SkillVaultskills Browse all 500 skills

People Operations · Version 1.0.0 · Reviewed 2026-08-02

Performance Review Evidence Editor

Make evidence-based feedback and impact and expectation clarity with evidence, explicit trade-offs, and a verification plan.

4 method steps 6 documented failure modes 5 diagnostic checks 7 quality gates

Rewrites performance feedback around observable behavior, scope, impact, expectations, and development actions while removing vague personality judgments.

₹149 one-time

Get this skill archive

What this skill helps you do

  • Evidence-based feedback
  • Impact and expectation clarity
  • Development action design

How Performance Review Evidence Editor works

You provide

Schema, query plans, and the real access pattern

It inspects

Plan accuracy and lock behavior for evidence-based feedback

It decides

A impact and expectation clarity change weighed against write cost

You verify

Re-measured plan with buffer reads and timing compared

What it checks first

Performance Review Evidence Editor rewrites performance feedback around observable behavior, scope, impact, expectations, and development actions while removing vague personality judgments. Use it when the work involves Evidence-based feedback, Impact and expectation clarity, Development action design.

  1. The actual query plan with real row counts, not the estimated plan or the query text alone.
  2. Whether the workload is read-heavy, write-heavy, or mixed, since the correct design differs sharply.
  3. Transaction boundaries and duration, because long transactions block vacuum and hold locks.
  4. Index coverage relative to both the filter and the sort, since satisfying one but not the other still costs a sort.
  5. Connection pool behavior, as pool exhaustion presents as database slowness while the database is idle.

Failure modes it recognizes

  • An index that serves the predicate but not the ordering, forcing a full sort for a small LIMIT.
  • A long-running transaction preventing vacuum and causing gradual bloat and plan degradation.
  • Implicit type casting on a join or filter column silently disabling index use.
  • Connection pool exhaustion from long-held connections, appearing as a database problem.
  • A write-heavy table with excessive indexes where insert cost dominates the workload.
  • Statistics stale after a bulk load, so the planner chooses a plan for a table size that no longer exists.

Answers it will reject

  • Adding an index per slow query until write amplification becomes the new bottleneck.
  • Tuning configuration parameters before examining the plan for the dominant query.
  • Interpreting `EXPLAIN` without `ANALYZE`, which reports estimates and proves nothing.
  • Increasing pool size to fix latency caused by lock contention, which adds waiters rather than capacity.

Decision rules it applies

  • Optimize the query that dominates total time, not the one that feels slowest in isolation.
  • Order composite index columns by equality first, then range or sort last.
  • Keep transactions short and never hold one open across an external call.
  • Create and drop indexes concurrently on live tables, accepting the longer build for the absent lock.

Evidence it asks for

  • `EXPLAIN (ANALYZE, BUFFERS)` to compare estimated with actual rows and attribute I/O.
  • Rank queries by cumulative execution time rather than by single-execution latency.
  • Monitor the oldest open transaction and lock wait counts as standing metrics.

The method inside

  1. Define the decision criterion before reading the evidence
  2. Separate observation from interpretation and bias
  3. Check consistency across people, segments, or reviewers
  4. Produce actionable language while preserving confidentiality

Deliverables

  • Evidence-based feedback evidence assessment
  • Impact and expectation clarity consistency findings
  • Development action design action-ready revision

Evidence requirements

  • Role rubric, policy, survey, or review artifact
  • Observable behavior and outcomes
  • Relevant context with unnecessary personal identifiers removed

Quality gates

  • Every material claim traces to supplied evidence or is labeled as a hypothesis.
  • The response follows the declared deliverable contract.
  • No execution, access, measurement, or verification is invented.
  • Secrets and personal data are redacted rather than repeated.
  • The user receives a concrete independent verification step.
  • The relevant failure modes in this domain were considered rather than only the reported symptom.
  • No listed anti-pattern was recommended as a solution.

Example task

Input

Edit this performance review so it is specific, fair, and useful without softening the difficult feedback.

Expected output

“Not strategic” is replaced with two observable planning gaps and their downstream impact. The review now states the expected behavior, a 90-day practice goal, and evidence that would demonstrate improvement...

Boundaries and compatibility

Ideal for

  • Evidence-based feedback: produce a decision or artifact grounded in supplied evidence.
  • Impact and expectation clarity: produce a decision or artifact grounded in supplied evidence.
  • Development action design: produce a decision or artifact grounded in supplied evidence.

Out of scope

  • Making employment decisions without accountable human review
  • Inferring protected characteristics or psychological states

Agent compatibility

  • GitHub Copilot custom agents
  • Claude Agent Skills / SKILL.md
  • Any instruction-following chat model

Tool policy: Advisory by default. No tools are assumed. If the host provides tools, use read-only evidence gathering unless the user explicitly approves a scoped write or execution action.