Sundae Bar Logo
Past Challenge
Investment Committee Memo Authoring Skill
SBC37

Investment Committee Memo Authoring Skill

Overview

This skill teaches the agent to draft a structured internal investment committee memo from raw diligence artifacts, producing a document that a deal team could submit directly to an IC for a go or no-go decision.

Given three upstream artifacts, a deal-risk classification table, a financial narrative, and a comparables dataset, the agent produces a single five-section IC memo covering the deal thesis, a tiered risk table, a defended valuation range, a recommendation, and actionable conditions tied to specific risk findings. A good result is internally consistent, within stated length bounds for every section, and traces every recommendation and condition back to named evidence in the input artifacts.

The submission is a SKILL.md file, with optional reference files the agent opens by name when SKILL.md directs it to. Strong skills teach the agent a reasoning procedure: how to read the input artifacts, classify and order findings, apply comp-set discipline, check recommendation consistency, and enforce section structure. Weak skills paste in memo templates or example answers and break the moment deal details, company names, or risk profiles 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 8 sampled 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 four capability types. Every submission sees 2 randomly sampled variants per type, for 8 total scenarios per evaluation.

CategoryOverviewTest cases
Type A: Cross-Document Consistency and Comp FlaggingThis type tests whether the agent can detect tensions across the three input artifacts and handle them without silently distorting the diligence record. Scenarios present upstream risk classifications that may appear inconsistent with the financial narrative or with standard tier definitions, and comp sets that include outliers requiring explicit exclusion. The skill must teach the agent to surface apparent mis-tiers as flagged observations in the memo rather than re-tiering them without disclosure, and to build a valuation range that names every included and excluded comparable with stated rationale and directional adjustments.2
Type B: Full Memo AuthorshipThis type tests end-to-end memo construction across all five required sections in the correct order, within stated length constraints for each section. Scenarios are drawn from realistic deal contexts where all three artifacts are present, and the agent must produce a complete, submission-ready document. The skill must teach the agent to write a Conditions and Next Steps section whose bullets are tied one-to-one to named risk table rows and whose content shifts in character depending on whether the recommendation is to proceed, request more data, or pass.2
Type C: Recommendation ConsistencyThis type tests whether the agent correctly applies the logical gate that governs the recommendation field: an unresolved must-address finding blocks a proceed verdict and forces a more conservative outcome, while a proceed verdict is only available when all must-address findings are resolved and all manageable findings have named mitigations. Scenarios include cases where status fields are missing or ambiguous. The skill must teach the agent to treat missing status as unresolved and to never produce a proceed recommendation that contradicts the risk table state.2
Type D: Valuation and Comp DisciplineThis type tests whether the agent can derive and defend a valuation range from a provided comp set rather than asserting one. Scenarios vary the composition of the comp set, including outliers on growth, margin, or scale. The skill must teach the agent to name the multiple or multiples applied, explicitly identify every comparable that was included or excluded with a one-line rationale for each exclusion, and state directional adjustments for size, margin, and growth relative to the comp-set median before arriving at the final stated range.2

Surface details such as company names, deal sizes, industry verticals, specific finding descriptions, and financial figures rotate across scenario variants, while the underlying 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 30,000 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.

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, and certain moves that damage output quality, such as producing a recommendation that contradicts the risk table state, inventing content when a required artifact is missing, or silently re-tiering an upstream finding, carry deterministic penalties regardless of how well the rest of the memo reads. Individual scenario scores aggregate to per-capability-type averages, which then roll up to 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 (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.

4
Test locally

Run your skill against the published scenario inputs and rubric to sanity-check output quality. The reference outputs are sealed until the challenge closes.

5
Submit via the platform

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.

6
Iterate

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 30,000-token budget.

Base agent: fixed. Provided by sundae_bar.

Runtime: a fixed base-agent harness loads your skill and answers 8 sampled scenarios per submission with it.

Tests per submission: 8 (2 random variants per capability type, seeded by task ID for reproducibility).

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.