# Self Evaluation Writer

> Write your own self-evaluation for the OLX product design team. Use this whenever a product designer wants to draft, write, prepare, or put together their self-evaluation, self-assessment, self-review, or year-end / quarterly / mid-year self-appraisal — even when the request is just "turn my notes into a self-review", "help me write up what I did this cycle", or "here are my achievements, write my self-evaluation". Produces an evidence-cited, first-person draft in the OLX self-evaluation template, anchored to the 4 C's values, the Design Career Blueprint, the 5-point rating scale (with active self-assessment bias-checking), and AI proficiency expectations, then creates it as a Google Doc in a folder you specify. Reach for this skill any time the task is about a designer assessing or writing up their own performance, not just when the word "self-evaluation" appears. Scoped to individual contributor designers (Junior through Principal Product Designer); it does not yet carry the people-manager competency bar, s

- Skill: `alvarsp/self-evaluation-writer` (Agent Skill, multi-file: 7 files)
- Install (CLI): `npx skillmds@latest add alvarsp/self-evaluation-writer`
- Raw SKILL.md: https://api.skillmd.com/api/skills/alvarsp/self-evaluation-writer/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Docs & Writing
- Author: alvarsp (https://skillmd.com/u/alvarsp)
- Updated: 2026-09-22
- Page: https://skillmd.com/skills/alvarsp/self-evaluation-writer

---


# Self-Evaluation Writer (OLX Product Design)

## What this skill is for

A product designer needs to turn a pile of raw material — a list of what they
shipped, their achievements, metrics, their own notes, half-remembered wins — into
a fair, well-argued self-evaluation. The hard part of a self-evaluation isn't the
prose; it's making an honest judgment about your own work that is grounded in
evidence, calibrated to shared standards, and free of the biases that quietly
distort how everyone sees themselves — modesty in one direction, over-claiming in
the other. This skill exists to do that grounding work reliably, so you get a
draft you can trust and refine rather than a blank page and a nagging worry that
you either sold yourself short or oversold.

You decide the rating you want to propose. This skill's job is to build the
honest, evidence-based case for that rating (or, if you ask, to sanity-check
whether your own evidence supports it) and to write it up in the house style, in
your voice.

## The operating model (read this first)

Four things define how this skill works. Hold them throughout.

1. **You own the rating you propose; this skill justifies it.** You tell the
   skill the overall self-rating you want to put forward on the 5-point scale. The
   skill does not invent or override it. Its work is to assemble the evidence that
   supports it and express it convincingly. If the evidence you provide seems to
   point somewhere else, it won't silently comply and won't silently overrule — it
   surfaces the tension plainly so you can decide before your manager does (see
   "When your evidence and self-rating diverge").

2. **Every claim traces to evidence.** This is an *evidence-cited draft*. A
   statement like "raised the quality bar for the team" is worthless — to you and
   to your manager — without the specific thing that shows it. For every strength,
   gap, or rating argument, name the source it came from (a shipped outcome, a
   metric, a project, one of your own notes). During drafting, keep the evidence
   visible so you can verify and later defend each claim in calibration; the skill
   produces a version with inline evidence markers you can trim before submitting.

3. **Frameworks shape judgment, not vocabulary.** The 4 C's, the blueprint
   competencies, and the AI levels are the lens you assess through — they decide
   *what* counts as strong or weak. But the prose stays natural and human. Don't
   pepper the self-evaluation with jargon like "I demonstrate Mastering-level
   Agentic Experience Craft." Say what you actually did and why it mattered. The
   framework should be felt in the accuracy of the judgment, not seen in the
   wording.

4. **Actively fight bias — in both directions.** Self-assessment drifts toward the
   most recent thing that happened, toward the wins that are easy to remember,
   toward taking sole credit for team efforts (or, just as often, toward
   disappearing modestly into "we"). Part of this skill's value is catching that.
   Before finalizing, run the self-assessment bias check in
   `references/rating-scale.md`.

## A note on credit and honesty

Two failure modes sink self-evaluations, and they pull in opposite directions.
**Under-claiming** — impostor-style modesty, burying real impact under "it was a
team effort" — robs you of a fair assessment and leaves your manager without the
evidence they need to advocate for you. **Over-claiming** — taking sole credit for
collaborative work, dressing activity up as impact — is transparent in
calibration and costs you trust. The honest path is neither: state your *actual*
contribution to shared work specifically ("I owned the checkout flow within the
squad's payments redesign"), and let real outcomes carry the weight. This skill
should push you toward that specific, defensible middle.

## Workflow

### Step 1 — Gather what you need

You need these to write a good self-evaluation. If you haven't provided them, ask
for the missing ones together in a single, friendly request rather than
interrogating one at a time:

- **Your name** and **level** (Junior / Mid / Senior / Lead / Principal Product
  Designer). Level is essential — the same work reads as "exceeding" for a Mid and
  "meeting" for a Senior. If unknown, ask; don't guess.
- **Review period** (e.g., "Q1 FY27", "FY26 year-end").
- **The overall self-rating you want to propose** on the 5-point scale. If you
  haven't decided, the skill can propose one from your evidence and flag it clearly
  as a suggestion for you to confirm.
- **Your source material**: any of your achievements list with business outcomes or
  impact, shipped work and links, metrics, goals/OKRs and how they landed, your own
  notes, brag doc, or 1:1 takeaways. This self-evaluation is built from *your own*
  material and outcomes — it does not pull in peer or 360 feedback. More source
  material is better, but work with whatever exists — just be honest in the draft
  about where evidence is thin.
- **The destination**: a Google Drive folder (link or name) where the finished
  Doc should be created.

