/score-audit, expected score and the next cheapest point
The point-budget equivalent of a weight budget. Adapted from SumoX-26's /bom-builder, which did the same job for grams.
Answers one question: given where the project actually is, what is the expected qualification score, and what is the cheapest point still unclaimed?
The model
Qualification % = 0.50 × (trial points / 19)
+ 0.20 × code
+ 0.10 × video
+ 0.20 × report
Full breakdown in docs/SCORING.md.
Steps
Read results/trials.csv. Take the best trial score, since the committee takes the best of three attempts. If the file is empty or missing, say so plainly: trial points are 0 banked, and everything else is projection.
Score the trial component honestly, per item, marking each banked or projected:
| Item |
Points |
Status |
| Column publish |
+1 |
banked / projected / not started |
| Column annotated image |
+2 |
|
| Navigate to column (needs the grasp) |
+3 |
|
| Row publish |
+1 |
|
| Row annotated image |
+2 |
|
| Grasp |
+3 |
|
| Navigate to bin (needs delivery) |
+3 |
|
| Place, dropped +2 or gentle +4 |
|
|
| Collisions observed |
-0.5 each |
|
Apply the two contingencies. Navigation to the column scores nothing without a successful grasp, and navigation to the bin scores nothing without delivery. Do not count them as banked while the grasp is unproven.
Assess the three deliverables against their stated criteria, not against a feeling:
| Component |
Weight |
Assess by |
| Code |
20% |
Are perception, planning and execution in distinct nodes? Does every stage have a timeout and a retry budget? Are recovery paths present and tested? Are comments explanatory? |
| Video |
10% |
Does a take exist that satisfies all six constraints? Has a full run been timed against the 5-minute ceiling? |
| Report |
20% |
Do the six sections exist? Do results/trials.csv and the RViz screenshots contain the required numbers and figures? |
The video and report should be scored as near-zero until the artifacts exist. A plan to write a report is not 20%.
Compute the expected score on the 100-point scale, showing the arithmetic, and separate what is banked from what is projected.
Find the cheapest unclaimed point. Rank remaining work by qualification points per hour, and prefer certainty. Reference values:
| Work |
Qualification points |
Certainty |
| Each vision publish |
2.6 |
High. Pure OpenCV |
| Each vision annotated image |
5.3 |
High |
| Gentle place instead of drop |
1.05 |
High once the grasp works. Hours of Cartesian pathing |
| The grasp, with its withheld navigation points |
15.8 |
Low. The keystone |
| Delivery chain after the grasp |
18.4 |
Medium |
| A recovery path |
Part of the 20% code component |
High |
| The report's six sections |
up to 20 |
High, if the data exists |
| The video |
up to 10 |
High. A checklist |
| Speed optimisation |
0 outside a tie |
n/a |
State the one recommendation, with the arithmetic behind it.
Output format
## Score audit, <date>, <days> days to 2026-09-15
### Trial component (50%)
Best logged trial: <n>/19 → <n × 0.50/19 × 100> qualification points
Banked: <list>
Projected: <list, with what each depends on>
### Code (20%)
<assessment against modularity, error handling, comments> → <estimate>
### Video (10%)
<does a compliant take exist> → <estimate>
### Report (20%)
<do the sections and the data exist> → <estimate>
### Expected qualification score
Banked: <n> / 100
Projected: <n> / 100
### Cheapest unclaimed point
**Do next:** <one thing>
**Worth:** <qualification points>
**Cost:** <rough hours>
**Certainty:** high / medium / low
**Instead of:** <what this displaces, and why that's right>
Rules
- Banked means a logged trial recorded it. Everything else is projected and must be labelled so. This distinction is the entire point of the skill.
- Apply the contingencies. The two navigation +3s are the most commonly over-counted points in this challenge, because they look earned when the robot drives correctly and they are not.
- Score the deliverables as near-zero until the artifacts exist. An intention is not a mark.
- Prefer certain points over uncertain ones when the hours are comparable.
- Never recommend work that isn't on the rubric. No dashboards, no backup perception pipelines, no visualisations. There are 29 days.
- Recompute rather than reusing a previous audit's numbers. The point of this skill is to reflect the current state.
- If the 2026-09-06 grasp decision is due or overdue, say so and give the arithmetic for both paths.
