Sundae Bar Logo
Past Challenge
Sales Pipeline Coaching & Anomaly Detection Skill
SBC20

Sales Pipeline Coaching & Anomaly Detection Skill

Overview

This skill teaches the agent to review a sales pipeline export, flag deals that are stalled or at risk, and produce a structured coaching brief that a sales-ops leader could act on immediately.

Given a tabular pipeline export — with fields such as deal name, stage, ARR, close date, last-activity date, and rep owner — the agent produces two artifacts: a per-deal coaching table sorted by risk and ARR, and a concise pipeline anomaly brief covering coverage gaps, sandbagging candidates, and forecast-category mismatches.

The submission is a single SKILL.md file. Strong skills teach the agent a repeatable reasoning procedure it can apply to any pipeline snapshot — recognising deal health signals, working through a defined sequence of checks, and generating specific next actions grounded in the actual deal data. Weak skills provide fill-in-the-blank templates or pre-written diagnoses that collapse the moment rep names, stage labels, ARR figures, or threshold rules 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 8 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 (8 Tests)

Your skill is tested across three capability types, with 8 scenarios in total. Every submission is evaluated against all 8 scenarios — there is no sampling, so consistent quality across every capability type counts.

CategoryOverviewTest cases
Type A — Full Reasoning Chain IntegrationThis type tests whether the agent can apply a complete, sequential deal-health diagnostic across a realistic mixed pipeline — moving through time-in-stage, activity gap, stage/close-date compatibility, and next-step quality in order, and citing each check in the diagnosis column of the coaching table. The skill must teach the agent to follow this four-step path as a discipline, not skip to conclusions, and to surface its reasoning transparently so a sales-ops reviewer can audit every call.1
Type B — Next-Action Quality & Threshold HandlingThis type tests whether the agent produces next-action recommendations that are specific and executable — grounded in the actual deal record fields and including a concrete deadline or escalation path — and whether it correctly applies non-default thresholds when the user overrides a rule (such as a different sandbagging window). The skill must teach the agent to adapt its analysis to caller-specified rules, state any threshold assumptions at the top of the output, and avoid generic coaching language that would apply to any deal regardless of its specifics.1
Type C — Data Integrity & Anomaly FaithfulnessThis type tests whether the agent remains faithful to difficult or incomplete pipeline data — correctly identifying sandbagging candidates, coverage gaps, and Commit vs. Best-Case mismatches without softening its findings, and handling missing fields by flagging them rather than inferring values. The skill must teach the agent to treat data-hygiene problems as a risk signal in their own right, to never re-categorise a stalled deal as on-track, and to omit no deal from the coaching table regardless of how unflattering the diagnosis.1

Surface details — rep names, deal names, ARR figures, stage labels, close dates, and quota numbers — rotate across scenario variants, while the underlying pipeline coaching capabilities being tested remain 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 four graders and a set of deterministic penalties.

CriteriaWeight

Response quality

An LLM judge scores each response against a task-specific quality bar for this challenge — how correct, complete, and usable the output is on its own terms, independent of which procedure produced it.

30 %

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.

30 %

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.

30 %

Output originality

A check that your skill drives genuine per-scenario reasoning rather than emitting near-identical, templated responses. Skills that reuse one canned output across scenarios lose credit here.

10 %

Scenarios are scored individually; deterministic penalties apply when the agent makes moves that damage output quality — such as silently assuming a reference date, omitting deals, inferring missing field values rather than flagging them, or producing next actions that are too generic to act on. Individual scenario scores roll up to capability-type averages, which 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 8 scenarios per submission with it.

Tests per submission: 8 (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.