원클릭으로
oat-explainer-kit
Use when building project explainers or recaps from OAT configuration, state, and lifecycle artifacts.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
메뉴
Use when building project explainers or recaps from OAT configuration, state, and lifecycle artifacts.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Run when you need to evaluate agent instruction file coverage, quality, and drift. Produces a severity-rated analysis artifact. Run before oat-agent-instructions-apply to identify what needs improvement.
Use when OAT work is mentioned in a Cursor Cloud environment. Orients agents to cloud detection, repo-rooted project homes, user-first assets, CLI availability, and Cursor dispatch context without owning lifecycle execution.
Use when an OAT skill or workflow needs provider-neutral selection, launch, recovery, or evidence for bounded subagent work without project lifecycle policy.
Use when an OAT project lifecycle skill needs to translate project state, phase or task scope, gates, and write authority into a provider-neutral subagent dispatch.
Use when the user requests or confirms documenting an active OAT project — e.g. "document the project", "update the docs", "run oat-project-document", or confirms a previously offered documentation run. Do NOT auto-invoke when implementation completes. Analyzes project artifacts, presents a documentation delta plan, and applies approved changes.
Use when plan.md is ready for execution. Dispatches one phase implementer per phase, owns independent phase review and bounded fix routing, and supports plan-declared worktree-isolated parallel phases.
| name | oat-explainer-kit |
| version | 1.0.1 |
| description | Use when building project explainers or recaps from OAT configuration, state, and lifecycle artifacts. |
| disable-model-invocation | false |
| user-invocable | true |
| allowed-tools | Read, Write, Edit, Bash, Grep, Glob, AskUserQuestion |
| metadata | {"internal":true} |
Adapt OAT project context into the versioned request consumed by the canonical
explainer-kit core.
explainer-kit core.This adapter depends on explainer-kit; the core never depends on this adapter.
Fail closed when the compatible installed core is unavailable. Do not copy core
runtime logic into the adapter.
Private wrappers use the core's frozen pre-resolution/request/core-run/manifest/
post-run seam directly; they do not route presets, vaults, Google Docs, Stoa, or
personal destinations through this adapter. For the release-candidate sequence,
rollback, and operator-owned real-wrapper gate, use references/migration.md.
Before reading OAT config or invoking the core, call
scripts/check-core.mjs#checkCoreCompatibility with this installed skill
directory and minimum core version 1.0.0. Continue only when it returns
ok: true.
oat tools install utility --scope user.oat tools update --pack utility --scope user.Resolve adapter scripts and references relative to this installed skill directory. Resolve the core only from its installed canonical skill path. Never fall back to a repository source checkout.
Call scripts/run.mjs#runOatExplainer with the repository root, project
invocation, active project path, recipe, slug, lifecycle mode, and any explicit
runtime overrides. The adapter:
1.0.0;explainers.* and workflow.explainers.* keys;project source set;ExplainerRunRequestV1;runExplainer(request, options) export; andexplainer-kit.manifest/v1.project-explainer binds plan.md, design.md, and spec.md.
project-recap additionally binds implementation.md and summary.md.
Missing optional artifacts are omitted, but at least one approved lifecycle
artifact is required. An explicit supplied fact-base path bypasses artifact
federation and is passed through as factBase.mode: supplied.
Unattended project runs pass approved-oat-artifacts provenance to the core's
content-approval seam and never prompt. Every unattended run also requires
exactly one provider-neutral author seam: in-process callers supply author,
while JSON/CLI callers supply authorModulePath naming a module with an
author function export. The adapter validates and resolves that executable
input before passing it to core.runExplainer; callbacks and module paths never
enter the persisted run request.
Federated runs still require an explicit provider-neutral critic callback.
In-process callers may supply critic (or coreOptions.critic for
compatibility); JSON/CLI callers supply criticModulePath naming a module whose
critic export implements the same provider-neutral request/result contract.
Supply exactly one critic seam. Approval provenance does not bypass fact
reconciliation. Do not read private presets, vault files, provider
configuration, or ambient destination configuration.
For interactive runs, show a concise banner and adapter stage updates:
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
OAT ▸ EXPLAINER KIT
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Report compatibility, config, intent, source-binding, core-run, and finalization stages. Lifecycle-triggered unattended runs must not prompt.