nanaagyei/noetherkin / skills/task-assignment
task-assignment
VerifiedDefine 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.
assets/proposal.md
View on GitHub# Unpublished proposal
## Request and identity
State the learner's request, originating skill, workspace, known learner identity, requested role, and observed actor/binding or why those are unresolved. Give this revision's filename and predecessor, if any. This document does not grant a role or authorize publication.
## Referenced inputs
Separate canonical records, inspected artifacts, learner self-report and draft dependencies. For each, record its path/URI, exact available revision or tool-computed digest, and what was actually inspected. Pin each draft dependency to a revision file. Explain missing or unverified inputs.
## Proposed change and rationale
Describe the intended records or field changes, their purpose, and the learner decision they support. Separate observations from interpretations. Mark unresolved canonical IDs, fields and prerequisites explicitly. Do not present an incomplete candidate as schema-valid.
## Assistance and evidence limits
Describe actual assistance, provider/recorder as known, affected claims and observed timing or unknowns. Cite real response/run artifacts only; distinguish proposed checks from results. Explain contrary evidence and limits on independence claims.
## Reconciliation
For a new revision, explain changed inputs or dependencies, differences from the predecessor, and which conclusions require fresh review. For an initial revision, say that there is no predecessor. Earlier approvals remain attached to their earlier revisions.
## Publication blockers and next action
List missing inputs, role grants, trusted binding, runtime capabilities and validation coverage. Identify the next learner action and required workflow. Keep canonical prerequisites pending. A learner-approved draft remains unpublished and cannot be copied into canonical state as a substitute for publication.
## Review
Point to actual entries in the sibling `reviews.md` if they exist; otherwise state “Not yet reviewed.” Do not invent a log entry. Review decisions must identify this exact revision and do not authorize a revised successor.
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: 471k | 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: 322k | 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: 322k | 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: 322k | Updated | Claude CodeCodex | Verified | Install |