OpenParable
Skip to content
← Back to skills

Paca Prioritize

Productivity
paca-prioritize

Paca Prioritize 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.

Set or adjust priorities across the Paca backlog, aligned to roadmap goals and business value. Use when the backlog needs sorting, before sprint planning, when tasks need explicit Critical/High/Medium/Low priority labels, or when asked to rank work by importance or urgency.

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-prioritize/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/paca-prioritize, 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 setting priorities for tasks in Paca. Use Paca MCP tools throughout — never create local files.

If no task is specified, operate on the full backlog of the most active project.


Step 1 — Load project context

  1. Resolve task references from the user's message if given (#42, ABC-42 → get_task_by_number). If no references, operate on the full backlog.
  2. Call list_docs and search for documents titled "roadmap", "goals", "OKR", "strategy", or "release plan". Read the most relevant ones with read_doc. Priority without a goal to align to is just opinion — the docs anchor your reasoning.
    • If no strategy docs exist, ask the user: "What are the top 3 outcomes you're trying to achieve this quarter?" Use their answer as the alignment anchor.
  3. Call list_tasks to load the full task set.
  4. Call list_sprints to know which tasks are already committed vs. unscheduled.

Step 2 — Score and rank

For each task, assess four dimensions:

DimensionWhat to look for
Business valueHow directly it advances the roadmap or improves user outcomes
Urgency / riskCustomer-facing bugs, blockers, compliance deadlines
EffortEstimated size — high-value + low-effort tasks rank up
DependenciesTasks that unblock others rank higher

Assign one of these labels:

  • Critical — blocks a release, breaks production, or is a contractual obligation
  • High — directly advances the top roadmap goal; would be missed by users if delayed
  • Medium — valuable but not time-sensitive; no clear near-term cost to waiting
  • Low — nice-to-have, cleanup, or exploratory; can be deprioritized indefinitely without user impact

Present the ranked list with one-line reasoning per task. Ask the user to confirm or adjust before writing.

Step 3 — Apply priorities

For each confirmed priority, call update_task:

  • Set the priority field to the agreed value
  • Optionally append a one-line rationale to the description so the reasoning is preserved and reviewable

Report back: full updated priority list as a table (task number · title · priority).


If Paca MCP is not connected

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


Tool reference

Tasks: get_task · get_task_by_number · list_tasks · update_task
Documents: list_docs · read_doc
Sprints: list_sprints
Projects: list_projects