OpenParable
Skip to content
← Back to skills

Paca Sprint

Productivity
paca-sprint

Paca Sprint is an Agent Skill for productivity published in the Paca-AI/paca repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.

Plan a Paca sprint by selecting tasks from the backlog, detecting carryover from the previous sprint, inferring velocity from past sprints, and assigning tasks to the sprint. Use when starting a new sprint, filling an upcoming sprint, reviewing sprint capacity, or setting the sprint goal.

View on GitHub ↗
QUICK START

How to use this skill

Bring this guide into your coding agent with a prompt tailored to the tool you use.

  1. Open your project in Codex.
  2. Copy and paste the prompt below.
  3. Review files and risks before approving any action.
Prompt to paste
Inspect the Agent Skill at https://github.com/Paca-AI/paca/blob/HEAD/skills/paca-sprint/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/paca-sprint, but wait for my approval before writing files or running scripts.

Copying this prompt does not install or run the skill. Review third-party files before use.

You are planning a sprint in Paca. Use Paca MCP tools throughout — never create local files.

If no sprint is specified, default to planning the next upcoming sprint for the most active project.


Step 1 — Load project context

  1. Call list_projects and identify the relevant project.
  2. Call list_docs and search for documents with keywords like "roadmap", "goals", "OKR", "retrospective", or "planning". Read the most relevant ones with read_doc. What the last sprint achieved and what the project's current goals are will shape which tasks belong in this sprint.
  3. Call list_sprints to see existing sprints (active, upcoming, completed).
  4. Call list_tasks (backlog or unassigned filter) to see the candidate task pool.

Step 2 — Detect carryover and infer velocity

Carryover: Check the most recently completed sprint for tasks that were in it but are still open (status is not done). Flag these — carryover tasks typically get priority in the next sprint.

Velocity: Look at the last 2–3 completed sprints. Sum the story point estimates of tasks that were marked done. Use the average as the default capacity if the user hasn't stated one.

Step 3 — Determine sprint parameters

From the user's message and context:

  • Which sprint — by number, name, or "next sprint"
  • Capacity — story points available; use inferred velocity as the default, ask to confirm
  • Goal — what outcome the sprint should deliver; infer from the roadmap or ask
  • Duration — start/end dates; infer from the cadence of past sprints or ask

Step 4 — Select tasks

Rank backlog tasks and recommend a set that fits within capacity:

  • First: carryover tasks from the previous sprint
  • Then: tasks ranked by explicit priority → unblocking dependencies → business value → estimate size
  • Flag: tasks missing estimates or acceptance criteria — offer to run /paca-estimate or /paca-clarify on them before committing

Present the proposed list with a total estimated points and the sprint goal. Ask the user to confirm, swap, or adjust before applying.

Step 5 — Apply the plan

Once confirmed:

  1. If the sprint does not exist, create it with create_sprint (name, goal, startDate, endDate)
  2. Assign each task to the sprint with update_task (set sprintId)
  3. Set or update the sprint goal with update_sprint

Optionally create or update a sprint planning note in Paca Docs (write_doc) with the sprint goal, task list, capacity, and velocity reference.

Report back: sprint name, dates, task count, total estimate, capacity used, and sprint goal.


If Paca MCP is not connected

Paca MCP tools are not available. Run /paca-setup to configure the connection.


Tool reference

Sprints: list_sprints · get_sprint · create_sprint · update_sprint · complete_sprint
Tasks: list_tasks · get_task · update_task · bulk_move_tasks
Documents: list_docs · read_doc · write_doc
Projects: list_projects