Skip to content

nanaagyei/noetherkin / skills/task-assignment

task-assignment

Verified

Define 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.

FileKindSize
SKILL.mdskill md3.7 KB
assets/proposal.mdmarkdown2.0 KB
references/FOUNDATION_V1.mdmarkdown5.4 KB
references/OPEN_QUESTIONS.mdmarkdown3.5 KB
references/PROJECT_CHARTER.mdmarkdown6.4 KB
references/apprenticeship-config.schema.jsonconfig3.0 KB
references/architectural-invariants.mdmarkdown2.3 KB
references/assessment.schema.jsonconfig5.0 KB
references/assistance-model.mdmarkdown4.0 KB
references/attention-advisory.schema.jsonconfig3.8 KB
references/bundle.jsonconfig12.0 KB
references/cli.mdmarkdown18.6 KB
references/competencies.yamlconfig37.7 KB
references/competency-model.mdmarkdown5.0 KB
references/competency-state.schema.jsonconfig3.4 KB
references/conformance.mdmarkdown22.0 KB
references/contract-README.mdmarkdown6.9 KB
references/contract-manager.mdmarkdown2.4 KB
references/contract-task-assignment.mdmarkdown3.2 KB
references/contract-team-lead.mdmarkdown2.8 KB
references/current-project.schema.jsonconfig2.3 KB
references/current-track.schema.jsonconfig1.5 KB
references/evidence-model.mdmarkdown4.1 KB
references/evidence.schema.jsonconfig10.3 KB
references/forge.schema.jsonconfig9.5 KB
references/index.mdmarkdown3.6 KB
references/judgment-validity.mdmarkdown6.6 KB
references/learner-profile.schema.jsonconfig1.5 KB
references/leveling-framework.mdmarkdown3.4 KB
references/levels.yamlconfig8.0 KB
references/overview.mdmarkdown2.9 KB
references/permissions-model.mdmarkdown6.7 KB
references/project.schema.jsonconfig9.4 KB
references/proposals.mdmarkdown4.2 KB
references/review-model.mdmarkdown7.2 KB
references/review.schema.jsonconfig13.0 KB
references/runtime.mdmarkdown7.8 KB
references/selection-model.mdmarkdown6.1 KB
references/simulation-lifecycle.mdmarkdown8.0 KB
references/state-model.mdmarkdown13.7 KB
references/task.schema.jsonconfig13.8 KB
references/track.schema.jsonconfig1.3 KB

references/OPEN_QUESTIONS.md

View on GitHub
# Open questions

No unresolved BLOCKING question remains for the V1 specification. The following product choices are exposed for maintainer review; current V1 behavior is explicit and does not depend on their resolution. Implementers must not silently change that behavior. The freeze resolves all BLOCKER/HIGH review findings; the IMPORTANT and LATER labels below are non-blocking priorities, not missing protocol decisions.

| ID | Class (all NON-BLOCKING) | Question | Current V1 decision and recommendation |
| --- | --- | --- | --- |
| OQ-001 | IMPORTANT | How should independent reviewers be calibrated against systematic model bias? | Separate principals and independently recorded judgments, with learner-authorized review. Recommend human-audited calibration scenarios before claiming trustworthy promotion quality. Multiple model vendors remain optional. |
| OQ-002 | IMPORTANT | How should disputed or revoked promotions be handled? | ACP-01 defines unresolved standing and ordered reconciliation through fresh authorized reviews. V1 has no demotion/revocation or discretionary appeal override. A future appeal policy is optional and cannot block the specified repair path. |
| OQ-003 | IMPORTANT | Should evidence recency have specialization-specific guidance? | Reviewer explains recency relative to context and technology changes. Recommend empirical calibration; do not invent universal expiry days. |
| OQ-004 | RESOLVED IN PHASE 6 | When can a project candidate be labeled supported? | Spring PetClinic Microservices is the one supported live catalog project. Selection requires exact repository identity, a full pinned commit and revision-aware task compatibility probes. The example state remains fixture-only. |
| OQ-005 | IMPORTANT | What protects local records against deliberate tampering? | Explicit provenance, immutable review policy, local history and role checks; no credential-grade assurance. Recommend threat modeling before multi-user or credentialing use. |
| OQ-006 | LATER | How should concurrent writers coordinate? | V1 single writer, stale-digest checks and crash-recoverable transactions. Recommend experience with a vertical slice before adding distributed locks or event sourcing. |
| OQ-007 | LATER | What artifact retention and redaction policy is needed? | Persist safe minimal artifacts, disclose unverifiable material, mark dependent judgments stale if evidence disappears. Recommend explicit retention/consent policy before hosted storage. |
| OQ-008 | LATER | Which additional skills should cover promotion, incidents and specialization? | Twenty-one contracts now exist, including a proposal-only promotion-review contract. Promotion execution stays manual by the prescribed principals; automating it needs its own proposal. |
| OQ-009 | LATER | Should levels allow specialization-specific titles or lateral progression? | Fixed E0–E5 internal levels, adjacent promotion only, with separate competency findings. Recommend preserving this separation in any extension. |

| OQ-010 | LATER, NON-BLOCKING | Can project metadata explicitly represent absent contribution guides or organizations (F18)? | V1 admits only catalog entries with truthful values for required fields. Incomplete candidates remain read-only suggestions outside the catalog; do not invent URLs or organizations. A future schema may support explicit absence. This does not block the supported V1 catalog contract. |

If Agent 2 discovers a contradiction requiring a foundational semantic choice, classify it BLOCKING and write an architecture change proposal. Do not disguise it as an implementation detail.
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: 471kUpdated Claude CodeCodexVerifiedInstall
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: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
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 availableStars: 322kUpdated Claude CodeCodexVerifiedInstall