agentleFS
Pearl1531Pearl1531/Archetype-talk/.claude/skills/prioritize/SKILL.md

prioritize

Skill2 starsChanged 49 days agoMITView on GitHub

Score and rank Ideas/ with RICE grounded in the graph. Use when the user runs /prioritize, asks which idea to build first, or wants a scored roadmap input.

20 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use decision-doc, weekly-plan and 7 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • MehdibargachSkill

    decision-doc

    Structure a product decision with options, trade-offs, and a clear recommendation. Takes a decision to make and outputs a concise decision document ready for stakeholder review.

    Also in 3 projects that use this

  • aleksander-dytkoSkill

    weekly-plan

    Plan weekly P-Tasks with in-repo task triage and overplanning challenge

    Also in 3 projects that use this

  • arezousSkill

    status-update

    Write a status update for a project or initiative. Matches the style to the audience.

    Also in 3 projects that use this

  • RhyGSkill

    write-prd

    Also in 3 projects that use this

  • SentrySkill

    onboard

    Onboard a service to sentry-options. Use when integrating a new service, creating schemas, or setting up the multi-repo sentry-options workflow.

    Also in 3 projects that use this

  • BlockSkill

    plan

    Draft a TDD, PRD, or lightweight plan in the conversation without committing it.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 19 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read every idea in scope + its linked Evidence/Signals (+ the persona sections that reference it).

    line 29

“Common” is measured: kept by at least 6 in 10 of the 19 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

prioritize — Grounded RICE over Ideas/

Standard RICE with one twist that this repo makes possible: the numbers have to say where they came from. Reach cites Evidence, Confidence is derived from claim Levels (not gut-picked), and anything unknowable from research is marked TBD instead of invented.

Trigger

/prioritize                 ← score every file in Ideas/ (Hypotheses/ are NEVER scored — no grounding, no RICE; promote to an Idea first)
/prioritize Ideas/<file>    ← score/rescore one idea

Scoring rules (per idea)

  • Reach — who/how many, cited from a linked Evidence/ file ("22.2% of subscribers share accounts [Shared accounts]"). No Evidence with a number → estimate, no data and a note that /researcher or /analytics-sync could firm it up. Never invent a percentage.
  • Impact (0.25–3) — how directly it addresses the linked Pain; one line of reasoning tied to the Signal.
  • Confidence — derived, never hand-picked, from the strongest claim Level among the idea's linked sources (canonical scale: ai-persona/references/levels.md):
    • L4–L5 → High (1.0) · L3 → Medium (0.8) · L2 → Low (0.5) · L1/none → Very low (0.2)
    • Stale sources (3-month rule) knock Confidence down one band — say so in the row.
  • Effort — the one input research can't provide. Ask the user/team for sizing; until given, TBD (and the RICE score stays TBD — an unranked idea is honest, a fake-ranked one isn't).
  • Metric to watch — the product metric this idea should move, phrased so /analytics-sync could actually query it.

Workflow

  1. Read every idea in scope + its linked Evidence/Signals (+ the persona sections that reference it).
  2. Compute the scoring block per idea; show the full table sorted by RICE (TBD-effort rows listed separately, not silently ranked last).
  3. On approval, write/update each idea's ## PM scoring section (the Ideas/_template.md block) — the file is the source of truth, the table is a view.
  4. Flag ideas whose Confidence is Very low/Low as research-first, not build-first — route to /interview-guide (that's the cheaper way to raise Confidence than shipping blind).
  5. Offer follow-ups: /feature-panel for a who-benefits view of the top idea, /export ticket for the winner, /opportunity-tree for the strategic view.

Rules

  • Confidence derivation is mechanical — if the user wants to override it, record the override explicitly ("Confidence raised by PM judgment, data says L3") rather than silently editing.
  • Rescoring after new research is expected and cheap — new Signals/Evidence change Levels, Levels change Confidence; say what moved and why.
  • This skill edits only Ideas/ scoring blocks — never the underlying Evidence/Signals.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.