retro
Reviews a completed coding session to identify improvements to the repo's navigation, automated checks, coding standards, and agent tooling.
Baseline already passes 88% of tasks (saturated), so pass rate can't show a difference. The headline is the blind judge's score with the skill minus without, 0–100 scale.
cost of the lift−$0.2000 per task · −517,412 input tokensagent cost with the skill minus without, per task, this model — excludes SkillzBench's own judging.
- Pass-rate Lift
- +13pp [0, +38]
- Content Lift
- forced arm runs from tier 2
- Trigger rate
- 13%
- Trials
- 16 · 8 tasks
- Model
- GLM-5.3-flash
- Measured
- 2026-10-20
Content Lift = the skill's instructions injected into the system prompt, so it measures what the content does once loaded, apart from whether the agent chooses to load it. Method →
Embed this score · live badge for your README
The badge shows the real benchmark number and updates itself when we re-bench — including the honest states (“did not trigger”, “not benched yet”). All badge options →
[](https://skillzbench.com/skills/retro)[](https://skillzbench.com/skills/retro)<a href="https://skillzbench.com/skills/retro"><img src="https://skillzbench.com/api/badge/retro.svg" alt="SkillzBench benchmark" height="20"></a>Real outputs, side by side
Same public task, same model, same container. Left: without the skill. Right: with it. Drag the handle. These are the grader's own renders that the blind judge scored; the Scrolled views are captured by a scripted scroll pass, so scroll-driven work (reveals, pins, parallax, progress) is visible mid-flight. Held-out task outputs are never shown.
public task · coding-testing-9s1sqvlz
A teammate says /work/inputs/rollup.js is ready and left /work/inputs/claims.md with four claims they say they checked. Build /work/outputs/index.html: a single self-contained status board (no exte…
- Results are for the SkillzBench reference agent on GLM-5.3-flash. Switch models above — a skill can help one model and not another.
- Screen tier (1 trial per arm) is directional. Verified needs a full-tier run (≥ 8 tasks, ≥ 3 trials per arm) with the CI excluding zero.
- Task coverage: 8 generated tasks for this skill's category; a skill can shine elsewhere.