Strategic Account Expansion Skill
Overview
This skill teaches the agent to analyse an existing customer account, identify where untapped product opportunities exist, and produce the structured artifacts an account manager needs to pursue expansion.
Given a structured account block — covering product footprint, usage signals, stakeholder map, and related data — the agent should produce a Whitespace Opportunity Brief that ranks expansion opportunities by evidence, and a Mutual Action Plan that turns the top-ranked opportunity into a time-boxed, jointly owned execution path. When requested, the agent also produces a concise executive-buyer summary leading with business outcomes.
The submission is a single SKILL.md file. Strong skills teach the agent a repeatable reasoning procedure: how to read account signals, build a coverage matrix, rank opportunities on two axes, anchor every claim to a named input record, and structure a MAP to fit the actual deal shape. Weak skills supply templates or pre-filled examples that collapse the moment account details 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 four 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.
| Category | Overview | Test cases |
|---|---|---|
| Type A — Deal Shape Calibration | This type tests whether the agent scales the Mutual Action Plan appropriately to the size and complexity of the recommended opportunity. The skill must teach the agent to read deal signals — ARR impact, stakeholder count, implementation complexity — and translate them into a milestone count and timeline that fits the deal, neither under-engineering a large expansion nor padding a simple add-on. | 1–2 |
| Type B — Full Brief, MAP, and Executive Summary | This type tests the agent's ability to produce all three required artifacts in a single response: the Whitespace Opportunity Brief, the Mutual Action Plan, and the executive-buyer summary. The skill must teach the agent to lead the executive summary with the customer's measurable business outcome and quantified impact, stripping any vendor-internal framing, while keeping the Brief and MAP structurally complete. | 1–2 |
| Type C — Stakeholder-Constrained Expansion | This type tests whether the agent ranks opportunities correctly when the stakeholder map is a binding constraint — that is, when some expansions are high in revenue potential but low in accessibility due to weak or absent relationships. The skill must teach the agent to apply both axes (revenue potential and likelihood/accessibility) simultaneously, using only named stakeholders and relationship signals present in the input, and to reflect stakeholder constraints explicitly in its tier assignments and rationale. | 1–2 |
| Type D — Whitespace Analysis | This type tests the core whitespace reasoning procedure in isolation: establishing the factual footprint baseline, building the coverage matrix, producing ranked tiers with evidence-grounded rationale, and generating a Needs Discovery list for gaps that lack sufficient signal. The skill must teach the agent to apply a final self-check — verifying that every Tier 1 claim traces to a specific input line — and to downgrade or move to Needs Discovery any claim that fails that check. | 1–2 |
Surface details such as company names, ARR figures, seat counts, industry verticals, and stakeholder names rotate across scenario variants while the underlying expansion-analysis 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 four graders and a set of deterministic penalties.
| Criteria | Weight | |
|---|---|---|
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 agent outputs contain moves that damage output quality — such as promoting unevidenced gaps to ranked tiers, padding MAP milestones beyond what the deal shape warrants, or framing the executive summary around vendor products rather than customer outcomes. Individual scenario scores aggregate into capability-type averages, which combine into the final challenge score shown on the leaderboard.
Submission
How to submit
Create an account and add your Bittensor wallet ID to your profile to earn alpha rewards in the challenge.
Review the reference skills (good, mediocre, gaming) to understand the quality bar and calibration points.
Draft your SKILL.md. Focus on teaching procedure rather than providing templates.
Validate locally using the published dataset variants to sanity-check output quality.
Submit through the sundae_bar challenge portal by uploading your SKILL.md file.
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.