agentleFS
Sign inStart free
rpraharajrpraharaj/ai-sdlc/skills/prioritize-backlog/SKILL.md

prioritize-backlog

Skill0 starsChanged 17 days agoMITView on GitHub

Rank backlog items from written evidence only, and list what you rejected. Use when the user asks to prioritize, rank a backlog, apply RICE or WSJF, or /prioritize-backlog. Do not invent scores. Do not write product code.

2 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 4 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Do not invent reach, impact, confidence, or job size.

    line 19
  2. Distinctive:

    If an item has no artifact, drop it to unscored — do not guess.

    line 35
  3. Very specific:

    Read AGENTS.md if present.

    line 44
  4. Distinctive:

    Read each named artifact. Copy numbers only if they appear there or the user typed them this session.

    line 45
  5. Distinctive:

    Do not write tracker tickets unless the user asked and a tracker CLI already exists.

    line 50

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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 backlog

Produce an ordered list plus rejects, scored only from artifacts you can open. This is not a PRD (write-prd) and not a status report.

Do not invent reach, impact, confidence, or job size.

Is this the right skill?

SignalDo this instead
Problem not written downwrite-opportunity / write-prd
Raw interviewssynthesize-discovery first
Scope change to a committed planassess-change
Tickets for an agreed howwrite-dev-tasks

Required inputs

  • Two or more candidate items, each with a path (opportunity, PRD, synthesis insight, requirement)
  • The scoring fields the user wants, or default: reach / impact / confidence / effort only if those numbers exist in the artifacts or the user supplies them

If an item has no artifact, drop it to unscored — do not guess.

Human decisions (do not invent)

  • Final rank if scores tie
  • What “now” vs “later” means for this increment

Procedure

  1. Read AGENTS.md if present. Read context/glossary.md if present.
  2. Read each named artifact. Copy numbers only if they appear there or the user typed them this session.
  3. Find the home: docs/discover/backlog-YYYY-MM-DD.md (or the existing discover home).
  4. Open references/backlog-template.md. Copy every heading. Write n/a when unused.
  5. Score only rows with complete inputs. Missing input → unscored + reason.
  6. Rejected is required: items out of evidence, duplicates, or user-dropped.
  7. Do not write tracker tickets unless the user asked and a tracker CLI already exists. Even then, link to this file.

Output

  • Path: docs/discover/backlog-YYYY-MM-DD.md
  • Template: references/backlog-template.md

Quality bar

  • Every ranked row cites an artifact path
  • No invented score field
  • Rejected or unscored list is non-empty or explicitly none
  • Unused headings are n/a

Done

  1. Path
  2. Ranked count / unscored count / rejected count
  3. Next skill: write-prd or write-dev-tasks for item 1 — or stop — need user

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.

Check your setup, free