agentleFS
aleksander-dytkoaleksander-dytko/ai-pm-workspace/.claude/skills/decision/SKILL.md

decision

Skill34 starsChanged 8 months agoMITView on GitHub

Make a product decision with full context from the vault and available sources

We split this skill into the rules it gives an agent

12 rules. 0 are common, 10 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 15 edited versions we read keep these.

  • 10

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Search repositories for related issues/PRs

    line 27
  2. Distinctive:

    Read engineering comments and discussions

    line 28
  3. Distinctive:

    If provided: extract opinions, concerns, constraints.

    line 33
  4. Distinctive:

    If skipped: proceed without.

    line 34
  5. Distinctive:

    Do not recommend yet - present objectively

    line 45
  6. Very specific:

    Add a link in today's journal (journals/YYYY/MM-Month/DD-MM-YYYY.md) under ## Notes.

    line 88
  7. Distinctive:

    Keep it concise (under 200 words).

    line 92
  8. Very specific:

    After confirmation, append each task to Dashboard/tasks.md under "This week" with format:

    line 99
  9. Distinctive:

    Always cite sources (meeting notes, GitHub issues).

    line 134
  10. Distinctive:

    If options are equal/unclear, present objectively and ask for user preference.

    line 135
  11. Distinctive:

    Leave the "Decision" section empty if not immediately clear.

    line 136
  12. Distinctive:

    If the decision is urgent, propose tasks with P2 priority.

    line 137

“Common” is measured: kept by at least 6 in 10 of the 15 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

Make a Product Decision

You help make a well-informed product decision by gathering context from all available sources and producing structured documentation, follow-up tasks, and a communication draft.

Input

The user provides a decision topic via $ARGUMENTS. Examples:

  • "should we support feature X in the next release"
  • "prioritize feature A vs feature B"
  • "should we adopt GraphQL for the new API"

Workflow

  1. Search the vault:
    • Recent meetings in Meetings/ that touched this topic
    • Daily notes in journals/ (last 2 weeks) for related context
    • Loose Notes/Work/ for related decisions or drafts
    • Dashboard/Weekly P-Tasks.md for related priorities
  2. Use GitHub MCP (if configured):
    • Search repositories for related issues/PRs
    • Read engineering comments and discussions
    • Identify any blockers or concerns raised
  3. Ask for additional context (before options):
    • "Do you have a Slack thread, document, or discussion about this decision? If yes, paste it now."
    • If provided: extract opinions, concerns, constraints.
    • If skipped: proceed without.
  4. Present context summary:
    • Relevant notes and prior discussions
    • Strategy alignment (if strategy docs exist)
    • Customer data or validation (if any)
    • Engineering discussions and feasibility (from GitHub)
  5. Draft options with trade-offs:
    • 2-3 viable options
    • For each: pros (benefits, alignment, customer value), cons (costs, risks, complexity, timeline)
    • Do not recommend yet - present objectively
  6. Create decision note:
    • Location: Loose Notes/Work/YYYY-MM-DD - Decision - [Topic].md
    • Structure:
---
tags: LooseNotes
date: YYYY-MM-DD
---
# Decision: [Topic]

**Date**: YYYY-MM-DD

## Context
[Why this decision is needed - background from notes, meetings, strategy]

## Options Considered
1. **Option 1**: [Description]
   - Pros: ...
   - Cons: ...
2. **Option 2**: [Description]
   - Pros: ...
   - Cons: ...

