OKR & Goal-Tracking Strategic Review Skill
Overview
This skill teaches the agent to read an OKR or goal-tracking export and produce a structured leadership-review narrative that tells executives exactly where the organisation stands, what decisions are required, and what actions owners must take.
Given a pasted tracker export — with objectives, key results, progress percentages, owners, due dates, and optional trend signals — a good result is a five-section narrative: an executive summary naming overall posture and the single most critical decision, a disciplined table of genuine leadership decisions, a blocked/at-risk highlight table, per-objective health verdicts with owner-level actions, and brief informational notes on wins.
The submission is a single SKILL.md. Strong skills teach the agent a reasoning procedure it can apply to any tracker snapshot it has never seen before: how to compute pace ratios, how to classify blockers, how to detect cross-objective dependencies, and when to raise versus withhold a decision ask. Weak skills paste in templated narratives or memorised phrasings that collapse the moment objective names, percentages, or cadences 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 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 four 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 — Leadership Decision Discipline | Tests whether the agent correctly identifies when genuine leadership decisions exist versus when none are required. The skill must teach the agent to evaluate each candidate ask against a leadership-vs-owner threshold, cap decision asks at five, and produce an explicit 'no decisions required' statement rather than manufacturing low-quality asks to fill the section. | 1 |
| Type B — Staleness Reclassification | Tests whether the agent correctly detects KRs that have not been updated for more than three weeks and reclassifies them as 'at-risk: measurement gap' regardless of their last-known tracker color. The skill must teach the agent to check last-update timestamps before accepting any health status at face value, and to flag absent timestamp data as a confidence-limiting condition. | 1 |
| Type C — Cross-Objective Dependency Propagation | Tests whether the agent reads the full set of objectives before drafting any section, identifies hard dependencies between KRs across objectives, and propagates at-risk or off-track status from blocking KRs to the KRs that depend on them. The skill must teach the agent to surface these linkages explicitly in both the blocked/at-risk table and the relevant per-objective narratives. | 1 |
| Type D — Blocker Classification | Tests whether the agent correctly classifies each blocker into one of four categories — resourcing, external dependency, scope creep, or measurement gap — or provides a plain-language description when none fit. The skill must teach the agent to apply this taxonomy consistently in the blocked/at-risk highlight table and to consolidate shared-root blockers rather than repeating them across objectives. | 1 |
Surface details such as objective names, key result labels, owner names, progress percentages, and due dates rotate across scenario variants, while the underlying capabilities being tested remain constant.
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 on the quality of the agent's output across the five required sections; deterministic penalties apply when the output omits required sections, manufactures leadership decisions, misclassifies blockers, carries forward stale health statuses without reclassification, or uses softened hedging language in place of the required verdict terms. Individual scenario scores are aggregated into per-capability-type averages, which combine into the overall 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 6 scenarios per submission with it.
Tests per submission: 6 (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.