Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Capture delivery evidence, commands, changed files, blockers, and standards feedback after a work session.
.claude/skills/hoangnguyen0403-session-report/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 51% | 0% |
| case-02 | ✗→✓ | ▲ Improved | -8% | 0% |
| case-04 | ✗→✓ | ▲ Improved | 29% | 0% |
| case-07 | ✗→✓ | ▲ Improved | -17% | 0% |
| case-09 | ✗→✓ | ▲ Improved | -35% | 0% |
> !IMPORTANT] > Capture delivery evidence, commands, changed files, blockers, and standards feedback after a work session.
Optional args: slug=<feature>, ticket=<id/url>, mode=interactive|autonomous|channel, channel=<id>, auto_continue=true|false, profile=business|hybrid|technical.
When the user asks to perform this workflow, execute the following steps:
Goal: Preserve a concise artifact of what changed, how it was verified, and what should improve.
common-operator-profile; carry the inherited operator_profile from the Handoff Payload without re-inferring it.implement-feature or dev-fix.verify-work or traceability-audit.retro-learn.publish-notes.slug, operator_profile, goal, changes, verification results, requirement-drift status, risks, follow-ups, next workflow.md# Session Report ## Goal ## Changes ## Verification | Command/Check | Result | Evidence | | --- | --- | --- | | [check] | [result] | [evidence] | ## BRD/PRD/SRS Update Status ## Risks And Follow-Ups ## Skill Feedback Candidates ## Outcome Report feature_status: partially_implemented | implemented | blocked requirement_trace: BRD-OBJ-* -> REQ-* -> AC-* -> SRS-* -> evidence completed_evidence: []; missing_evidence: []; decision_needed: []; recommended_next_workflow: implement-feature | verify-work | publish-notes | retro-learn ## Next Workflow ## Cost Report Call `get_session_cost(workflow="session-report")` before final handoff.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-22 | pass→pass | 11,883 | 16,697 | +41% | 1 | 1 | 0% | 2,344 | 3,614 | +54% | 0 | 0 | — |
case-16 | pass→pass | 8,168 | 7,226 | -12% | 1 | 1 | 0% | 1,337 | 1,920 | +44% | 0 | 0 | — |
case-21 | pass→fail | 11,143 | 18,836 | +69% | 1 | 1 | 0% | 1,871 | 4,118 | +120% | 0 | 0 | — |
case-01 | fail→pass | 9,014 | 9,375 | +4% | 1 | 1 | 0% | 1,705 | 2,574 | +51% | 0 | 0 | — |
case-02 | fail→pass | 10,783 | 6,981 | -35% | 1 | 1 | 0% | 2,136 | 1,963 | -8% | 0 | 0 | — |
case-03 | fail→fail | 5,817 | 5,487 | -6% | 1 | 1 | 0% | 1,071 | 1,228 | +15% | 0 | 0 | — |
case-04 | fail→pass | 7,105 | 4,262 | -40% | 1 | 1 | 0% | 1,163 | 1,496 | +29% | 0 | 0 | — |
case-05 | pass→pass | 5,779 | 5,994 | +4% | 1 | 1 | 0% | 979 | 1,734 | +77% | 0 | 0 | — |
case-06 | pass→pass | 3,652 | 7,397 | +103% | 1 | 1 | 0% | 672 | 2,030 | +202% | 0 | 0 | — |
case-07 | fail→pass | 9,942 | 4,288 | -57% | 1 | 1 | 0% | 1,747 | 1,453 | -17% | 0 | 0 | — |
case-08 | pass→pass | 5,786 | 5,439 | -6% | 1 | 1 | 0% | 930 | 1,739 | +87% | 0 | 0 | — |
case-09 | fail→pass | 8,915 | 1,981 | -78% | 1 | 1 | 0% | 1,582 | 1,025 | -35% | 0 | 0 | — |
case-10 | fail→pass | 9,910 | 4,109 | -59% | 1 | 1 | 0% | 1,624 | 1,539 | -5% | 0 | 0 | — |
case-11 | pass→pass | 5,246 | 1,390 | -74% | 1 | 1 | 0% | 796 | 877 | +10% | 0 | 0 | — |
case-12 | pass→pass | 5,926 | 4,752 | -20% | 1 | 1 | 0% | 969 | 1,591 | +64% | 0 | 0 | — |
case-13 | fail→fail | 9,516 | 6,542 | -31% | 1 | 1 | 0% | 1,658 | 1,685 | +2% | 0 | 0 | — |
case-14 | pass→pass | 3,834 | 1,608 | -58% | 1 | 1 | 0% | 719 | 904 | +26% | 0 | 0 | — |
case-15 | pass→pass | 4,756 | 6,121 | +29% | 1 | 1 | 0% | 811 | 1,752 | +116% | 0 | 0 | — |
case-17 | pass→pass | 6,297 | 3,658 | -42% | 1 | 1 | 0% | 957 | 1,271 | +33% | 0 | 0 | — |
case-18 | fail→pass | 12,142 | 5,144 | -58% | 1 | 1 | 0% | 1,868 | 1,464 | -22% | 0 | 0 | — |
case-19 | pass→pass | 10,842 | 4,251 | -61% | 1 | 1 | 0% | 1,557 | 1,302 | -16% | 0 | 0 | — |
case-20 | fail→fail | 8,299 | 10,092 | +22% | 1 | 1 | 0% | 791 | 1,680 | +112% | 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 21 counted toward the lift figure. The other 1 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 +27 percentage points is the difference between those two pass rates over the 21 comparable cases. 2 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.