nanaagyei/noetherkin / skills/task-assignment
task-assignment
UnverifiedDefine a bounded, testable Noetherkin assignment and its investigation prompt without revealing the solution. Use when a learner requests next work or a manager recommends new scope; execution gates belong to team-lead.
Task assignment
Read runtime limits, your contract, and shared conventions. Assignment is a team-lead responsibility, not a separate principal.
Before reading source, follow the context budget in shared conventions: read a checked map first, then only the uncovered, in-scope paths, and say when you read source. A map that is not checked stays the learner's unverified claim even when the learner asks you to trust it; read the source instead. If source contradicts a map claim, say so and invite the learner to correct their map. If you need files outside the task scope, say so and note that widening scope takes a replacement task from the team lead.
- Inspect learner goals, canonical onboarding/baseline, selected project snapshot and source binding, relevant tasks and available capability evidence. State unresolved prerequisites; approved drafts cannot establish assignment eligibility. Catalog fixtures cannot support live assignments. When the request explicitly asks for hypothetical level calibration, evaluate the requested level's task shape without treating the fictional learner's current standing as an eligibility gate. Keep the output noncanonical and conditional on source binding, and do not redirect to a lower level unless requested. Current evidence still governs any later live assignment.
- Identify the actual problem and observable success. If unclear, ask the smallest question that establishes problem or impact. Set TRAINING for a labeled simulated exercise, PRODUCT for learner-local improvement, or UPSTREAM for an intended contribution without submission authority. Never invent upstream demand or acceptance.
- Propose bounded scope, supported competency IDs, unique criterion labels, test expectations, constraints and documentation needs using the task schema. Use the competency catalog and rubric to explain fit without promising advancement.
- Default design and code review to required. Any allowed waiver needs its rationale before assignment under lifecycle rules. Preserve the entire frozen assignment; new criteria or changed scope require replacement work, not edits to an assigned contract.
- When the bound project has a curated pack, use
task assign: for a compatible PetClinic checkout it instantiatespet-type-integrity, and for a forge project the next task in pack order, each as a frozen TRAINING task with its backlog-to-assigned history. Use a proposal for other tasks, with unresolved IDs and publication prerequisites explicit.
Give one learner investigation prompt without the architecture map, root cause, solution or implementation. Before implementation, elicit their prediction, approach, defended alternatives and failure cases appropriate to the stakes. Assignment itself creates no capability evidence.
Return the proposed task, scope rationale, waiver explanations when applicable, and next learner action. Refer execution/design/acceptance to team-lead and help to teach or peer-engineer; explain the workflow if the corresponding skill is not installed. The reference index contains the remaining record shapes and provenance.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 467k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 319k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 319k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 319k | Updated | Claude CodeCodex | Verified | Install |