Enterprise Stakeholder Mapping & Relationship Intelligence Skill
Overview
This skill teaches the agent to analyse account contact data and produce a structured stakeholder map that tells a seller exactly who matters, how strong each relationship is, where the coverage gaps are, and what to do next to advance the deal.
Given a paste or export containing contact names and titles, meeting notes, email or CRM activity summaries, deal stage and size, and any reported org context, the agent produces a single markdown document with a stakeholder table, a coverage gap analysis, a sequenced engagement plan, and an executive sponsor recommendation grounded in specific signals from the input.
The submission is a SKILL.md with optional reference files the agent opens on demand. A good skill teaches a reasoning procedure: how to classify influence tiers from behavioural evidence, how to score relationship strength, how to identify gaps from deal shape rather than a roster check, and how to sequence actions so the most deal-unblocking move comes first. A weak skill provides template tables or hardcoded answers 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: a SKILL.md and, if you need them, reference files it points at. A fixed base agent loads it and answers all 6 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 (6 Tests)
Your skill is tested across 5 capability types, with 6 scenarios in total. Every submission is evaluated against all 6 scenarios. There is no sampling, so consistent quality across every capability type counts.
| Category | Overview | Test cases |
|---|---|---|
| Type A: Behavioural Tier Classification | This type tests whether the agent correctly classifies a contact's influence tier when their job title and their behavioural signals point in different directions. The skill must teach the agent to identify which signals carry actual deal authority, meeting initiation, budget or decision references, internal advocacy, and to override title-based assumptions when the evidence warrants it. | 1 |
| Type B: Deal-Shape Coverage Gap Analysis | This type tests whether the agent identifies missing personas by reasoning about what the deal size, stage, and org structure require, rather than simply listing who is absent. The skill must teach the agent to construct the required persona set from deal context first, then compare the known contact roster against it to surface meaningful gaps. | 1 |
| Type C: Signal-Cited Engagement Sequencing | This type tests whether the agent sequences engagement actions in the order that most directly unblocks the deal, citing a specific input signal and any dependency for each step. The skill must teach the agent to reason about what is blocking progress, which action removes that blocker first, and how downstream actions depend on earlier ones completing. | 1 |
| Type D: Multi-Signal Tier Conflict Resolution | This type tests whether the agent correctly classifies influence tiers when multiple signals across notes, emails, and CRM activity conflict with one another. The skill must teach the agent to surface the conflict explicitly in the rationale column, weigh the signals, and recommend a disambiguating action rather than silently resolving the contradiction in either direction. | 1 |
| Type E: Single-Threading Detection and Gap Prioritisation | This type tests whether the agent identifies and explicitly flags single-threading when exactly one contact controls economic-buyer or champion access, and places the mitigating action at the top of the engagement plan. The skill must teach the agent to recognise single-thread risk as a structural deal risk distinct from ordinary coverage gaps, and to treat the routing of dormant buyer outreach through a warm introduction as the default repair move. | 1 |
Surface details such as account names, contact names, deal sizes, and activity dates rotate across scenario variants while the underlying stakeholder-mapping capability being tested remains the same.
Datasets
Available Datasets
When you submit, we run your skill 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.md and the list of your reference files, opens a reference with read_reference when your SKILL.md tells it to, and follows the skill 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.
What is public at open: the scenario inputs, the rubric, and the sha256 hash of the sealed reference set (the same scenarios with their reference outputs and grading notes). Validators grade against the sealed set; the hash on the challenge page is your proof that it cannot change while the challenge runs.
What you see while it runs: your total, a score for every scenario and every grader, and the written notes of the gate checks (dataset derivation, skill alignment, redundancy, novelty). The quality judges' written explanations are held back, because they describe the reference answer.
What is published when the challenge closes: the sealed reference set, every judge explanation, and the full validator outputs for every submission. Check the file against the published hash and re-run any evaluation yourself.
What you submit: a folder or a .zip with SKILL.md at the top level and an optional references/ folder. A single SKILL.md is also accepted. All files are the submission.
Limits: SKILL.md is at most 10,000 bytes and is always loaded. references/ holds up to 30 files, each at most 32,000 characters, 128,000 characters in total. Text formats only: .md, .txt, .json, .yaml, .yml and .csv. Lower-case file names using letters, digits, dots, dashes and underscores. The current values are published by the platform API at GET /api/v2/submissions/limits; the submission form reads them from there.
How references are read: the agent always sees SKILL.md plus a list of your reference file names. It opens a reference only when SKILL.md tells it to, by name. Each read is one harness step within a cap of 10 steps per scenario, and the file's text counts against the scenario's token budget of 35,000 tokens. A reference the agent never opens does nothing for the score.
Rejected at upload: HTML comments, images, scripts, hidden or invisible characters, nested archives, disallowed file types, and anything over a limit. Text addressed to the evaluators, or that tries to override instructions, is accepted but places the entry under review and scores zero.
Important: the base-agent harness is fixed at evaluation time and its available tools are load_skill, read_reference. You submit only skill files; 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, and certain output choices carry deterministic penalties when they damage the usefulness or accuracy of the stakeholder map, for example, projecting false certainty on thin input, silently resolving conflicting signals, or producing output that falls outside the required format boundaries. Individual scenario scores roll up to per-capability-type averages, which then 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 (at most 10,000 bytes; it is always loaded) and, if the method needs them, put tables, templates and worked examples in reference files under references/. Tell the agent in SKILL.md which reference to open and when, by file name. Focus on teaching procedure rather than providing templates.
Run your skill against the published scenario inputs and rubric to sanity-check output quality. The reference outputs are sealed until the challenge closes.
Submit through the sundae_bar challenge portal by uploading your skill folder, a .zip of it, or a single SKILL.md. The folder has SKILL.md at the top level and an optional references/ folder beside it.
Review your scored breakdown (a score for every scenario and every grader, plus the gate checks' notes) and resubmit. The judges' written explanations are published when the challenge closes.
Constraints
Submission format: a folder or .zip with SKILL.md (YAML frontmatter with name and description, then a Markdown body) at the top level and an optional references/ folder. A single SKILL.md is also accepted.
Limits: SKILL.md at most 10,000 bytes. Up to 30 reference files, each at most 32,000 characters and 128,000 characters in total; text formats only (.md, .txt, .json, .yaml, .yml and .csv); lower-case file names.
Reference reads: the agent opens a reference only when SKILL.md names it. Each read is one of 10 steps per scenario and its text counts against the scenario's 35,000-token budget.
Base agent: fixed. Provided by sundae_bar.
Runtime: a fixed base-agent harness loads your skill and answers all 6 scenarios per submission with it.
Tests per submission: 6 (the full scenario set, no sampling).
Submission limits: 7 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.
Every file in your submission is scanned at submission time by a skill integrity gate: your SKILL.md and every reference file, whether or not your skill points at it. The gate checks that your skill teaches procedure rather than encoding scenario-specific content from our evaluation pool. Content placed in a reference file is checked exactly as content in SKILL.md.
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.
Text addressed to the evaluators or judges, or text that tries to override instructions, anywhere in the bundle, is accepted at upload but places the entry under review and scores zero. Files that are not plain text (HTML comments, images, scripts, hidden or invisible characters, nested archives, disallowed file types) or that exceed a limit are rejected at upload. The copy and similarity checks run over the whole bundle, chunk by chunk, so padding a copied skill with extra reference files does not pass them.