# Assessing Developer Proficiency

> Use when a developer needs an evidence-aware diagnosis of current capabilities, confidence, unknowns, and weakly demonstrated areas before deciding what to improve.

- Skill: `jhonatan-oliveiradev/assessing-developer-proficiency` (Agent Skill)
- Install (CLI): `npx skillmds@latest add jhonatan-oliveiradev/assessing-developer-proficiency`
- Raw SKILL.md: https://api.skillmd.com/api/skills/jhonatan-oliveiradev/assessing-developer-proficiency/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: jhonatan-oliveiradev (https://skillmd.com/u/jhonatan-oliveiradev)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/jhonatan-oliveiradev/assessing-developer-proficiency

---


# Assessing Developer Proficiency

Establish a current capability baseline from evidence, not confidence theater. The result should make demonstrated strengths, uncertainty, and missing evidence explicit enough for another method to act on.

## Build the evidence inventory
Start with the target role or capability set, then collect only evidence relevant to the current-state question:
- self-reported experience and confidence;
- conceptual explanations or knowledge checks;
- code-reading and technical-reasoning observations;
- implementation or debugging performance;
- authentic project artifacts and their provenance.

Keep claims separate from observations. Missing evidence is an unknown, not a low score.

## Map evidence to fixed criteria
Use the capability definitions supplied by the product, assessment blueprint, or explicit evaluation contract. For each capability:
1. identify which observable criteria are supported;
2. respect required evidence dimensions and blocking gates;
3. determine the highest level actually demonstrated;
4. record the evidence IDs or artifacts supporting that conclusion;
5. retain contradictions rather than averaging them away.

Do not invent a new definition of proficiency because the available evidence is inconvenient.

## Derive confidence separately
Describe confidence from evidence strength, diversity, consistency, quantity, recency, and provenance. A strong level with old or contradictory evidence may legitimately be `proficient / low confidence`.

Self-report alone cannot establish proficient or advanced capability. External unverified artifacts may inform the baseline, but should remain explicitly unverified until independently reproduced or checked.

## Report the baseline
Return a compact diagnosis with:
- demonstrated capability state;
- confidence for each state;
- evidence used;
- unknown or weakly evidenced areas;
- contradictions or stale evidence;
- recommended reassessment targets where uncertainty matters.

Prefer named capability gaps over a synthetic overall score.

## Ownership boundaries
This method owns **current-state diagnosis and uncertainty**. It does not sequence a roadmap, teach the missing material, redefine assessment criteria, or prioritize gaps from job-market demand. Hand those decisions to their dedicated methods.