Plan Task
- 3 installs
- 19 repo stars
- Updated March 1, 2026
- haowjy/orchestrate
Reads a plan and progress files, then writes the next implementable task file with context, scope, and acceptance criteria.
About
Decomposes a multi-step plan into the next ordered task file, reading prior progress to keep continuity and writing ALL_DONE when complete. A developer uses it to turn a plan into discrete work units an implementing agent can execute.
- Reads plan, progress.md, and prior task.md for continuity
- Writes a task.md with context, scope, acceptance criteria, and constraints
Plan Task by the numbers
- 3 all-time installs (skills.sh)
- +1 installs in the week ending Aug 2, 2026 (Skillselion tracking)
- Ranked #2,390 of 3,282 Productivity & Planning skills by installs in the Skillselion catalog
- Data as of Aug 2, 2026 (Skillselion catalog sync)
npx skills add https://github.com/haowjy/orchestrate --skill plan-taskAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 3 |
|---|---|
| repo stars | ★ 19 |
| Last updated | March 1, 2026 |
| Repository | haowjy/orchestrate ↗ |
What it does
Reads a plan and progress files, then writes the next implementable task file with context, scope, and acceptance criteria.
Files
Plan Task
Create the next implementable task from a plan.
When Invoked
Step 1: Read Inputs
Use these prompt variables:
{{PLAN_FILE}}— source plan to read
Resolve output directory:
- Always use a path next to the plan:
<dir-of-PLAN_FILE>/tasks. - Create the output directory if it does not exist.
Step 2: Read Progress
Gather context on what is already completed:
1. Read {{PLAN_FILE}} and inspect status/phase tracking sections. 2. If <resolved-tasks-dir>/progress.md exists, read it for prior completed tasks. 3. If <resolved-tasks-dir>/task.md exists, use it as context for continuity.
Step 3: Determine Completion
If all phases/steps in the plan are complete:
- Write only the text
ALL_DONEto<resolved-tasks-dir>/task.md. - Stop here.
Step 4: Create Task File
Determine the next logical task from the plan.
Write <resolved-tasks-dir>/task.md. Include whatever structure makes sense, but the task file should give an implementing agent everything it needs:
- Context: why this task is next
- Scope: what to implement — files, functions, integration points
- Acceptance criteria: how to verify it's done
- Constraints: architectural limits, gotchas
A good task is self-contained: the codebase must be in a working state when done. Size is secondary — focus on logical completeness, not line count.
# Runtime artifacts — hidden directories are generated, never committed
.*
!.gitignore
Related skills
Grill MeHave an agent relentlessly pressure-test their plan or design until every decision branch is resolved and shared understanding is reached.691k196kGrill With DocsPressure-test architecture decisions against their live codebase and living documentation before writing production code.585k196k
Lark CalendarLet their coding agents read, create, and manage events inside Lark (Feishu) Calendar directly from natural language instructions.493kLark ImLet their coding agent send instant notifications, post updates, and receive commands directly inside Lark (Feishu) workspaces.493kLark ContactLet their AI coding agents read and write contacts, send messages, and manage user data inside Lark (Feishu).493kLark AttendanceAutomatically fetch and report daily attendance data from Lark (Feishu) into their own tools or agents.493k