Implement approved Harness Engineering work. Use when a plan, todo list, or tiny spec needs traceable delivery and validation.
46
48%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./Plugins/harness-engineering/fixtures/budget-archive/2026-04-21/deferred-store/skills/team_automation/he-work/SKILL.mdUse when implementation is expected from an approved plan, todo list, or tightly scoped low-risk spec.
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still-valid context to references and index it when meaningful; intentionally discard stale, duplicated, unsafe, superseded, or low-signal text.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-work when the user wants approved Harness Engineering work implemented with traceable progress and validation evidence.
plan-led, todo-led, or narrow small-spec-direct before editing.Final handoff must record completed IDs, validation evidence, PR link or pending-PR blocker, and Linear update/comment result. Do not ship tracked work with only a PR link; tie PR evidence back to Linear and the governing plan/spec.
python3 Infrastructure/scripts/validation-and-linting/he_linear_traceability_lint.py <artifact-path> before claiming completion.If the governing artifact is missing, Linear context is required but absent, or validation cannot prove the delivered slice, stop and report the blocker before continuing.
Plugins/harness-engineering/fixtures/preserved-context/skills/he-work/SKILL.full.mdPlugins/harness-engineering/fixtures/preserved-context/skills/he-work/references/handoff-and-shipping.mdPlugins/harness-engineering/fixtures/preserved-context/skills/he-work/references/execution-modes.mdrepo:Plugins/harness-engineering/skills/shared/references/approval-flow.mdPlugins/harness-engineering/references/session-evidence-contract.mdPlugins/harness-engineering/references/subagent-routing.mdPlugins/harness-engineering/references/domain-model-routing.mdd00c351
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.