agentleFS
nickmerichnickmerich/artist-led-events-skills/skills/artist-fit-and-concept/SKILL.md

artist-fit-and-concept

Skill0 starsChanged 25 days agoMITView on GitHub

Evaluates whether an artist and an athletic event concept belong together before anyone spends money, using eligibility checks and a five-question evidence scorecard with routing rules. Use for "should we do an event with [artist]", "score this artist", "which artist should we pitch", "is this concept authentic", or ranking a list of artist prospects. Produces a scored evidence packet and a next stage, never a launch approval.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    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:

    If an item fails, the right move is usually a smaller format (a private run with the artist and 15 club members, a one-week fan challenge), …

    line 22
  2. Very specific:

    Use assets/evidence-packet.md.

    line 26
  3. Distinctive:

    All five Supported → Final Review by the human decision-maker.

    line 49
  4. Distinctive:

    Write the concept in one sentence a fan would repeat: [Artist] is [doing the hard thing] with [who], in [place], because [true reason].

    line 55

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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

Artist Fit and Concept

The best artist-led events feel like the artist was going to do this anyway and invited you. The worst feel like a brand deal with a finish line. This skill tells them apart with evidence.

Step 1: Eligibility (pass/fail, before scoring)

For a produced public event (not a small private pilot), the artist should show:

  1. Current activity: releasing, touring, or actively building an audience now.
  2. A real practice: recent public evidence they do the activity or something hard and physical regularly. Posts, interviews, race results, gym clips.
  3. Local pull: evidence they can bring people in person in this city. Past show attendance, local fan groups, a hometown story. Set the bar to the format: for a produced 5K, aim for evidence of at least 50 people who'd come because of the artist.
  4. A reachable decision-maker: artist, manager, or agent who can say yes.

If an item fails, the right move is usually a smaller format (a private run with the artist and 15 club members, a one-week fan challenge), not lowering the bar. Say so.

Step 2: Build the evidence packet

Use assets/evidence-packet.md. Every claim gets a source link or a label (VERIFIED, REPORTED, ASSUMPTION, UNKNOWN).

Step 3: Score five questions

Each question is scored independently: Supported (2), Partial (1), Not Met (0), Unknown (unscored). Unknown is never treated as a pass.

#QuestionSupported looks like
Q1Authenticity: Does evidence show this reflects the artist's current practice or a real personal goal?Multiple recent, unprompted posts or statements about the activity.
Q2Shared participation: Can fans take part alongside the artist, at their own level, and meet each other?Format has scaled/walk/no-equipment options and a reason fans talk to each other, not just watch.
Q3Artist commitment: Has the artist or their team agreed to a specific role in writing?Email or message from the decision-maker naming date, role, and time.
Q4Demand evidence: Does observed demand support the headcount target?Waitlist signups, poll responses, past event turnout, or a soft RSVP test at 1.5x the target.
Q5Production readiness: Is there an operating plan and budget a producer would sign off on?Format brief, budget with break-even, venue path, insurance path, owner named.

Step 4: Route

Apply in order. First match wins.

  1. Any Not Met → Hold / Redesign. Name the failing question and the redesign that could fix it.
  2. Q1 Unknown → Research. Find authenticity evidence before contacting anyone.
  3. Q1 Partial or Q3 Unknown → Discovery. A short call or message with the artist team.
  4. Q2 not Supported, Q3 Partial, or Q5 not Supported → Pilot Design. Work the format, deal, or plan.
  5. Q1, Q2, Q3, Q5 Supported and Q4 Partial/Unknown → Demand Validation. Run a soft RSVP or waitlist test.
  6. All five Supported → Final Review by the human decision-maker. This is not launch approval.

The routing is deterministic. If you have a script environment, compute it in code rather than by judgment.

Step 5: Concept line

Write the concept in one sentence a fan would repeat: [Artist] is [doing the hard thing] with [who], in [place], because [true reason]. If the "because" isn't true and sourced, go back to Q1.

Discovery call questions (Q1, Q3)

  • What do you actually do to stay moving right now? How often?
  • Have you ever done something like this with fans? What did you like or hate about it?
  • What would make this feel like yours and not a brand activation?
  • How much time can you give on the day? Before the day?
  • Any brand deals, exclusivities, or sensitivities we need to know? (Feeds the conflict check.)
  • Who signs off on announcements and your name and likeness?

Red flags

  • The artist's only connection to the sport is a sponsor's request.
  • The plan only works if the artist does a meet-and-greet line.
  • The headcount target came from follower count.
  • "We'll figure out the venue after we announce."

Output

A packet with: eligibility results, the five scores with evidence, the route, the concept line, and one next action with an owner.

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.