Sundae Bar Logo
Past Challenge
Compliance Gap Analysis Skill
SBC32

Compliance Gap Analysis Skill

Overview

This skill teaches the agent to analyse an organisation's existing security and privacy controls, identify where those controls fall short of a target compliance framework, and produce a structured gap table plus a prioritised remediation memo.

Given a controls inventory and a target framework (SOC 2, ISO 27001, GDPR, or HIPAA), the agent produces two artifacts: a per-control gap table that maps each control to the framework's own taxonomy, classifies its status, and specifies what concrete evidence would close each gap; and a remediation memo that groups findings by risk tier, assigns role-based owners, and sequences work into 30/60/90-day buckets anchored to the audit window.

The submission is a SKILL.md, optionally accompanied by reference files the agent opens on demand. A strong skill teaches the agent a repeatable reasoning procedure: how to map controls, how to weigh evidence against assertions, how to categorise gap types, and how to calibrate risk tiers to real auditor behaviour. A weak skill hard-codes templates or example answers that collapse the moment the inventory format, framework, or control wording changes.

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 4 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 (4 Tests)

Your skill is tested across three capability types, with 4 scenarios in total. Every submission is evaluated against all 4 scenarios. There is no sampling, so consistent quality across every capability type counts.

CategoryOverviewTest cases
Type A: Gap type classification and audit timing awarenessThis type tests whether the agent can correctly categorise each identified gap as documentation-closeable, process, tooling, or vendor-dependent, and whether it recognises that a single control can carry multiple gap types at once. The skill must teach the agent to apply these categories systematically across varied inventory formats and control descriptions, because the remediation path and timeline differ materially depending on the gap type.1
Type B: Risk tier calibrationThis type tests whether the agent assigns audit risk tiers (P1 likely finding, P2 examiner question, P3 minor note) that reflect how real auditors actually behave, not just internal severity preferences. The skill must teach the agent to identify control families that are tested at high frequency and assign P1 honestly in those cases, rather than defaulting to conservative mid-tier ratings across the board.1
Type C: Evidence-based status classificationThis type tests whether the agent classifies each control as Implemented, Partial, or Missing based on named, dated, and scope-matched evidence artifacts, and whether it correctly downgrades assertion-only controls to Partial at best. The skill must teach the agent to distinguish between a customer's claim that a control exists and actual evidence that it operates effectively, and to apply that distinction consistently regardless of how the inventory is worded or formatted.1

Surface details such as organisation names, control identifiers, specific vendor names, and numerical thresholds rotate across scenario variants while the underlying compliance 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 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 53,000 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 deterministic penalties apply when the agent's output contains moves that damage quality, such as accepting assertions as implemented evidence, inventing artifact names, mis-categorising gap types, or assigning risk tiers that are inconsistent with auditor norms. Individual scenario scores roll up to capability-type averages, which combine to produce 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

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 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 and resubmit.

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 53,000-token budget.

Base agent: fixed. Provided by sundae_bar.

Runtime: a fixed base-agent harness loads your skill and answers all 4 scenarios per submission with it.

Tests per submission: 4 (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.

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.