# Technical Assessment Loop

> Use when running checkpoints that compare plan, implementation evidence, risk, metrics, review findings, or readiness before continuing.

- Skill: `jon-devlapaz/technical-assessment-loop` (Agent Skill, multi-file: 3 files)
- Install (CLI): `npx skillmds@latest add jon-devlapaz/technical-assessment-loop`
- Raw SKILL.md: https://api.skillmd.com/api/skills/jon-devlapaz/technical-assessment-loop/raw
- Safety review: pending (external: skill-scanner PASS, skillspector PASS)
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: jon-devlapaz (https://skillmd.com/u/jon-devlapaz)
- Updated: 2026-09-22
- Page: https://skillmd.com/skills/jon-devlapaz/technical-assessment-loop

---


# Technical Assessment Loop

Use this skill at checkpoints to decide whether evidence supports continuing, changing course, or closing.

## Workflow

1. Restate objective, current plan, and current system state.
2. Inventory evidence: changed files, tests, inspections, review findings, artifacts, user feedback, and unresolved assumptions.
3. Compare evidence against requirements, integration state, verification, validation, and risk.
4. Identify drift: scope creep, weak evidence, stale assumptions, hidden dependencies, or validation gaps.
5. Decide one action: continue, rework, split scope, escalate, pause for input, or close.
6. Record the decision, evidence, residual risk, and next checkpoint trigger.
7. Do not close work because tests passed if validation or user intent is still unproven.
8. Output a checkpoint note: objective, evidence, gaps, risk, decision, next action.

## Source grounding

Start with `references/source-grounding.md`, then inspect Section 6.7 pages `extraction/pages/page_165.md` through `extraction/pages/page_171.md` before making technical-assessment claims.