Sundae Bar Logo
Past Challenge
Sales Pipeline Daily Briefing Skill
SBC19

Sales Pipeline Daily Briefing Skill

Overview

This skill teaches the agent to read a sales rep's open pipeline and daily calendar and produce a structured, prioritised briefing that tells them exactly what to do that day.

Given a snapshot of open deals, calendar meetings, and pending tasks, a good result is a clean markdown briefing with six ordered sections: a one-sentence pipeline health summary, exactly three ranked outbound actions, per-meeting prep notes, remaining high-urgency deals, deals to monitor, and a list of records missing critical fields — nothing more, nothing less.

The submission is a single SKILL.md file. Strong skills teach the agent a repeatable reasoning procedure — how to tier every deal by urgency, how to pick and rank actions, how to separate prep from outbound work, and when to flag incomplete data — so that procedure holds across any pipeline snapshot the agent has never seen before. Weak skills paste in template outputs or memorised action lists that collapse the moment deal names, stages, or dates change.

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 6 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 — Urgency Tier CalibrationThis type tests whether the agent correctly identifies when a proposed Tier A list is implausibly large for a normal day and applies a calibration check to demote marginal deals. The skill must teach the agent to resist urgency inflation by recognising the threshold at which a tier count becomes unreliable and systematically reviewing borderline deals for demotion.1
Type B — Prioritised Action SelectionThis type tests whether the agent selects and ranks exactly three outbound actions from Tier A deals using an ordered set of heuristics rather than intuition or recency bias. The skill must teach the agent to apply those heuristics in sequence — weighing revenue exposure, reversibility of inaction, recipient availability, and effort-to-impact — and produce a ranked list with deal name, a specific action, and a one-line rationale.1
Type C — Missing Data HandlingThis type tests whether the agent correctly routes deals with incomplete triage fields to a dedicated section instead of forcing them into an urgency tier. The skill must teach the agent to treat absent last-activity dates or next-step notes as a data-quality flag and to surface those deals under Needs Record Update without inferring urgency from gaps.1
Type D — Deal Triage ProcedureThis type tests whether the agent applies a defined, ordered set of triage criteria to classify every open deal into an urgency tier before constructing any action queue. The skill must teach the agent to evaluate deals against criteria — meeting proximity, last-activity age, close-date imminence, stage-dwell duration, and rep-noted deadlines — in a consistent sequence, not by feel.1
Type E — Scope Boundary RecognitionThis type tests whether the agent correctly omits Tier C deals from default output and declines out-of-scope requests such as quota rollups, forecast summaries, team hygiene audits, or drafted emails. The skill must teach the agent to recognise when a request falls outside the briefing skill's remit and to say so clearly rather than attempting an answer.1
Type F — Concrete Action SpecificationThis type tests whether the agent produces a single, concrete, one-step next action per Tier A deal using precise action verbs. The skill must teach the agent to identify what one specific thing should happen next for each high-urgency deal and express it unambiguously, avoiding vague or multi-step language that leaves the rep uncertain about what to actually do.1

Surface details — deal names, account names, dollar amounts, close dates, stage labels, and rep context — 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 %

Scenarios are scored individually, and deterministic penalties apply where agent outputs damage briefing quality — for example by misrouting sections, inflating tiers, using vague action language, or producing out-of-scope content. Individual scenario scores aggregate to capability-type averages, which in turn roll up to the overall 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.