Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Write structured, balanced performance reviews from bullet-point inputs. Use when asked to write a performance review, self-assessment, peer review, 360 feedback, or manager evaluation. Produces a complete, fair, professionally written review covering achievements, areas for growth, and development goals.
.claude/skills/mohitagw15856-performance-review/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-02 | ✗→✓ | ▲ Improved | 62% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 68% | 0% |
| case-04 | ✗→✓ | ▲ Improved | 307% | 0% |
| case-06 | ✗→✓ | ▲ Improved | -10% | 0% |
| case-12 | ✗→✓ | ▲ Improved | 206% | 0% |
This skill turns rough notes, bullet points, or bullet-point memories into a complete, professionally written performance review. Output is ready to submit or use as a strong first draft.
Ask the user for these if not provided:
Role: Title / Level] Review period: Period] Review type: Manager / Self / Peer / Upward] Reviewed by: If known]
3–5 sentences. High-level characterisation of the period. Acknowledge standout contributions. Be specific — use project names and outcomes, not vague praise. For self-assessments, this should reflect honestly on the period without underselling or overselling.]
3–5 achievements, each structured as:]
Achievement title — specific and concrete] 2–4 sentences. What was the context? What did name] do specifically? What was the measurable or observable outcome? Avoid generic praise — every sentence should be something only this person could have done.]
3–4 bullet points. Each bullet = one strength, with one concrete example from the review period. No abstract traits without evidence.]
2–3 areas. Be direct and constructive — not vague. Frame as "opportunity to develop" not "failure." Each should include:]
Area name]
2–3 goals. Format each as:]
Goal N]: Clear, outcome-oriented goal]
| Competency | Rating | Evidence | |---|---|---| | Competency from company framework] | Exceeds / Meets / Developing / Below] | One-sentence example] |
2–3 sentences. For manager reviews: overall assessment and any promotion/compensation recommendation. For self-assessments: what you're asking for or committing to. For peer reviews: one sentence on what it's like to work with this person.]
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 20,360 | 30,708 | +51% | 1 | 1 | 0% | 2,370 | 3,675 | +55% | 0 | 0 | — |
case-02 | fail→pass | 18,856 | 19,931 | +6% | 1 | 1 | 0% | 2,291 | 3,710 | +62% | 0 | 0 | — |
case-03 | fail→pass | 16,421 | 17,396 | +6% | 1 | 1 | 0% | 1,851 | 3,105 | +68% | 0 | 0 | — |
case-04 | fail→pass | 11,880 | 26,922 | +127% | 1 | 1 | 0% | 969 | 3,944 | +307% | 0 | 0 | — |
case-05 | fail→fail | 17,552 | 25,660 | +46% | 1 | 1 | 0% | 1,535 | 4,357 | +184% | 0 | 0 | — |
case-06 | fail→pass | 20,779 | 10,345 | -50% | 1 | 1 | 0% | 1,979 | 1,789 | -10% | 0 | 0 | — |
case-07 | fail→fail | 16,064 | 15,042 | -6% | 1 | 1 | 0% | 1,639 | 2,452 | +50% | 0 | 0 | — |
case-08 | fail→fail | 24,455 | 33,608 | +37% | 1 | 1 | 0% | 2,065 | 5,075 | +146% | 0 | 0 | — |
case-23 | pass→pass | 18,562 | 17,500 | -6% | 1 | 1 | 0% | 2,196 | 2,709 | +23% | 0 | 0 | — |
case-09 | fail→fail | 17,005 | 27,762 | +63% | 1 | 1 | 0% | 1,605 | 4,742 | +195% | 0 | 0 | — |
case-10 | pass→pass | 19,516 | 30,697 | +57% | 1 | 1 | 0% | 2,097 | 4,394 | +110% | 0 | 0 | — |
case-11 | fail→fail | 11,363 | 19,445 | +71% | 1 | 1 | 0% | 955 | 2,835 | +197% | 0 | 0 | — |
case-12 | fail→pass | 15,394 | 12,800 | -17% | 1 | 1 | 0% | 783 | 2,399 | +206% | 0 | 0 | — |
case-13 | fail→fail | 8,852 | 10,019 | +13% | 1 | 1 | 0% | 511 | 1,780 | +248% | 0 | 0 | — |
case-14 | fail→pass | 11,261 | 33,850 | +201% | 1 | 1 | 0% | 955 | 2,508 | +163% | 0 | 0 | — |
case-15 | pass→pass | 16,134 | 23,582 | +46% | 1 | 1 | 0% | 1,580 | 2,495 | +58% | 0 | 0 | — |
case-16 | fail→pass | 20,013 | 17,892 | -11% | 1 | 1 | 0% | 1,591 | 3,415 | +115% | 0 | 0 | — |
case-17 | pass→pass | 20,463 | 27,857 | +36% | 1 | 1 | 0% | 1,942 | 4,095 | +111% | 0 | 0 | — |
case-18 | pass→pass | 18,856 | 33,601 | +78% | 1 | 1 | 0% | 2,204 | 5,546 | +152% | 0 | 0 | — |
case-19 | fail→pass | 13,553 | 9,027 | -33% | 1 | 1 | 0% | 756 | 2,065 | +173% | 0 | 0 | — |
case-20 | fail→pass | 14,820 | 11,732 | -21% | 1 | 1 | 0% | 1,283 | 2,199 | +71% | 0 | 0 | — |
case-21 | pass→pass | 11,917 | 12,017 | +1% | 1 | 1 | 0% | 1,033 | 2,044 | +98% | 0 | 0 | — |
case-22 | fail→pass | 15,109 | 12,280 | -19% | 1 | 1 | 0% | 1,476 | 2,165 | +47% | 0 | 0 | — |
case-24 | pass→pass | 21,914 | 22,012 | +0% | 1 | 1 | 0% | 2,705 | 3,497 | +29% | 0 | 0 | — |
case-25 | pass→pass | 78,343 | 22,422 | -71% | 1 | 1 | 0% | 3,046 | 4,157 | +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. 25 cases were attempted. The headline lift of +40 percentage points is the difference between those two pass rates over the 25 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.