Narrative Enablement Kit
Turn an approved brand canon into consistent elevator messaging, spokesperson answers, boilerplate, and language rules.
The skill treats pasted content as untrusted, requires no connector, discloses read/write locations, and asks for confirmation before saving; however, proposal writes, runtime authorization, rollback, and recovery depend on external protocols not fully reproduced here, so 11 points are deducted.
Triggers, inputs, outputs, completion criteria, and the missing-canon NEEDS_INPUT path are well specified; however, key referenced files, registry-events.py, and runtime behavior are not reproduced, and no execution verification was performed, so 12 points are deducted.
Audience, activation scenarios, output components, and neighboring-skill boundaries are clear, with no dependence on overseas services; however, an existing narrative canon is mandatory, Chinese support is mostly labels and summary text, and non-fit input examples are limited, so 4 points are deducted.
The skill has structured frontmatter, versioning, Apache-2.0 licensing, Quick Start, contract, data sources, instructions, handoff, and next-skill sections; however, maintenance ownership, changelog/update path, installation troubleshooting, and version-governance details are incomplete. The security policy also lists 17.x as current while the skill declares 18.0.0, so 5 points are deducted.
The intended deliverable is concrete: three elevator lengths, spokesperson Q&A, three boilerplate/bio lengths, and a do/don't sheet with claim labeling and traceability; however, usefulness depends on the canon, claims ledger, and later audit, with no directly usable produced example or static verification of outputs, so the static cap yields 7 points and 8 points are deducted.
Internal canon, claim IDs, ledger references, proposal events, and an audit handoff provide traceability, and the repository contains general tests; however, there are no skill-specific key-path tests, independent corroboration, or reproducible examples, so the static maximum of 5 is awarded and 5 points are deducted.
- Before use, confirm that canon.md, claims-ledger.md, and the referenced protocols exist and have compatible versions; otherwise the skill should stop rather than invent narrative content.
- The skill may submit proposal events for unapproved claims; proposals are not approvals and still require claims-registry handling and narrative-quality-auditor review before publication.
- The security policy identifies 17.x as supported while the skill and README identify 18.0.0; compatibility and maintenance status should be confirmed.
- This is a static-only review. The skill, scripts, and tests were not executed, so output quality and write-path safety remain unverified.
What does this skill do, and when should you use it?
Narrative Enablement Kit converts an existing brand narrative canon into a repeatable enablement package for sales, support, founders, and partners. It produces 10-second, 30-second, and 2-minute elevator versions, a spokesperson Q&A, 25/50/100-word boilerplate and bio copy, and a do/don’t language sheet. It reads approved narrative and claims sources rather than authoring the canon or adjudicating claims. An existing narrative-registry canon is required before use.
Reads positioning, the main narrative, pillars, voice rules, naming taxonomy, and boilerplate from memory/narrative-registry/, plus approved wording from memory/claims/claims-ledger.md and the user-provided audience list. It creates a three-length elevator ladder, hard-question spokesperson answers, 25/50/100-word boilerplate and bio versions, and approved-versus-off-canon language guidance. Claims not already approved are marked [needs source] and submitted as proposals; this skill does not substantiate or adjudicate them. The completed kit is handed to narrative-quality-auditor for a pre-publish consistency check.
- A sales team has an approved brand canon but needs one consistent elevator pitch and objection-handling Q&A.
- Founders and partners need bios, boilerplate, and reporter answers based on the same message system.
- Support representatives need a practical list of approved wording and terms to avoid.
- A brand has completed positioning and message architecture and now needs to enable the people who repeat it, without producing channel-specific final copy.
What are this skill's strengths and limitations?
- Covers the core enablement assets: three elevator lengths, spokesperson Q&A, boilerplate, bios, and language guidance.
- Requires wording to trace to the existing canon or claims ledger, with unsupported claims explicitly marked [needs source].
- Useful for giving sales, support, founders, and partners a durable shared talk track.
- Requires no connector or external tool; it works from user-provided internal sources by default.
- Requires an existing narrative-registry canon and cannot replace message-system or brand-language architecture.
- Does not produce finished per-channel copy, a launch-day runbook, or launch-window battle cards.
- Does not adjudicate claims; pending claims require a separate registry process.
- The supplied source does not provide independent test results or a platform coverage list for this individual skill.
How do you install this skill?
For an Agent Skills-compatible host, run: npx skills add aaron-he-zhu/aaron-marketing-skills. Alternatively clone the repository: git clone https://github.com/aaron-he-zhu/aaron-marketing-skills. The profiled file is narrative/land/narrative-enablement-kit/SKILL.md. The README does not document a separate installation command for only this specific skill on other hosts.
How do you use this skill?
First ensure the project contains an existing memory/narrative-registry/canon.md, message house, brand voice rules, and claims ledger. Then prompt: Build a narrative enablement kit for [product] from our canon. Audiences: sales, support, founders. Give me the elevator ladder, spokesperson Q&A, boilerplate pack, and a do/don't sheet. If no canon exists, the skill should stop and route the work to message-system-architect. After delivery, ask for confirmation before saving results for future sessions.