1---2name: score-audit3description: Compute ERC-26's current expected qualification score against the rubric, identify the cheapest unclaimed point, and recommend what to build next in point order. Use when deciding priorities, when time is short, or before the 2026-09-06 grasp decision.4---56# /score-audit, expected score and the next cheapest point78The point-budget equivalent of a weight budget. Adapted from SumoX-26's `/bom-builder`, which did the same job for grams.910Answers one question: given where the project actually is, what is the expected qualification score, and what is the cheapest point still unclaimed?1112## The model1314```15Qualification % = 0.50 × (trial points / 19)16 + 0.20 × code17 + 0.10 × video18 + 0.20 × report19```2021Full breakdown in `docs/SCORING.md`.2223## Steps24251. **Read `results/trials.csv`.** Take the best trial score, since the committee takes the best of three attempts. If the file is empty or missing, say so plainly: trial points are 0 banked, and everything else is projection.26272. **Score the trial component honestly**, per item, marking each banked or projected:2829 | Item | Points | Status |30 |---|---|---|31 | Column publish | +1 | banked / projected / not started |32 | Column annotated image | +2 | |33 | Navigate to column (**needs the grasp**) | +3 | |34 | Row publish | +1 | |35 | Row annotated image | +2 | |36 | Grasp | +3 | |37 | Navigate to bin (**needs delivery**) | +3 | |38 | Place, dropped +2 or gentle +4 | | |39 | Collisions observed | -0.5 each | |4041 Apply the two contingencies. Navigation to the column scores nothing without a successful grasp, and navigation to the bin scores nothing without delivery. Do not count them as banked while the grasp is unproven.42433. **Assess the three deliverables** against their stated criteria, not against a feeling:4445 | Component | Weight | Assess by |46 |---|---|---|47 | Code | 20% | Are perception, planning and execution in distinct nodes? Does every stage have a timeout and a retry budget? Are recovery paths present and tested? Are comments explanatory? |48 | Video | 10% | Does a take exist that satisfies all six constraints? Has a full run been timed against the 5-minute ceiling? |49 | Report | 20% | Do the six sections exist? Do `results/trials.csv` and the RViz screenshots contain the required numbers and figures? |5051 The video and report should be scored as near-zero until the artifacts exist. A plan to write a report is not 20%.52534. **Compute the expected score** on the 100-point scale, showing the arithmetic, and separate what is banked from what is projected.54555. **Find the cheapest unclaimed point.** Rank remaining work by qualification points per hour, and prefer certainty. Reference values:5657 | Work | Qualification points | Certainty |58 |---|---|---|59 | Each vision publish | 2.6 | High. Pure OpenCV |60 | Each vision annotated image | 5.3 | High |61 | Gentle place instead of drop | 1.05 | High once the grasp works. Hours of Cartesian pathing |62 | The grasp, with its withheld navigation points | 15.8 | Low. The keystone |63 | Delivery chain after the grasp | 18.4 | Medium |64 | A recovery path | Part of the 20% code component | High |65 | The report's six sections | up to 20 | High, if the data exists |66 | The video | up to 10 | High. A checklist |67 | Speed optimisation | 0 outside a tie | n/a |68696. **State the one recommendation**, with the arithmetic behind it.7071## Output format7273```74## Score audit, <date>, <days> days to 2026-09-157576### Trial component (50%)77Best logged trial: <n>/19 → <n × 0.50/19 × 100> qualification points78Banked: <list>79Projected: <list, with what each depends on>8081### Code (20%)82<assessment against modularity, error handling, comments> → <estimate>8384### Video (10%)85<does a compliant take exist> → <estimate>8687### Report (20%)88<do the sections and the data exist> → <estimate>8990### Expected qualification score91Banked: <n> / 10092Projected: <n> / 1009394### Cheapest unclaimed point95**Do next:** <one thing>96**Worth:** <qualification points>97**Cost:** <rough hours>98**Certainty:** high / medium / low99**Instead of:** <what this displaces, and why that's right>100```101102## Rules103104- **Banked means a logged trial recorded it.** Everything else is projected and must be labelled so. This distinction is the entire point of the skill.105- **Apply the contingencies.** The two navigation +3s are the most commonly over-counted points in this challenge, because they look earned when the robot drives correctly and they are not.106- **Score the deliverables as near-zero until the artifacts exist.** An intention is not a mark.107- **Prefer certain points over uncertain ones** when the hours are comparable.108- **Never recommend work that isn't on the rubric.** No dashboards, no backup perception pipelines, no visualisations. There are 29 days.109- Recompute rather than reusing a previous audit's numbers. The point of this skill is to reflect the current state.110- If the 2026-09-06 grasp decision is due or overdue, say so and give the arithmetic for both paths.
Faaz17