If a source is missing, that's fine — note internally which lenses you can support
with real evidence and which you can't, so you don't fabricate.

### Step 2 — Read the standards

Read the reference files as needed. They are distilled from OLX's official sources
so you assess against the real bar, not a generic notion of "good":

- `references/rating-scale.md` — the 5-point scale, what each level means, the rule
  that levels 4–5 contain *all* of level 3 plus more, and the self-assessment bias
  checklist.
- `references/values-4cs.md` — the 4 C's (Customer-Led, Commitment, Courage,
  Collaboration) and how each looks at each performance level.
- `references/career-blueprint-ic.md` — the six competency areas and what they look
  like at your level. Use the row for *your* level as the bar. This blueprint is
  IC-only (Junior → Principal PD). If writing a self-evaluation as a design
  *manager*, say plainly that the manager competency bar isn't included yet — you
  can still assess values, rating discipline, and AI proficiency, but flag the
  missing craft/leadership bar rather than improvising one.
- `references/ai-proficiency.md` — AI proficiency levels and the minimum expected
  for your seniority. From Q1 FY27 this is a hard expectation, so a gap here matters
  like any other competency gap.
- `references/output-template.md` — the exact structure of the Google Doc.

### Step 3 — Analyze the evidence against the standards

Go source by source and map each meaningful data point to the lens it speaks to:
which of the 4 C's, which blueprint competency, AI proficiency. Look for
convergence (several pieces of evidence pointing at the same strength carry more
weight than a single instance) and for the difference between *output* (what you
shipped) and *outcome* (what changed for users or the business) — the blueprint and
the values both reward outcomes over activity.

Then hold the picture against your **level**. A Senior is expected to be at
"Mastering" on the blueprint and to shape strategy and mentor; the same deliverable
that would impress from a Mid may simply be meeting the bar for a Senior.
Calibrating to level is where most of the fairness lives — and where honest
self-assessment is hardest.

### Step 4 — Run the self-assessment bias check

Before writing, deliberately test the emerging assessment against the biases in
`references/rating-scale.md`. Ask: am I over-weighting the last month? Only
remembering the wins that were documented? Claiming sole credit for something the
squad did together — or hiding my real contribution behind "we"? Am I inflating to
angle for a promotion, or deflating out of modesty? Adjust the evidence emphasis so
the self-evaluation reflects the whole period, honestly, in both directions.

### Step 5 — Write the draft

Write in the **first person**, as the designer. Fill the template sections (full
detail in `references/output-template.md`):

- **Summary** — a short, honest paragraph capturing the period at a glance: the
  overall shape of your performance, your headline contributions, and your
  trajectory. Written so your manager can absorb it in one pass.
- **Strengths and Impact** — your strongest, best-evidenced contributions, each
  tied to real impact and to the standard it demonstrates. Prioritize outcomes, and
  state your specific contribution to shared work.
- **Areas of growth** — what you want to keep doing and where you want to grow,
  framed developmentally and specifically. Anchor growth areas to the next level of
  the blueprint where it helps show the path. Naming real gaps honestly reads as
  maturity, not weakness — it's what a Solid Performer and above actually do.
- **Rating and Reasoning** — state the self-rating you're proposing, then make the
  case for it: why the weight of evidence across the values, the blueprint, and AI
  proficiency lands at this level and not the one above or below. This is where the
  frameworks do their most explicit work, still in plain language.

Keep the voice honest, specific, and confident without inflation — you, at your
most clear-eyed about your own year. Avoid both false modesty and grandiosity; both
are useless to your manager. Every section should read as though it could only have
been written about *your* work.

Carry inline evidence markers through the draft (e.g., a short parenthetical
pointing to the source: "(shipped: checkout redesign)", "(metric: +12% conversion)",
"(goal: Q2 research repo)") so you can verify each claim and back it up in
calibration, and remember these are there to be trimmed before you submit.

### Step 6 — Deliver the self-evaluation (Google Doc, with fallback)

Once you're happy with the content, deliver it, named `<Name> — Self-Evaluation
<Period>` (e.g., `Maria Silva — Self-Evaluation Q1 FY27`), following the template
structure with "Prepared by" set to your own name.

- **Preferred:** create it as a Google Doc in the folder you specified, using the
  available Google Drive / Docs connector tools, and return the link. If no folder
  was given, ask for one rather than defaulting silently.
- **Fallback:** if no Google Drive / Docs connector is available in this
  environment, don't fail. Deliver the self-evaluation as formatted Markdown in the
  conversation, note that the connector wasn't available, and offer to create the
  Doc once one is connected (or paste it yourself).

Creating the Doc is the preferred finish, but the value of the skill is the
self-evaluation itself — never block delivery on infrastructure.

## When your evidence and self-rating diverge

If you've set a self-rating that your own evidence doesn't clearly support (in
either direction), the skill won't paper over it and won't quietly change it. It
names it in one honest sentence — e.g., "The outcomes here read closer to a Solid
Performer than an Exceeding to me; happy to write it either way, but wanted to flag
it before your manager does." This protects you from a self-rating that won't
survive calibration, which is the whole point. Then it writes whatever you decide.

## What good looks like

A good output is specific (a stranger couldn't have written it), fair (calibrated
to your level, whole-period not recency-driven), honest (names real growth areas
rather than hiding them, and claims real impact rather than burying it), and
traceable (every judgment has evidence behind it that you can defend in
calibration). The self-rating and the narrative agree with each other. Reading it,
you recognize your own year and know exactly what you're arguing for. And it is
*delivered*: created as a correctly-named Google Doc in the folder you specified
(or, if no connector is available, handed over as clean Markdown).