prioritize
Skill0 starsChanged 32 days agoMITView on GitHub
Rank a list of features, initiatives or backlog items with RICE or ICE, with every estimate written down and justified and the arithmetic done by a script rather than by the model. Use when the user asks to prioritise, rank, score, compare options, build a roadmap order, or decide what to do first.
20 other projects use a version of this.
Adopted by
Most recently taken up by
- 5hirish/ducttheir own version, first seen Nov 8, 2026
- eggs-gd/career-spacetheir own version, first seen Nov 8, 2026
- raphaeltm/simple-agent-managertheir own version, first seen Nov 7, 2026
- zanellig/skillstheir own version, first seen Oct 29, 2026
- mohitkhandelwal242/ai-pm-operatortheir own version, first seen Oct 20, 2026
- andreaskelm/pm-braintheir own version, first seen Oct 17, 2026
Used with
Projects with it also use decision-doc, weekly-plan and 9 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.
MehdibargachSkilldecision-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-dytkoSkillweekly-plan
Plan weekly P-Tasks with in-repo task triage and overplanning challenge
Also in 3 projects that use this
nbirknerSkillinterview-guide
Use when preparing to conduct user research interviews and needing structured JTBD-based questions. Also use when starting a new discovery research effort or when existing interview questions feel generic. Keywords: interview guide, user research questions, discovery interview, JTBD questions, research script.
Also in 3 projects that use this
launchapp-devSkilljourney-map
Create an end-to-end user journey map with stages, touchpoints, emotions, pain points, and opportunity areas. Use when mapping the full user experience for a product, feature, or service.
Also in 3 projects that use this
arezousSkillstatus-update
Write a status update for a project or initiative. Matches the style to the audience.
Also in 3 projects that use this
GitHubSkillprd
Generate high-quality Product Requirements Documents (PRDs) for software systems and AI-powered features. Includes executive summaries, user stories, technical specifications, and risk analysis.
Also in 4 projects that use this
Other versions20 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 20
- gitkraken/vscode-gitlens★ 10ksame name
- suboss87/FDEOps★ 940same name
- menkesu/awesome-pm-skills★ 441same name
- andreaskelm/pm-brain★ 235same name
- kv0906/pm-kit★ 138same name
- Mehdibargach/claude-code-pm-skills★ 97same name
- raphaeltm/simple-agent-manager★ 69same name
- arezous/pm-pilot★ 20same name
- 5hirish/duct★ 8same name
- eggs-gd/career-space★ 4same name
10 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.
In this repository7 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- acceptance-criteriaSkill
- review-specSkill
- slice-storiesSkill
- stakeholder-updateSkill
- write-prdSkill
The file
We split this skill into the rules it gives an agent
4 rules. 0 are common, 2 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 19 edited versions we read keep these.
2
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
- Distinctive: line 14
RICE: when you can estimate how many users an item reaches in a fixed period.
- Distinctive: line 17
Use one method for the whole list.
- Very specific: line 21
Start from pm-skills template prioritize.
- Very specific: line 35
Run pm-skills score <file>.
“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.
Files
Prioritise with RICE or ICE
Scores are a way to make assumptions visible and arguable, not an oracle. The value is in the written reasons, and in noticing when two options are too close to call.
CLI: node "${CLAUDE_PLUGIN_ROOT}/cli/pm-skills.mjs" (or ../../cli/pm-skills.mjs relative to this file). Below, pm-skills. Never compute scores yourself. Always run pm-skills score.
1. Choose the method
- RICE when you can estimate how many users an item reaches in a fixed period. Score = Reach × Impact × Confidence ÷ Effort.
- ICE for early ideas or growth experiments where reach is unknowable. Score = Impact × Confidence × Ease, each 1 to 10.
Use one method for the whole list. Ask the user which period reach is measured over (for example "users per quarter") and in which unit effort is measured (for example person-weeks), and use the same for every row.
2. Estimate each input, with a reason
Start from pm-skills template prioritize. For every item fill in the inputs and a one-line reason for each. Use the scales strictly:
| Input | Scale |
| Reach (RICE) | number of users or events in the chosen period, from data where possible |
| Impact (RICE) | 3 massive, 2 high, 1 medium, 0.5 low, 0.25 minimal |
| Confidence (RICE) | 100% with data, 80% with some evidence, 50% gut feel. Above 80% needs data |
| Effort (RICE) | person-weeks or person-months, from the people doing the work if possible |
| Impact, Confidence, Ease (ICE) | 1 to 10 each |
Where you are guessing, say so and lower confidence. Do not let the user's favourite item get a generous score that you would not give the others.
3. Score
Run pm-skills score <file>. It prints the ranked table, rejects inputs off the scale, flags confidence above 80% and lists pairs within 10% of each other. Add --write to put Score and Rank columns into the user's table.
4. Present the result
- The ranked table from the script, unchanged.
- Close calls: for each pair the script lists, say what would decide between them (strategy, dependencies, timing), not which number is bigger.
- Sensitivity: name the one or two estimates that, if wrong, would change the top three. Those are the ones worth validating first.
- What the score ignores: dependencies, deadlines, strategic bets, risk reduction. Point out where any of these should override the ranking.
Let the user make the call. Your job is to make the trade-offs visible.
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
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.