agentsclimarketplace
Sign in

Iterate refinement notes

Skill product-on-purpose/pm-skills/skills/iterate-refinement-notes

Documents backlog refinement session outcomes including stories refined, estimates, questions raised, and decisions made. Use during or after refinement to capture the results and share with absent team members.From its SKILL.md

Install
npx -y skills add product-on-purpose/pm-skills --skill iterate-refinement-notes

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

What its file declares

Copied from the file, not written here

The file declares its own license as Apache-2.0. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

3.3 KB, 599 tokens by cl100k_base, as published. Nobody here has run it

<!-- PM-Skills | https://github.com/product-on-purpose/pm-skills | Apache 2.0 -->

Refinement Notes

Refinement notes capture the outcomes of backlog refinement (grooming) sessions.what was discussed, what was estimated, and what decisions were made. They serve as a quick reference for team members who missed the session and a historical record of how stories evolved from idea to ready-for-sprint.

When to Use

  • During refinement sessions to capture decisions in real-time
  • After refinement to share outcomes with absent team members
  • When onboarding new team members to explain backlog context
  • Before sprint planning to review what's been refined
  • When stories need re-refinement due to time elapsed

When NOT to Use

  • You need the stories themselves written -> use deliver-user-stories
  • You need a general meeting summary, not a backlog-refinement record -> use foundation-meeting-recap
  • You are running the retrospective ceremony -> use iterate-retrospective
  • Refined stories need their failure scenarios enumerated -> use deliver-edge-cases

Instructions

When asked to document refinement notes, follow these steps:

  1. Record Session Metadata Note the date, attendees, and duration. This helps track who was part of decisions and when discussions happened.

  2. List Stories Discussed For each story, capture the outcome: estimated points, refined status, key discussion points, and any modifications made to the original scope.

  3. Document Questions Raised Questions that couldn't be answered in the session need owners and due dates. Don't let them disappear.they often block sprint planning.

  4. Capture Decisions Made Record any scope decisions, technical approaches agreed upon, or priority changes. These decisions are valuable context that gets lost without documentation.

  5. Note Action Items Any follow-up work needed before stories are sprint-ready: mockups to create, technical spikes to run, stakeholders to consult.

  6. Flag Blocked Stories Clearly identify stories that can't proceed until blockers are resolved. Include what the blocker is and who owns resolution.

  7. Plan Next Session Note what should be refined next and any preparation needed.

Output Format

Use the template in references/TEMPLATE.md to structure the output. Complete notes fill every template section: Session Info; Summary; Stories Refined; Stories Summary Table; Questions Raised; Decisions Made; Action Items; Blocked Stories; Parking Lot; and Next Session.

Quality Checklist

Before finalizing, verify:

  • All discussed stories have outcomes recorded
  • Open questions have owners assigned
  • Decisions are captured with enough context
  • Blocked stories are clearly flagged
  • A reader who missed the session can tell each story's outcome and what happens next without asking

Examples

See references/EXAMPLE.md for a completed example.

What ships with it: 4 files

15.5 KB alongside SKILL.md

evals/

references/

Gives 0 of the 12 instructions most note taking skills give in 599 tokens

Counted across 632 of the 857 authors here whose files we hold, read 2026-09-06

  • Use standard Markdown links for external URLsin 16 of 632, across 8 files
  • Use wikilinks for internal vault connectionsin 15 of 632, across 7 files
  • Embed content using the exclamation mark prefixin 14 of 632, across 6 files
  • Ask for clarification if the user request is ambiguousin 13 of 632
  • Add frontmatter properties at the top of the filein 12 of 632, across 4 files
  • Verify note renders correctly in reading viewin 12 of 632, across 4 files
  • Include a visual element on every slidein 11 of 632, across 5 files
  • Left-align body text and listsin 11 of 632, across 5 files
  • Maintain 0.5 inch minimum marginsin 11 of 632, across 5 files
  • Wrap formulas containing double quotes in single quotesin 11 of 632, across 5 files
  • Repeat one distinctive visual motif across all slidesin 10 of 632, across 4 files
  • Use 36pt or larger for slide titlesin 10 of 632, across 4 files

Said here and by no other author read

  • Record session date attendees and duration
  • List estimated points and refined status for stories
  • Capture key discussion points and scope modifications
  • Assign owners and due dates to open questions
  • Record scope decisions and technical approaches
  • Note follow-up work as action items

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 325,949. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.