agentleFS
CharleneTStrainCharleneTStrain/product-ops-skills/skills/cross-team-dependency-map/SKILL.md

cross-team-dependency-map

Skill0 starsChanged 17 days agoMITView on GitHub

Map which teams or people are waiting on which others across a project, launch, or quarter — what's needed, by when, and what's at risk — so blockers surface before they slip the date. Use when someone asks who's blocked, wants a dependency map or tracker, is planning a cross-team launch or quarter, or says work keeps stalling between teams.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    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:

    Write the table, then offer a simple visual.

    line 42
  2. Distinctive:

    Every "Needs attention" row ends with a next step and a person, usually "Confirm date with [provider]."

    line 65

≈ “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

Cross-team dependency map

Most slipped dates aren't one team being slow. They're one team waiting on another that didn't know it was being waited on. This map makes every wait visible and owned.

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.

Step 1: List every dependency

Pull from the project plan, notes, tickets, or what the person describes. A dependency is one specific thing one party needs from another.

#Needs (team / person)Waiting on (team / person)What exactlyNeeded byStatusAgreed?

Rules:

  • "What exactly" is a deliverable, not a topic: "Final API spec for webhooks," not "API stuff."
  • Name a person on both sides whenever the source allows.
  • Agreed? is Yes only if the source shows the providing side accepted the ask and the date. Otherwise No or Unknown. This column catches most problems.

Status is one of: Delivered, On track, At risk, Late, Not started, Unknown.

Step 2: Find the risks

Flag:

  • Unagreed: the provider doesn't know or hasn't confirmed
  • Late or at risk: needed-by date is close or passed
  • Chains: A waits on B, who waits on C. The whole chain is only as fast as its slowest link; list the chain in order
  • Hubs: one team or person that many others are waiting on
  • Circular: two teams each waiting on the other
  • No date: needed but nobody said when

Step 3: Show it

Write the table, then offer a simple visual. A swim lane diagram (one lane per team, arrows for each dependency) or a flow diagram of the chains works well. Mark agreed dependencies solid and unagreed ones dashed.

Output

# Dependency map — [Project] — [Date]

## Needs attention
| # | Needs | Waiting on | What | By | Problem | Next step |

## Chains
- [Team A] → [Team B] → [Team C]: [deliverable], earliest finish [date if known]

## Hubs
- [Team or person]: [N] teams waiting

## On track
[Short table]

## Missing information
- #[N]: [what's unknown] — ask [name]

Every "Needs attention" row ends with a next step and a person, usually "Confirm date with [provider]."

Related skills

  • raci-builder — make ownership clear on each dependency
  • launch-readiness-checklist — check dependencies before launch
  • ritual-calendar — decide where blockers get reviewed

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.