Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Generate a concise end-of-day work update from local diary, GitHub activity, PR queue state, and optional Asana config. Use when the user asks for daily update, EOD update, standup, or what they did today.
.claude/skills/tetherto-qv-daily-work-update/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-22 | ✗→✓ | ▲ Improved | -20% | 0% |
| case-12 | ✗→✓ | ▲ Improved | 28% | 0% |
| case-13 | ✗→✓ | ▲ Improved | -9% | 0% |
| case-07 | ✓→✗ | ▼ Worse | 45% | 0% |
| case-10 | ✓→✗ | ▼ Worse | 29% | 0% |
Generate a copy-paste-ready EOD update. Do not post it anywhere unless the user explicitly asks and confirms.
Today:
bashnode .cursor/skills/_lib/developer-workflow/daily-work-update.mjs
Specific date:
bashnode .cursor/skills/_lib/developer-workflow/daily-work-update.mjs --date YYYY-MM-DD
With user-provided tomorrow/blocker text:
bashnode .cursor/skills/_lib/developer-workflow/daily-work-update.mjs \ --tomorrow $'Finish QVAC-12345\nFollow up on PR review' \ --blockers "None"
~/.config/qvac-pr-skills/diary/gh user.cursor/skills/_lib/pr-skills/pr-status.mjs --json when queue context is needed.cursor/skills/_lib/developer-workflow/asana.mjs when configuredAlways ask the user for:
Then render all three Slack sections every time:
text:hammer: Completed today (<Day Date>) - Approved: <ticket link>, <PR link>; <ticket link>, <PR link> - Commented / Requested changes: <ticket link>, <PR link> - <ticket link>, <PR link> - <authored/opened/merged work> :calendar: Planned for tomorrow - <user-provided plan> :construction: Blockers / risks - <user-provided blockers, or None>
Rules:
daily-work-update.mjs and use stdout as the source of truth.Approved: review summary into one bullet per PR. If the generator emits Approved: ...; ..., preserve that one summary bullet.- ). Do not escape bullets.[label](url).[#123](https://github.com/org/repo/pull/123).[QVAC-12345 Task title](https://app.asana.com/...).Approved: [#123](...) - [QVAC-12345: task](...), [#124](...) - [QVAC-12346: task](...)Commented / Requested changes: [#125](...) - [QVAC-12347: task](...)owner/repo#123 when a URL is available.<url|label> for copy-paste output.:hammer:, :calendar:, and :construction: sections, even if one section is None or No recorded activity.$'line one\nline two' or quote literal newlines.| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 5,337 | 6,653 | +25% | 1 | 1 | 0% | 854 | 1,406 | +65% | 0 | 0 | — |
case-02 | fail→fail | 4,827 | 6,023 | +25% | 1 | 1 | 0% | 787 | 1,413 | +80% | 0 | 0 | — |
case-03 | fail→fail | 6,806 | 8,013 | +18% | 1 | 1 | 0% | 984 | 1,774 | +80% | 0 | 0 | — |
case-04 | pass→pass | 10,015 | 6,975 | -30% | 1 | 1 | 0% | 1,709 | 2,020 | +18% | 0 | 0 | — |
case-05 | pass→pass | 10,942 | 7,586 | -31% | 1 | 1 | 0% | 1,745 | 2,097 | +20% | 0 | 0 | — |
case-06 | pass→pass | 10,703 | 8,145 | -24% | 1 | 1 | 0% | 1,697 | 2,105 | +24% | 0 | 0 | — |
case-07 | pass→fail | 5,782 | 4,921 | -15% | 1 | 1 | 0% | 852 | 1,234 | +45% | 0 | 0 | — |
case-08 | fail→fail | 4,754 | 5,866 | +23% | 1 | 1 | 0% | 736 | 1,376 | +87% | 0 | 0 | — |
case-09 | pass→pass | 3,928 | 2,288 | -42% | 1 | 1 | 0% | 733 | 1,382 | +89% | 0 | 0 | — |
case-22 | fail→pass | 10,755 | 2,301 | -79% | 1 | 1 | 0% | 1,693 | 1,351 | -20% | 0 | 0 | — |
case-10 | pass→fail | 6,531 | 6,849 | +5% | 1 | 1 | 0% | 1,090 | 1,410 | +29% | 0 | 0 | — |
case-11 | pass→fail | 3,577 | 5,062 | +42% | 1 | 1 | 0% | 578 | 1,279 | +121% | 0 | 0 | — |
case-12 | fail→pass | 7,547 | 2,621 | -65% | 1 | 1 | 0% | 1,167 | 1,497 | +28% | 0 | 0 | — |
case-13 | fail→pass | 11,724 | 4,166 | -64% | 1 | 1 | 0% | 1,820 | 1,663 | -9% | 0 | 0 | — |
case-14 | fail→fail | 3,975 | 5,576 | +40% | 1 | 1 | 0% | 579 | 1,301 | +125% | 0 | 0 | — |
case-15 | pass→pass | 4,574 | 2,186 | -52% | 1 | 1 | 0% | 748 | 1,306 | +75% | 0 | 0 | — |
case-16 | pass→fail | 5,505 | 6,919 | +26% | 1 | 1 | 0% | 841 | 1,481 | +76% | 0 | 0 | — |
case-17 | pass→pass | 7,757 | 2,428 | -69% | 1 | 1 | 0% | 1,355 | 1,463 | +8% | 0 | 0 | — |
case-18 | fail→fail | 6,401 | 2,457 | -62% | 1 | 1 | 0% | 1,156 | 1,449 | +25% | 0 | 0 | — |
case-19 | fail→fail | 7,298 | 1,889 | -74% | 1 | 1 | 0% | 1,055 | 1,239 | +17% | 0 | 0 | — |
case-20 | pass→pass | 11,407 | 2,861 | -75% | 1 | 1 | 0% | 1,761 | 1,515 | -14% | 0 | 0 | — |
case-21 | pass→pass | 6,554 | 2,639 | -60% | 1 | 1 | 0% | 990 | 1,346 | +36% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted, and 14 counted toward the lift figure. The other 8 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of -5 percentage points is the difference between those two pass rates over the 14 comparable cases. 4 cases got worse with the skill loaded, and they are included in that figure.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.