Review PRs, branches, diffs, and workflow artifacts for package-level go/no-go readiness with severity-ranked synthesis. Use when users need readiness synthesis rather than detailed technical-risk critique.
62
73%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Failed to scan
The risk profile of this skill
Fix and improve this skill with Tessl
tessl review fix ./Plugins/harness-engineering/fixtures/budget-archive/2026-04-21/deferred-store/skills/code_quality_review/he-code-review/SKILL.mdUse when package-level readiness, merge risk, release go/no-go, or tracked PR closure is the core question.
Context disposition: Apply the context-disposition policy: move important still-valid context to references and index it when meaningful; intentionally discard stale, duplicated, unsafe, superseded, or low-signal text.
Use he-code-review when the user wants a package-level readiness verdict for a PR, branch, diff, or delivery slice.
go, go-with-conditions, or no-go recommendation.he-work, autofix, security-ops, or GitHub PR workflow when required.P0-P3; discard style-only, speculative, duplicate, and protected-artifact cleanup notes.go, go-with-conditions, or no-go.For tracked delivery, verify:
Linear issue -> spec/source acceptance IDs -> plan units -> PR evidence -> validation
Do not treat branch names, PR titles, or resolver claims as closure. A clean go requires behavior and validation evidence tied back to Linear and the governing artifacts.
go for unresolved P0/P1, actionable reviewer threads, relevant failing checks, stale conflicts, missing validation, or missing Linear/spec/plan/PR traceability.python3 Infrastructure/scripts/validation-and-linting/he_linear_traceability_lint.py <artifact-path> before returning a go verdict.security-ops or a security reviewer.If the base, target, review scope, or required tracker/spec/plan evidence is missing, stop and request that source instead of giving a false readiness verdict.
Plugins/harness-engineering/fixtures/preserved-context/skills/he-code-review/SKILL.full.mdPlugins/harness-engineering/fixtures/preserved-context/skills/he-code-review/references/codex-review-flow.mdPlugins/harness-engineering/fixtures/preserved-context/skills/he-code-review/references/review-modes.mdPlugins/harness-engineering/references/subagent-routing.mdPlugins/harness-engineering/references/domain-model-routing.md, Plugins/harness-engineering/references/qa-intake-routing.md2f91362
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.