agentleFS
Sign inStart free
ai-analyst-labai-analyst-lab/interview-prep-with-ai/.claude/skills/kickoff/SKILL.md

kickoff

Skill9 starsChanged 46 days agoMITView on GitHub

Build the candidate's experience database (story cards, numbers card, coverage map, story matrix, gaps) from a live one-question-at-a-time conversation or from talk-through transcripts in me/raw/. Use for /kickoff and whenever the coverage map shows a gap to fill.

31 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use standup, grill and 3 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.
  • AnthropicSkill

    standup

    Generate a standup update from recent activity. Use when preparing for daily standup, summarizing yesterday's commits and PRs and ticket moves, formatting work into yesterday/today/blockers, or structuring a few rough notes into a shareable update.

    Also in 3 projects that use this

  • renatorozasSkill

    grill

    Adversarial code review. Don't let me ship until the changes pass your scrutiny.

    Also in 3 projects that use this

  • AnthropicSkill

    status

    Case status summary by audience — client-facing (plain language), internal (for the professor), or court-ready (formal caption format per local rules). Same facts, different framing and depth. Use when a student needs to update the client, brief the professor, or prepare a court status report.

    Also in 3 projects that use this

  • MicrosoftSkill

    handoff

    Compact the current conversation into a handoff document for another agent to pick up.

    Also in 5 projects that use this

  • SentrySkill

    review

    Fixture review skill.

    Also in 4 projects that use this

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 3 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 24 edited versions we read keep these.

  • 3

    Distinctive

    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:

    Ask ONE question at a time.

    line 17
  2. Distinctive:

    Don't score, coach, or correct during the kickoff.

    line 19
  3. Very specific:

    Read me/raw/*. Treat it as private: don't quote long passages back.

    line 23
  4. Distinctive:

    Use only facts the candidate gave.

    line 38

“Common” is measured: kept by at least 6 in 10 of the 24 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

Kickoff: build the experience database

People recall more and undersell less when they talk casually. Your job is to draw the stories out, then do the structuring yourself.

Sources

  • Question guides: kickoff/session-1-work-and-scope.md through kickoff/session-5-managers.md (session 5 only for managers)
  • Live mode rules: kickoff/live-kickoff-prompt.md
  • Extraction rules and output format: kickoff/extraction-prompt.md
  • Worked example: examples/priya-kickoff-transcript.md to examples/priya-experience-db.md

Live mode

  1. Ask ONE question at a time. Wait.
  2. Relaxed tone. Follow up on anything vague or missing a number: "roughly how many?", "what did you do yourself?", "what changed after that?"
  3. Don't score, coach, or correct during the kickoff.
  4. Respect "pause", "next area", and "build it".

Extract mode

  1. Read me/raw/*. Treat it as private: don't quote long passages back.
  2. Apply kickoff/extraction-prompt.md exactly.

Output files

FileContents
me/experience-db.mdStory cards: Title, Situation, What I did, Result, Headline, Answers questions like, Likely follow-ups, Undersold (if any)
me/numbers-card.md8 to 12 numbers with one line of context
me/coverage-map.mdCommon questions per round, Strong / Thin / Missing, with the covering story
me/story-matrix.mdStories as rows, question themes as columns
me/gaps.mdEvery [NEED NUMBER] and [NEED DETAIL], plus follow-up questions, most important first

Merge into existing files. Never delete the candidate's words.

Rules

  • Use only facts the candidate gave. Never invent a project, number, title, team size, or result.
  • Missing facts are [NEED NUMBER] or [NEED DETAIL]. Anything you composed is marked (suggested).
  • Flag underselling ("just", "only", "helped with", "small project") and show the stronger, still-true version.
  • Remind the candidate to use ranges for confidential numbers.
  • No em dashes.
  • End with the 3 biggest gaps and offer to ask the first follow-up.

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