Menu
Rubric-based readiness assessment before task completion or phase transition
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
One-command project setup for OpenUP - interactive initialization wizard
Mark a task as complete, update roadmap, commit changes, and prepare traceability logs
Execute an already-claimed lane's Operations boxes with script/judgment classification — script steps run directly with zero self-brief, judgment steps self-brief and execute. Handles only pick/resume; every other resolve path routes to /openup-next.
Run OpenUP Assess Results at iteration end — check evaluation criteria, demo only completed acceptance-tested work, feed discovered work back, and trigger the milestone review at a phase boundary
Run the phase milestone go/no-go — prepare derived evidence, pause for the human decision via an input-request, and record the milestone (never advance the phase itself)
Begin a new OpenUP iteration with proper phase context and task selection
| name | openup-assess-completeness |
| description | Rubric-based readiness assessment before task completion or phase transition |
| model | inherit |
| fit | {"great":["pre-merge quality gate","phase transitions","artifact rubric grading"],"ok":["mid-iteration sanity checks on partially-built artifacts"],"poor":["pure code changes with no rubric to grade against","exploratory work"]} |
| arguments | [{"name":"scope","description":"Assessment scope (task, iteration, phase)","required":false},{"name":"artifact","description":"Work product type to assess against its rubric (use-case, architecture-notebook, iteration-plan, test-plan, vision). Auto-detected if not provided.","required":false},{"name":"strict","description":"Fail on any missing items (true/false, default: false)","required":false}] |
Rubric-based readiness assessment to verify all required work is complete before marking a task done, completing an iteration, or transitioning phases.
For work product artifacts (use cases, architecture notebooks, etc.), this skill grades each quality criterion explicitly — producing a per-criterion breakdown rather than a generic pass/fail.
Based on $ARGUMENTS[scope] (defaults to "task"):
| Scope | Focus | Typical Checks |
|---|---|---|
| task | Single task completion | Code, tests, docs, commit |
| iteration | Iteration completion | All tasks, metrics, goals met |
| phase | Phase transition | Phase criteria, artifacts |
If the task involves a work product artifact, load the appropriate rubric and grade each criterion explicitly.
Detect artifact type (use $ARGUMENTS[artifact] if provided, otherwise auto-detect):
docs/use-cases/*.md was modified → use-case rubricdocs/architecture-notebook.md was modified → architecture-notebook rubricdocs/iteration-plan.md was modified → iteration-plan rubricdocs/test-plan.md was modified → test-plan rubricdocs/vision.md was modified → vision rubricdocs/changes/*/plan.md is the artifact (or $ARGUMENTS[artifact] == "task-spec") → task-spec rubricLoad rubric from .claude/rubrics/<artifact-type>-rubric.md
Grade each criterion in the rubric:
✅ [criterion name] — fully satisfied❌ [criterion name] — [specific gap description] — what exactly is missingDeterministic pre-check for task-spec — before grading criterion 11
(Scenario Coverage) by reading, run the structure validator and let its exit
code decide the criterion:
python3 scripts/openup-spec-scenarios.py check docs/changes/<task_id>/plan.md
# exit 0 → every requirement carries a Given/When/Then scenario (or quick track, exempt)
# exit 1 → a requirement lacks a scenario (criterion 11 is ❌; the offending requirements
# are listed on stderr — fix the spec, do not grade around it)
# exit 2 → malformed spec (no ## Requirements section, or file missing)
Pass --track <track> (read from .openup/state.json) when the spec's
frontmatter has no track. A quick-track spec is exempt — criterion 11 is then
marked n/a (quick track), not ❌.
Rubric result:
satisfied — all criteria are ✅ → proceedneeds_revision — any criteria are ❌ → do not mark complete; fix gaps and re-assessIf needs_revision: address each ❌ gap, then re-run this assessment. Continue iterating until all criteria are satisfied.
Task Scope:
git status --porcelainsatisfiedIteration Scope (all task checks plus):
Phase Scope (all iteration checks plus):
Output a structured report:
## Completeness Assessment
Scope: [task|iteration|phase]
Date: [today]
### Work Product Quality (Rubric Assessment)
[If artifact assessed:]
Artifact: [type]
[Per-criterion grading output]
Result: satisfied | needs_revision
### Process Checks
[Each check with ✅ or ❌]
### Overall
Status: PASS | FAIL
[If FAIL: list specific items to address before re-running]
If $ARGUMENTS[strict] == "true": any ❌ results in FAIL and the skill stops. Otherwise: provide specific gaps; the agent should address them before proceeding.
Returns: assessment scope, rubric grading (if applicable), process checks, overall pass/fail status, specific gaps to address.