## Decision
[To be filled after review, or suggest recommendation if clear]

## Rationale
[Why this option, trade-offs accepted]

## Impact
[What changes, who is affected, timeline]

## Communication
[Who needs to be informed, how]

## Follow-up Tasks
- [ ] [Task]
  1. Link the decision note:
    • Add a link in today's journal (journals/YYYY/MM-Month/DD-MM-YYYY.md) under ## Notes.
  2. Draft a communication:
    • A ready-to-post message announcing the decision.
    • Keep it concise (under 200 words).
    • Format: Context → Decision → Impact → Next steps.
    • Channel-neutral by default; if the user names a channel (Slack/email), adapt to that channel's style (see /communicate).
  3. Propose follow-up tasks (confirm before writing):
    • Identify tasks needed to implement and communicate the decision.
    • Show the proposed list and wait for confirmation.
    • After confirmation, append each task to Dashboard/tasks.md under "This week" with format:
- [ ] Task - source: [[YYYY-MM-DD - Decision - Topic]] - due: YYYY-MM-DD - priority: P2

Output Format

Report results in conversational prose, not a fenced template card. Use backtick-wrapped paths for any file references in chat (wikilinks stay inside the decision note itself, not chat output).

Cover these beats in 3-4 sentences of prose:

  • Where the decision note was written (backtick path to the new file in Loose Notes/Work/).
  • Whether it was linked in today's journal (or "skipped - no journal for today").
  • How much context was pulled in (rough count: N related notes, N GitHub issues/PRs).
  • Your recommendation in one line - or "awaiting your input" if the decision genuinely could go either way.

Then show the communication draft (this one stays fenced - it's copy-paste content) and the proposed follow-up tasks as a numbered list so the user can approve with y / n / picking numbers.

Example tone:

Decision note written to Loose Notes/Work/2026-04-21 - Decision - Invoice portal scope.md, linked in today's journal. Pulled context from 3 related meeting notes and 2 GitHub issues. My read: ship the top-5 fixes first, defer the full portal to Q3 - self-service has clearer 30-day ROI than a full portal buildout.

Draft Slack message to #billing-team:

[message body]

Proposed follow-up tasks for Dashboard/tasks.md:

  1. Write spec for top-5 complaint fixes - P2, due 2026-04-28
  2. Book Q3 roadmap review for the portal scope - P3

Add these? (Y / N / pick numbers)

Notes

  • Always cite sources (meeting notes, GitHub issues).
  • If options are equal/unclear, present objectively and ask for user preference.
  • Leave the "Decision" section empty if not immediately clear.
  • If the decision is urgent, propose tasks with P2 priority.

Download now (ZIP)

  • Other versions16 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 16

    1. chrisalehman/bionic★ 9same name
    2. mhxie/Atelier★ 4same name
    3. lulufoo/lulu-workflow★ 3same name
    4. roethlar/AgentGovernanceBootstrap★ 2same name
    5. Tamircohen28/tamirs-superpowers★ 2same name
    6. yacb2/aidex★ 2same name
    7. cerebrocybersolutions/libro★ 1same name
    8. Jsnnmsc/10000x-engineer★ 1same name
    9. madebypx/PXOS★ 1same name
    10. mauroepce/claude-workspace★ 1same name

    6 more not listed

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • Used alongsideProjects with it also use brief, plan and 2 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.
    • AnthropicSkill

      brief

      Generate contextual briefings for legal work — daily summary, topic research, or incident response. Use when starting your day and need a scan of legal-relevant items across email, calendar, and contracts, when researching a specific legal question across internal sources, or when a developing situation (data breach, litigation threat, regulatory inquiry) needs rapid context.

      Also in 3 projects that use this

    • BlockSkill

      plan

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

      Also in 4 projects that use this

    • OpenAISkill

      audit

      Audit or critique a product flow, journey, workflow, funnel, onboarding path, checkout path, settings path, screen, or multi-step product experience by capturing screenshots first, then reporting UX, design, and accessibility findings inline from that evidence. Use Figma only when the user explicitly asks for a board. Use when the user asks to audit, review, critique, inspect, assess, analyze, evaluate, or give feedback on a product experience.

      Also in 3 projects that use this

    • SentrySkill

      review

      Fixture review skill.

      Also in 4 projects that use this

  • In this repository12 other files it gives its agents.

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.