agentleFS
CharleneTStrainCharleneTStrain/product-ops-skills/skills/raci-builder/SKILL.md

raci-builder

Skill0 starsChanged 18 days agoMITView on GitHub

Build a RACI chart that makes clear, for each task or decision in a project, who does the work, who signs off, who gives input, and who just needs to know. Use when someone asks for a RACI, a responsibility matrix, "who owns what," role clarity for a project or launch, or when ownership keeps getting dropped between teams.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    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:

    Use only what the source says or what the person confirms.

    line 37

≈ “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

RACI builder

A RACI exists to end the question "wait, whose job was that?" It only works if every row has exactly one person accountable.

Before you start

If .agents/product-ops-context.md exists (or .claude/product-ops-context.md), read it first. Use the team, owners, tools, meetings, and metric definitions it already has, and only ask for what's missing or specific to this task. If it doesn't exist, go ahead with what you're given, and suggest running product-ops-context once so the next skill doesn't have to ask.

The four roles

LetterRoleMeaningHow many per row
RResponsibleDoes the workOne or more
AAccountableMakes the final call and owns the outcomeExactly one
CConsultedGives input before it's done (two-way)As few as possible
IInformedTold after it's done (one-way)As needed

Step 1: List the rows

Rows are tasks or decisions, not people or teams. Pull them from the project plan, launch checklist, or the person's description. Each row starts with a verb: "Approve final pricing," "Write help center article," "Decide launch date."

Aim for 8 to 20 rows. Fewer means the rows are too broad to settle anything; more means it's become a task list.

Step 2: List the columns

Columns are people, by name or by role if names aren't known. Prefer names. A team as a column hides who actually owns it.

Step 3: Fill it in

Use only what the source says or what the person confirms. Where the source is silent, leave the cell blank and list it as an open question. Don't assign accountability on anyone's behalf.

Step 4: Check the chart

Flag every one of these:

  • No A: nobody owns the outcome
  • More than one A: two people think they make the call
  • No R: nobody does the work
  • A with no R anywhere near them: the decider is far from the work; check they have what they need
  • Too many C's: more than three consulted people on a row slows everything down
  • One person who is A on most rows: a bottleneck
  • A column with no letters: that person doesn't need to be on the project

Output

# RACI — [Project] — [Date]

| Task or decision | [Name] | [Name] | [Name] | [Name] |
|---|---|---|---|---|
| [Verb + object] | A | R | C | I |

## Flags
- [Row]: [problem] — Suggested fix: [one line]

## Open questions
- [Row]: who is Accountable? Needs decision from: [name]

Suggest fixes, but mark them as suggestions. The people on the chart agree to it, not the person who drew it.

Related skills

  • decision-log — record decisions the chart says who makes
  • cross-team-dependency-map — see where ownership gaps cause waiting
  • process-documentation — put owners into the SOP

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.