agentleFS
sebssebs/rewelo/.claude/skills/intake/SKILL.md

intake

Skill2 starsChanged 50 days agoMITView on GitHub

Conduct a stakeholder interview to create scored backlog tickets

34 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use plan, triage and 7 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.
  • BlockSkill

    plan

    Draft a TDD, PRD, or lightweight plan in the conversation without committing it.

    Also in 4 projects that use this

  • Google CloudSkill

    triage

    Gather context on a change or bug and plan the implementation.

    Also in 4 projects that use this

  • AWSSkill

    retro

    Conduct a retrospective on a coding session.

    Also in 4 projects that use this

  • Microsoft AzureSkill

    build

    Build the TypeSpec Rust emitter from source. Run this after cloning the repo, after pulling changes, or when TypeScript source files have been modified.

    Also in 3 projects that use this

  • VercelSkill

    deploy

    Deploy applications to Vercel. Use when the user says "deploy", "deploy to Vercel", "push to production", "deploy my app", or "go live".

    Also in 3 projects that use this

  • Microsoft AzureSkill

    verify

    End-to-end app testing pipeline for browser-based web apps on cloud browsers via Azure Playwright Workspaces: verify the live app, author tests for working flows, heal failing tests, then re-run with video and produce one consolidated report. Three phases (app verification, test authoring, test healing) plus a scoped final sanity run; each phase emits a sub-report. Use when asked to "verify my app", "make sure my app works and has good test coverage", "do a full QA pass", "add tests where I'm missing coverage", "fix failing tests and add new ones", "smoke test before deploy", "QA my deployment", or any combined verify-and-test ask. Requires Azure CLI (`az login`) and a Playwright Workspace resource ID — bootstraps configs on first invocation. Browser-based web apps with Playwright only — not for unit/API tests, native mobile/desktop, load/perf, or full accessibility audits.

    Also in 4 projects that use this

The file

We split this skill into the rules it gives an agent

11 rules. 0 are common, 8 are distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 33 edited versions we read keep these.

  • 8

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Check if the project exists via project_list.

    line 14
  2. Distinctive:

    Ask: "What do you need? Describe the feature or change in one sentence." Create a clear, concise ticket title from their answer.

    line 21
  3. Distinctive:

    Create a clear, concise ticket title from their answer.

    line 22
  4. Distinctive:

    Ask: "How valuable is this if we build it?" Anchor: 1 = nice-to-have, 5 = clearly useful, 13 = critical, 21 = existential

    line 27
  5. Distinctive:

    Ask: "What happens if we don't build it?" Anchor: 1 = nothing, 5 = inconvenience, 13 = significant loss, 21 = business failure

    line 31
  6. Distinctive:

    Ask: "How much effort do you think this takes?" Anchor: 1 = hours, 3 = days, 8 = weeks, 21 = months

    line 35
  7. Distinctive:

    Ask: "How uncertain or complex is this?" Anchor: 1 = well-understood, 5 = some unknowns, 13 = major unknowns, 21 = research project

    line 39
  8. Distinctive:

    Ask: "Any labels? (e.g. feature:checkout, team:platform)"

    line 43
  9. Very specific:

    Create the ticket using ticket_create

    line 47
  10. Distinctive:

    Ask: "Next story, or are we done?"

    line 50
  11. Very specific:

    When done, show all created tickets in a priority-ranked table, in the order and with the weighted priorities calc_priority gives them.

    line 54

“Common” is measured: kept by at least 6 in 10 of the 33 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Stakeholder Intake Interview

Conduct a structured interview to capture stories for project $0.

Setup

  1. Check if the project exists via project_list. If not, ask the user if you should create it.

Interview flow

For each story the stakeholder describes, guide them through scoring:

Step 1: Capture the story

Ask: "What do you need? Describe the feature or change in one sentence." Create a clear, concise ticket title from their answer.

Then call suggest_scores with the title (and a description, if there is one). If similar lists a ticket that looks like the same story, ask whether it's a duplicate before going on. Use references in the steps below: name an existing ticket at a score as the anchor ("Login page has benefit 8: is this more or less valuable?"), so the new ticket is scored relative to this backlog rather than in the abstract.

Step 2: Score benefit (1-21, Fibonacci)

Ask: "How valuable is this if we build it?" Anchor: 1 = nice-to-have, 5 = clearly useful, 13 = critical, 21 = existential

Step 3: Score penalty (1-21, Fibonacci)

Ask: "What happens if we don't build it?" Anchor: 1 = nothing, 5 = inconvenience, 13 = significant loss, 21 = business failure

Step 4: Score estimate (1-21, Fibonacci)

Ask: "How much effort do you think this takes?" Anchor: 1 = hours, 3 = days, 8 = weeks, 21 = months

Step 5: Score risk (1-21, Fibonacci)

Ask: "How uncertain or complex is this?" Anchor: 1 = well-understood, 5 = some unknowns, 13 = major unknowns, 21 = research project

Step 6: Tags

Ask: "Any labels? (e.g. feature:checkout, team:platform)"

After each story

  • Create the ticket using ticket_create
  • Tag it state:backlog and any user-provided tags using tag_assign
  • Show a summary: title, scores, and priority. ticket_create returns no priority: take it from calc_priority, which weights the scores with the project's weights, rather than working it out yourself
  • Ask: "Next story, or are we done?"

Wrap-up

When done, show all created tickets in a priority-ranked table, in the order and with the weighted priorities calc_priority gives them.

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.