Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Respond to a performance improvement plan strategically — decode what the PIP really is, decide fight-vs-land-softly with clear eyes, build the evidence file, and run the parallel job search the situation demands. Use when asked I was just put on a PIP what do I do, help me respond to a performance improvement plan, is my PIP survivable, or write my PIP check-in updates. Produces the honest read of the PIP, the two-track plan (perform + search), the documentation system, and templates for check-
.claude/skills/mohitagw15856-pip-responder/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-03 | ✗→✓ | ▲ Improved | 10% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 93% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 59% | 0% |
| case-14 | ✗→✓ | ▲ Improved | 44% | 0% |
| case-20 | ✗→✓ | ▲ Improved | 33% | 0% |
A PIP is sometimes a genuine turnaround offer and often paperwork for a decision already made — and the response strategy is nearly identical either way: perform visibly against the letter of the plan, document everything, and run a job search in parallel starting now. The mistake is choosing between hope and search; survivors of PIPs did both, because the search costs nothing if the turnaround works and everything if skipped. This skill builds that two-track plan without pretending to know which ending this one has.
Ask for these if not provided:
Recoverable-vs-scripted signals present here · what the metrics' winnability says · stated as a read, not a verdict]
Each PIP goal → its pinned-down measurable definition → the weekly proof artifact]
Week-by-week against the PIP clock · materials, outreach, interview pacing]
What to save · external storage rule · the weekly update template, ready to send]
Draft: professional acknowledgment · clarifying questions pinning vague goals · factual corrections, flat tone]
> A PIP has legal dimensions — signatures, discrimination/retaliation angles, severance offers, visa timelines. This is strategy, not legal advice; an employment lawyer reviewing the documents is money well spent.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-23 | pass→pass | 17,945 | 22,594 | +26% | 1 | 1 | 0% | 1,722 | 3,395 | +97% | 0 | 0 | — |
case-01 | fail→fail | 34,173 | 28,970 | -15% | 1 | 1 | 0% | 4,758 | 4,876 | +2% | 0 | 0 | — |
case-02 | pass→pass | 31,789 | 33,473 | +5% | 1 | 1 | 0% | 3,905 | 4,764 | +22% | 0 | 0 | — |
case-03 | fail→pass | 30,478 | 22,136 | -27% | 1 | 1 | 0% | 4,284 | 4,730 | +10% | 0 | 0 | — |
case-04 | pass→pass | 19,515 | 25,576 | +31% | 1 | 1 | 0% | 2,526 | 3,860 | +53% | 0 | 0 | — |
case-05 | pass→pass | 12,702 | 15,351 | +21% | 1 | 1 | 0% | 2,093 | 2,727 | +30% | 0 | 0 | — |
case-06 | pass→pass | 19,792 | 28,083 | +42% | 1 | 1 | 0% | 2,199 | 4,489 | +104% | 0 | 0 | — |
case-07 | fail→pass | 18,439 | 24,384 | +32% | 1 | 1 | 0% | 2,129 | 4,103 | +93% | 0 | 0 | — |
case-08 | pass→pass | 18,587 | 20,343 | +9% | 1 | 1 | 0% | 1,945 | 3,464 | +78% | 0 | 0 | — |
case-09 | fail→pass | 21,228 | 22,343 | +5% | 1 | 1 | 0% | 2,108 | 3,354 | +59% | 0 | 0 | — |
case-10 | pass→pass | 22,526 | 25,801 | +15% | 1 | 1 | 0% | 2,478 | 4,103 | +66% | 0 | 0 | — |
case-11 | pass→pass | 25,326 | 25,318 | -0% | 1 | 1 | 0% | 2,822 | 4,295 | +52% | 0 | 0 | — |
case-12 | pass→pass | 19,461 | 16,460 | -15% | 1 | 1 | 0% | 2,345 | 3,722 | +59% | 0 | 0 | — |
case-13 | pass→pass | 21,649 | 23,947 | +11% | 1 | 1 | 0% | 2,270 | 3,640 | +60% | 0 | 0 | — |
case-14 | fail→pass | 19,747 | 18,794 | -5% | 1 | 1 | 0% | 2,163 | 3,124 | +44% | 0 | 0 | — |
case-15 | pass→pass | 23,859 | 23,779 | -0% | 1 | 1 | 0% | 2,713 | 3,579 | +32% | 0 | 0 | — |
case-16 | pass→pass | 25,668 | 19,583 | -24% | 1 | 1 | 0% | 2,705 | 3,733 | +38% | 0 | 0 | — |
case-17 | pass→pass | 14,618 | 24,594 | +68% | 1 | 1 | 0% | 2,116 | 3,989 | +89% | 0 | 0 | — |
case-18 | fail→fail | 28,316 | 25,313 | -11% | 1 | 1 | 0% | 3,227 | 4,205 | +30% | 0 | 0 | — |
case-19 | pass→pass | 20,828 | 13,905 | -33% | 1 | 1 | 0% | 2,263 | 3,111 | +37% | 0 | 0 | — |
case-20 | fail→pass | 21,080 | 19,376 | -8% | 1 | 1 | 0% | 2,371 | 3,152 | +33% | 0 | 0 | — |
case-21 | pass→pass | 22,573 | 34,099 | +51% | 1 | 1 | 0% | 2,489 | 4,981 | +100% | 0 | 0 | — |
case-22 | pass→pass | 17,149 | 14,680 | -14% | 1 | 1 | 0% | 1,945 | 2,929 | +51% | 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. 23 cases were attempted. The headline lift of +22 percentage points is the difference between those two pass rates over the 23 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.