원클릭으로
explainer-kit
Use when building destination-neutral visual explainer artifacts from explicit, versioned inputs.
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 destination-neutral visual explainer artifacts from explicit, versioned inputs.
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 | explainer-kit |
| version | 1.0.2 |
| description | Use when building destination-neutral visual explainer artifacts from explicit, versioned inputs. |
| user-invocable | true |
| allowed-tools | Read, Write, Edit, Bash, Grep, Glob, Agent, mcp__* |
| metadata | {"internal":true} |
Build visual explainer artifact sets from explicit inputs without reading OAT, user, vault, or destination configuration.
This skill is the canonical core. It must not depend on oat-explainer-kit or
OAT project state. Adapters and private wrappers may construct a core run
request and consume its manifest, build record, and optional publish receipt.
Wrappers own private pre-resolution and post-run work. They resolve presets,
vaults, external documents, and personal destinations before translating the
result into one ExplainerRunRequestV1; after the core run, they consume the
versioned manifest and optional receipt to create links or companion records.
They must not inject private work between core stages or expose private lanes as
public config. See references/extension-contract.md for the frozen sequence,
version policy, and compatibility fixture.
Resolve schemas, recipes, templates, scripts, examples, and references relative to this installed skill directory. Never resolve runtime assets from a source checkout or from absolute operator-specific paths.
Construct a complete ExplainerRunRequestV1, then invoke the packaged core:
node scripts/run.mjs --request /path/to/request.json
The core composes validation, fact-base processing, bounded recipe/content
discovery, theme resolution, rendering, QA, and manifest/build-record
persistence. It runs without OAT files or ambient configuration. Supplied fact
bases receive only lightweight consistency/freshness checks. Federated inputs
require a provider-neutral critic callback and invoke it exactly once.
Optional claim sections tags route facts to matching recipe narrative
sections; untagged claims remain shared context for every required section.
Unattended calls use explicit, already-approved source artifacts and require a
provider-neutral author callback once per recipe artifact. In-process callers
supply options.author; JSON-only CLI callers supply --author-module. The
core validates exact narrative sections and non-secret author provenance,
rejects excessive verbatim source overlap, retains each validated result under
source/author/, persists review provenance in
source/content-approval.json, and never prompts. Keep executable callback
references out of the persisted run request.
Interactive runs stop with an incomplete outcome after writing
source/content/*.md. Review and correct that Markdown, then provide an
explicit JSON decision and rerun the same request:
node scripts/run.mjs \
--request /path/to/request.json \
--reviewed-source /path/to/content-review.json
An approval decision resumes the existing run at theme/render; a rejection
persists its correction list and leaves downstream stages pending. Approval
does not authorize publishing: a publish request still requires the separate
human-gated publisher callback. See references/contracts.md for source
formats, callback modules, retained intermediates, and result semantics.
Durability and publishing run only when the request selects them and the caller
supplies the matching callback. The core does not create commits, discover
destinations, or publish automatically. A successful build remains
built-not-durable until caller-supplied evidence is verified.
For interactive runs, show a concise banner and stage updates:
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
EXPLAINER KIT
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Report validation, fact-base, content, theme, render, QA, durability, and publish stages as they begin and complete. Keep unattended output structured and non-interactive.