Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Creates a safe en-US handoff markdown file from the current session, including the session timestamp, status, objective, expected result, work done, wins, failures, blockers, related sessions or agents, and next steps. Use when the user asks to create a session handoff or to end the session.
.claude/skills/wanderlima-session-handoff/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-02 | ✗→✓ | ▲ Improved | 62% | 0% |
| case-06 | ✗→✓ | ▲ Improved | 59% | 0% |
| case-12 | ✗→✓ | ▲ Improved | 19% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 58% | 0% |
| case-10 | ✗→✓ | ▲ Improved | 11% | 0% |
Create a concise continuation note for the current session so another agent or future run can pick up the work quickly without reading the full transcript.
<active-workspace>/handoffs/<objective-summary>.md.env values or anything that looks like a secret or credentialhandoffs/ folder if it does not exist[redacted].optimize-linkedin-profile.mdsession-handoff.mdUse this structure:
markdown# Session Handoff: <short title> ## Session metadata - Date/time: <timestamp> - Status: <completed | partial | blocked> ## Objective ## Expected result ## What was done ## What worked ## What did not work yet ## Blockers and risks ## Decisions made ## Related sessions or agents ## Relevant files or references ## Next steps ## Notes
handoffs/.Handoff saved to: /absolute/path/to/file.md.| Rationalization | Reality | | --- | --- | | The transcript is enough without a file | The skill exists to create a durable handoff artifact | | A filename doesn't matter much | The filename is the retrieval handle for future continuation | | Minor sensitive details are fine | Handoffs must be safe to share internally | | Related sessions are optional in every case | They matter whenever they change the continuation plan |
handoffs/<active-workspace>/handoffs/| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-02 | fail→pass | 11,952 | 13,955 | +17% | 1 | 1 | 0% | 1,920 | 3,119 | +62% | 0 | 0 | — |
case-01 | fail→fail | 12,851 | 6,591 | -49% | 1 | 1 | 0% | 2,180 | 1,437 | -34% | 0 | 0 | — |
case-03 | fail→fail | 13,919 | 5,458 | -61% | 1 | 1 | 0% | 2,508 | 1,418 | -43% | 0 | 0 | — |
case-04 | pass→pass | 4,997 | 3,655 | -27% | 1 | 1 | 0% | 612 | 1,486 | +143% | 0 | 0 | — |
case-05 | pass→pass | 10,833 | 6,872 | -37% | 1 | 1 | 0% | 1,644 | 2,038 | +24% | 0 | 0 | — |
case-06 | fail→pass | 10,657 | 10,592 | -1% | 1 | 1 | 0% | 1,720 | 2,731 | +59% | 0 | 0 | — |
case-12 | fail→pass | 12,649 | 11,925 | -6% | 1 | 1 | 0% | 2,303 | 2,733 | +19% | 0 | 0 | — |
case-07 | fail→pass | 10,131 | 10,592 | +5% | 1 | 1 | 0% | 1,900 | 3,011 | +58% | 0 | 0 | — |
case-08 | fail→fail | 12,830 | 7,945 | -38% | 1 | 1 | 0% | 2,255 | 1,250 | -45% | 0 | 0 | — |
case-09 | fail→fail | 7,312 | 8,027 | +10% | 1 | 1 | 0% | 1,094 | 2,458 | +125% | 0 | 0 | — |
case-10 | fail→pass | 11,580 | 7,662 | -34% | 1 | 1 | 0% | 2,043 | 2,266 | +11% | 0 | 0 | — |
case-11 | fail→pass | 12,261 | 9,619 | -22% | 1 | 1 | 0% | 1,937 | 2,694 | +39% | 0 | 0 | — |
case-13 | fail→fail | 15,605 | 6,921 | -56% | 1 | 1 | 0% | 3,008 | 1,448 | -52% | 0 | 0 | — |
case-14 | fail→fail | 11,904 | 5,825 | -51% | 1 | 1 | 0% | 1,924 | 1,287 | -33% | 0 | 0 | — |
case-15 | pass→pass | 12,112 | 8,464 | -30% | 1 | 1 | 0% | 2,259 | 2,600 | +15% | 0 | 0 | — |
case-16 | fail→fail | 6,553 | 16,991 | +159% | 1 | 1 | 0% | 1,231 | 3,720 | +202% | 0 | 0 | — |
case-17 | fail→fail | 10,238 | 6,002 | -41% | 1 | 1 | 0% | 1,781 | 1,356 | -24% | 0 | 0 | — |
case-18 | fail→pass | 14,331 | 12,744 | -11% | 1 | 1 | 0% | 2,415 | 3,255 | +35% | 0 | 0 | — |
case-19 | fail→fail | 6,064 | 10,219 | +69% | 1 | 1 | 0% | 1,064 | 2,329 | +119% | 0 | 0 | — |
case-20 | fail→pass | 9,504 | 11,963 | +26% | 1 | 1 | 0% | 1,490 | 3,313 | +122% | 0 | 0 | — |
case-21 | fail→pass | 13,545 | 12,507 | -8% | 1 | 1 | 0% | 2,177 | 3,360 | +54% | 0 | 0 | — |
case-22 | fail→fail | 14,499 | 6,814 | -53% | 1 | 1 | 0% | 2,428 | 1,288 | -47% | 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 +41 percentage points is the difference between those two pass rates over the 14 comparable cases.
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.