Sundae Bar Logo
Past Challenge
Meeting Preparation Skill
SBC15

Meeting Preparation Skill

Overview

Given a meeting invite — including title, attendee names and roles, stated objective, and meeting length, with optional prior notes or open action items — the agent must produce two structured artifacts in a single response: a time-boxed agenda and a one-page attendee-segmented pre-read, followed by a brief organizer notes section.

Your submission is a single SKILL.md file that teaches a fixed base agent how to prepare these artifacts reliably across any meeting scenario it encounters. The skill defines the reasoning procedure the agent must follow — from intake through classification, drafting, and risk-flagging — so that the agent can handle unfamiliar meetings, not just the ones it has seen.

Strong skills teach the agent to recognise the meeting type from objective and attendee signals, apply the right structural approach for that type, proportionally time-box agenda items, segment the pre-read by role group rather than individual names, and surface operational risks before returning any output. They name the failure modes the agent must avoid and explain why each step of the procedure matters.

Weak skills hand the agent a fixed template to fill in or a list of sample outputs to imitate. These break immediately when surface details change — different industries, unfamiliar role combinations, ambiguous objectives, or missing inputs. A skill built to memorise specific scenarios will not hold up as challenges evolve.

You submit a SKILL.md file. A fixed base agent loads it and answers all 10 scenarios with it, then returns a scored breakdown. The submission that holds the top of the leaderboard accrues on-chain emissions for as long as it stays first.

We are looking for skills that demonstrate good design and help the agent perform like a capable practitioner in this domain.

Requirements (10 Tests)

Your skill is tested across 7 capability types, with 10 scenarios in total. Every submission is evaluated against all 10 scenarios — there is no sampling, so consistent quality across every capability type counts.

CategoryOverviewTest cases
Type A — Operational risk flaggingTests whether the agent proactively identifies and surfaces risks that could undermine meeting effectiveness before returning its artifacts. The skill must teach the agent to check for absent decision-makers, mismatches between the stated objective and who is in the room, overpacked agendas, and unresolved prior action items — and to consolidate these into an organizer notes section every time.1
Type B — Attendee-segmented pre-read draftingTests whether the agent can produce a complete, structured one-page pre-read that serves distinct role groups rather than a generic audience. The skill must teach the agent to open with a TL;DR and shared context, write per-role-segment sections, and close each segment with a specific and actionable call-to-action rather than a restatement of background information.1
Type C — Role-group segmentation judgmentTests whether the agent exercises judgment about when attendees with similar roles should share a pre-read segment versus receive separate ones. The skill must teach the agent to group by functional role and decision authority rather than by individual name, and to articulate the reasoning behind its segmentation choices.1
Type D — Meeting-type-differentiated agenda structureTests whether the agent adapts its agenda structure meaningfully to the type of meeting, rather than applying one universal format. The skill must teach the agent that a decision meeting should concentrate time on options and tradeoffs — not serial status updates — and show how structure, purpose labels, and time allocation should shift across meeting types when prior context is also present.1
Type E — Input verification and clarifying questionsTests whether the agent correctly identifies missing required inputs and responds by asking targeted clarifying questions rather than drafting with assumed values. The skill must teach the agent to ask at most two focused questions, explain what is missing and why it matters, and withhold artifact drafting until the minimum viable inputs are confirmed.1
Type F — Meeting-type classificationTests whether the agent can correctly classify a meeting into the appropriate type — including interpersonally nuanced scenarios such as 1-on-1s — using signals embedded in the objective and the attendee list. The skill must teach the agent which signals are diagnostic for each meeting type and how that classification drives all subsequent structural decisions.1
Type G — Prior-context cross-referencingTests whether the agent uses prior meeting notes or open action-item lists to enrich both artifacts rather than treating the meeting in isolation. The skill must teach the agent to surface unresolved items, overdue actions, and deferred decisions explicitly in the agenda, and to reflect relevant carry-over context in the pre-read.1

Surface details such as attendee names, meeting titles, industries, and specific figures rotate across scenario variants, while the underlying capability being tested remains the same.

Datasets

Available Datasets

When you submit, we run your SKILL.md through a standardised base agent provided by sundae_bar. The base agent is the same for every submission and is not supplied by you. It receives the challenge's test scenarios one at a time, calls the load_skill tool to read your skill, and follows it to answer each scenario.

Same base agent, same tests, only the submitted skill changes. Scores therefore reflect the quality of your skill, not agent configuration: the agent's answers are only as good as the procedure your skill teaches.

Graders then score each answer for output quality, correct skill use, and gaming behavior, and the per-scenario scores are averaged into your challenge score.

Important: the base-agent harness is fixed at evaluation time and its available tools are load_skill. You submit only a SKILL.md; you cannot supply your own agent, add tools, or alter the base agent's configuration.

Tip: write your skill as though you are onboarding a capable new hire who needs a procedure, not scripting a chatbot.

Evaluation Criteria

Each scenario is graded by an LLM judge. Final scores combine two graders and a set of deterministic penalties.

CriteriaWeight

Skill use

An LLM judge evaluates whether the agent's output actually followed the procedures your skill teaches, rather than freelancing or pretending to use the skill.

50 %

Scenario quality

An LLM judge evaluates how well each output meets the per-type quality bar, independent of whether your skill was followed. A reference good output anchors the judge's sense of the quality bar.

50 %

Each scenario is scored on the quality of the agent's output. Certain moves — such as drafting artifacts when required inputs are missing, omitting the organizer risk notes, or producing a pre-read that treats all attendees as a single undifferentiated audience — carry deterministic penalties that reduce the score regardless of other output quality. Scenario scores aggregate to capability-type averages, which in turn combine into the final challenge score shown on the leaderboard.

Submission

How to submit

1
Login or create a sundaebar.ai account

Create an account and add your Bittensor wallet ID to your profile to earn alpha rewards in the challenge.

2
Review the requirements

Review the reference skills (good, mediocre, gaming) to understand the quality bar and calibration points.

3
Build your skill

Draft your SKILL.md. Focus on teaching procedure rather than providing templates.

4
Test locally

Validate locally using the published dataset variants to sanity-check output quality.

5
Submit via the platform

Submit through the sundae_bar challenge portal by uploading your SKILL.md file.

6
Iterate

Review your scored breakdown and resubmit.

Constraints

Submission format: a single SKILL.md file with YAML frontmatter (name, description) and Markdown body.

Base agent: fixed. Provided by sundae_bar.

Runtime: a fixed base-agent harness loads your SKILL.md and answers all 10 scenarios per submission with it.

Tests per submission: 10 (the full scenario set — no sampling).

Submission limits: 3 submissions per day. A rolling challenge limit also applies.

Rewards

Emissions accrue on-chain to whichever submission currently holds the top of the leaderboard. There is no fixed per-submission payout: the current leader earns for as long as it stays first.

Time at the top takes all. A strong skill submitted early starts accruing immediately and keeps earning until another submission displaces it. Once you are displaced, accrual stops until you reclaim the top.

Rankings shift as others iterate. Get to the top early, then keep refining your skill to defend the position.

Your SKILL.md is scanned at submission time by a skill integrity gate. The gate checks that your skill teaches procedure rather than encoding scenario-specific content from our evaluation pool.

A skill that fails the integrity gate scores 0 for the submission. The gate runs deterministically and reports its finding as part of your results. This is how the evaluation framework stays credible: a high score should reflect a skill that genuinely teaches procedure, not one that memorised our test set.