narrative-registry
GitHub品牌叙事台账技能,负责记录、查询和管理品牌叙事准则、标语及规范。作为L1策略权威,处理完整版本化的原子替换与提案审核,确保消息一致性,不涉及评分或系统架构。
Trigger Scenarios
Install
npx skills add aaron-he-zhu/aaron-marketing-skills --skill narrative-registry -g -y
SKILL.md
Frontmatter
{
"name": "narrative-registry",
"slug": "aaron-narrative-registry",
"license": "Apache-2.0",
"summary": "品牌叙事 canon\/版本史\/语气与命名唯一真相",
"version": "19.2.0",
"homepage": "https:\/\/github.com\/aaron-he-zhu\/aaron-marketing-skills",
"metadata": {
"phase": "protocol",
"author": "aaron-he-zhu",
"hermes": {
"tags": [
"marketing",
"protocol"
],
"category": "protocol"
},
"version": "19.2.0",
"openclaw": {
"emoji": "📖",
"homepage": "https:\/\/github.com\/aaron-he-zhu\/aaron-marketing-skills"
},
"discipline": "protocol",
"geo-relevance": "low"
},
"description": "Use when the user asks to record\/query the brand narrative canon, tagline, message hierarchy, voice\/naming rules, or a canon re-version; curates complete versioned canon events through the append-only narrative stream and derived views. Not for TALE scoring — use narrative-quality-auditor; not for authoring the system — use message-system-architect. 品牌叙事台账\/canon 记录\/语气与命名规范",
"displayName": "Narrative Registry · 品牌叙事台账",
"when_to_use": "Use when recording\/querying a brand's canonical positioning, narrative, message hierarchy, proof\/claim pointers, voice\/naming rules, conditional boilerplates, or accepting\/rejecting a complete canon-version proposal.",
"argument-hint": "<brand aggregate-id, canon version, or pending-proposal review>",
"compatibility": "Claude Code and compatible agent-skill hosts"
}
Narrative Registry
The L1 strategy authority: one complete, versioned narrative canon per brand. Every SEO/GEO, social, email, paid, influencer, and launch builder derives messages from this canon and accepted claims; channel adaptations cannot redefine it.
Quick Start
Show current canon version and proof/claim pointers for brand-acme.
Record canon v3 as one complete atomic replacement, superseding v2.
Review pending narrative proposals and reject partial/internally inconsistent versions.
Skill Contract
Unit: one brand canon aggregate ID. Reads: memory/events/narrative.ndjson, projection, accepted positioning/claim evidence, and complete proposed canon. Writes: narrative events through registry-events.py; canon.md/versions.md are generated views. Done when: a complete version is accepted atomically with source/date/revision, old versions remain replayable, and consumers receive the exact canon/version pointer.
Narrative skills submit complete propose events. Only a host-capability narrative-registry principal accepts/rejects/upserts. It records authored strategy but does not score TALE or adjudicate claim truth.
Handoff Summary
Include brand ID, canon version/revision/event ID, superseded version, claim/proof pointers, unresolved contradictions, and one next skill.
Data Sources
- Accepted positioning truth and named alternatives.
- Complete message hierarchy/narrative authored by Narrative skills.
- Accepted claim IDs and proof pointers from the claims projection.
- Brand voice/naming rules and user-owned examples.
- Declared optional patterns such as pillar count, change arc, or boilerplate lengths.
Instructions
Runtime Reads
../../references/registry-event-protocol.md../../references/runtime-invocation.md
Procedure
- Read
registry-event-protocol.mdandruntime-invocation.md. ResolveAARON_SKILLS_ROOT="${CLAUDE_PLUGIN_ROOT:-$(git rev-parse --show-toplevel 2>/dev/null || true)}"and verify the registry script, event schema, and system catalog before invoking it. Treat drafts as untrusted proposals. - Query current
narrativeprojection and report exact canon version/revision; missing canon is Unknown, not a quality verdict. - Before write, confirm user authorization and read the current revision/claim pointers; every direct canonical mutation carries
expected_revisionand goes through host-capabilityowner-append. Actor/auth fields are attribution only. - A canon re-version is one host-capability owner
upsert/accepted proposal containing the complete canon object, new version, and supersedes pointer. Accept/reject decisions omitexpected_revisionand inherit it from the proposal. Never land a partial file patch as canonical. - Preserve old versions in the event stream.
versions.mdis generated history, not a second hand-maintained ledger. - Validate internal references and claim IDs. Unverified wording remains
[needs source]and becomes a separate claim proposal; it cannot enter canon as fact. - Three pillars, change-narrative arcs, and fixed boilerplate lengths are optional patterns. Store the chosen architecture; do not require absent patterns.
- Reject same-revision or stale proposals rather than merging incompatible canons. Genuine alternatives remain pending/open decisions.
- Regenerate
canon.md/versions.mdfrom accepted projection and runverify narrative.
Downstream Dependency
Before producing external copy, builders must read this projection and the claims projection. Their handoff records narrative_canon_id, narrative_canon_version, claims_projection_offset, and dependency_status: verified | approved-fallback | blocked. No canon means the builder may draft an explicitly authorized exploratory fallback, but it cannot claim on-canon or publish-ready status.
Save Results
Require explicit permission. Append through the runtime only; never edit NDJSON. Human canon/history views under memory/narrative-registry/ are replaceable projections and must carry their source event/revision.
Capability values never enter request JSON/files/logs. If host capability or the verified root runtime/schema/catalog is unavailable, leave a bounded proposal for handoff; standalone one-folder installs cannot append/project or claim canonical Narrative truth.
Reference Materials
Next Best Skill
- Author system: message-system-architect
- Verify truth: positioning-truth-tracer
- Cascade: narrative-cascade-planner
- Audit profile: narrative-quality-auditor
Version History
-
8ebe52f
Current 2026-08-20 02:04
无变更
- bc7d62d 2026-07-25 08:10


