assess

Assess

Authority

Assess reconciles one exact target/base/head with the original user request, authoritative requirements, any available Blueprint, repository rules, tests, and base behavior. Snapshot every used external target, authority, evidence, proof, or diagnosis; Git/repository-local truth needs none. Unknown required external currentness means blocked.

The assessment is read-only: never repair, edit the target, merge, approve, or mutate GitHub. Construct owns implementation; Diagnose owns broader defect/risk investigation. assessment.md is a result, never approval, certification, or merge authority. Posting its findings is a separate step after check, only on the user's explicit yes.

Assessment

If you wrote or planned this change in this context, hand the whole stage to a fresh-context owner per the Bounded Delegation Protocol, reading nothing else; read it before any other delegation too.

Otherwise first read assess guidance, plus Blueprint evidence when a sealed Blueprint exists, delta review when an earlier assessment does, and pull requests when the target pull request's head may be missing from the current repository. Establish exact target/base/head, current authority, base truth, and requested delta once. Derive requirements from authority and the change from base/head before reading PR prose, comments, audits, or prior reviews; those are hints that may add candidates, never clear one.

Then, at any change size, consult reason before committing to the assessment approach: full or delta review, scope, and depth.

Author and seal

Copy the minimal bundle template outside the skill and target repository and fill it per the guidance's bundle fields; it has no default verdict. Prepare a new slug first; sealing accepts only its ignored .first-four-hours/assessments/<slug>/assessment.md and never replaces one. The agent decides currentness, depth, compliance, severity, findings, limitations, Diagnose need, and result; scripts verify only shape, exact Git/snapshot identity and freshness, locators, safe output, and integrity.

python /absolute/skill-root/scripts/cli.py --repo-root /absolute/repo \
  --input slug=<slug> --format json prepare
python /absolute/skill-root/scripts/cli.py --repo-root /absolute/repo \
  --input bundle=/absolute/assessment-bundle.json \
  --input output=<prepared output_path> --format json run

Result precedence: blocked when unavailable or contradictory authority/evidence/proof prevents a trustworthy result; else findings, reporting every independently material defect discovered in the bounded assessment; else clear. assessment.md holds only the compact result.

Complete

python /absolute/skill-root/scripts/cli.py --repo-root /absolute/repo \
  --input output=<prepared output_path> --format json check

Report the sealed result, path, and each finding's severity, defect, and scenario as sealed, with no approval or readiness claim beyond it. When the result is findings and target is a pull request's URL, read publishing and offer to post them. Stop after one current assessment.md is sealed and checked and any offer is settled. End with one optional next step fitting this outcome: a fenced, self-contained prompt naming any repository, issue, PR, or artifact it needs, or say none is needed. Only a "yes" starts it, via any skill it names, but the user runs a charter, diagnose, or ticket step as its /<skill> command.