Plan

Skill Le-Xuan-Thang/workflow-kit/skills/plan

Use to generate a structured workplan — objectives and tasks — from workflow/product.md. Requires init to have run first (phase must be 'define' or 'plan'). Also triggers when the user says "generate my workplan", "plan the project", "create tasks from the product definition", or "what should the agent work on".From its SKILL.md

Install

npx -y skills add Le-Xuan-Thang/workflow-kit --skill plan

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

2.5 KB, as published. Nobody here has run it

Workflow Plan

Read workflow/product.md and generate objectives + tasks matched to worker capability. Advances phase to plan.

<HARD-GATE> Do NOT generate tasks if workflow/product.md is missing or phase is past 'plan'. Warn and stop. </HARD-GATE>

Step 1: Check prerequisites

python3 -c "
from workflow_kit.runtime.state import load_state
from pathlib import Path
s = load_state(Path('.'))
print('phase:', s.phase)
print('product_type:', s.product_type)
"
ls workflow/product.md 2>/dev/null && echo "product-ok" || echo "product-missing"
ls workflow/worker_capability.json 2>/dev/null && echo "capability-ok" || echo "no-capability-warning"

Phase execute or later: "Already past planning. Use /workflow-kit:execute to continue."
workflow/product.md missing: "Run /workflow-kit:init first."
No capability file: warn but continue — orchestrator will plan conservatively.

Step 2: Generate workplan

python -m workflow_kit workplan

Orchestrator (DeepSeek) reads:

workflow/product.md (Vision/Mission/Core)
workflow/worker_capability.json (skill scores)
workflow/tasks/completed/ (what's already done)

Creates 3–5 objectives aligned to Vision. Tasks under each objective matched to worker skill scores. Tasks needing a skill < 3.0 are decomposed into smaller sub-tasks.

Step 3: Write workflow/workplan.md

# Workplan — <product name>

Generated: <timestamp>

## Objectives

### <Objective 1>
**Why:** aligned to Vision/Mission
**Success criteria:** measurable outcome

Tasks:
- [ ] <task-id>: <description>

Step 4: Advance state to 'plan'

from workflow_kit.runtime.state import load_state, save_state
from pathlib import Path
s = load_state(Path('.'))
if s.phase == "define":
    s.transition_to("plan")
    save_state(s, Path('.'))
    print("Phase: define → plan")

Step 5: Report

Workplan generated:

  Objectives: N
  Tasks:      N pending in workflow/tasks/pending/

  obj-01: <name>  (N tasks)
  obj-02: <name>  (N tasks)

Review workflow/workplan.md, then:
  /workflow-kit:execute  — start the dispatcher with reviewer agents