skill actually does is implied rather than stated, and its boundary with task-management is only drawn in the body.

Suggestions

Open with a one-clause capability statement (e.g., 'Manages Project files, lifecycle, and DAG/Loop execution plans via projectflow') before the trigger list so the 'what' is explicit, not implied.

Add a trigger phrase or clause distinguishing this from task-management (e.g., 'For individual Worker task files, use task-management instead').

Trim repeated qualifier words ('Project ... project') in the trigger list to tighten the phrasing without losing coverage.

DimensionReasoningScore

Specificity

Enumerates many concrete domain actions ('DAG planning, Loop planning, ready node checks, pause/resume/complete, project recovery, heartbeat project checks, or project-level result aggregation'), but presents them as workflow triggers rather than explicit capability statements, so it falls just short of comprehensive anchor-5 coverage.

4 / 5

Completeness

The 'when' is explicit and concrete ('Use before any projectflow call or Team Leader workflow involving...'), but the 'what' is only implied through the scope enumeration rather than stated as capabilities, so it does not reach the anchor-5 bar of clearly answering both.

4 / 5

Trigger Term Quality

Good natural keyword coverage for this ecosystem ('projectflow call', 'Team Leader workflow', 'DAG planning', 'Loop planning', 'pause/resume/complete', 'project recovery', 'heartbeat project checks'), though a few plausible user phrasings such as project status or project reporting are missing.

4 / 5

Distinctiveness Conflict Risk

Explicit boundary guidance ('Always use team-coordination first when the question is how to organize the work') and a clear projectflow/Project-state niche reduce conflict, but overlap with the sibling task-management skill (Worker tasks) is not addressed in the description itself.

4 / 5

Total

16

/

20

Passed

Validation

100%

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/team-leader-agent/skills/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.