pitch-narrative-builder

Use when the user asks to "build our pitch deck narrative", "write a fundraising story", or "structure the sales pitch narrative"; derives from the narrative canon a company pitch/deck narrative — problem → the undeniable shift → product-as-hero → proof → the ask — as a slide-beat outline (one narrative beat per slide, with the claim ID each proof beat rests on), for both a sales pitch and a fundraising deck. Every proof beat is labeled Measured / User-provided / '[needs source]' and unverified ones route to the claims candidates. Not for the launch-window battle cards and talk track — use sales-enablement-kit; not for the durable message hierarchy or the arc itself — use message-system-architect / strategic-narrative-designer; not for finished deck visual design — out of scope; not for claim adjudication — use offer-claims-registry. 路演叙事/融资故事/销售 pitch/幻灯节拍

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

85%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is well-organized, highly actionable, and has a clear workflow with validation checkpoints. The main weakness is conciseness: the core arc and the claims-routing clause are repeated near-verbatim across several sections and would benefit from consolidation.

Suggestions

State the five-beat arc once (e.g. in the intro) and reference it thereafter instead of repeating 'problem → shift → product-as-hero → proof → ask' verbatim in the Skill Contract, Instructions step 2, and step 7.

Consolidate the '[needs source] → memory/events/claims.ndjson via operation: propose to registry-events.py' routing into one canonical statement (e.g. the Skill Contract Writes line) and point back to it from Instructions step 4 and Save Results rather than restating the full clause each time.

Consider moving the dense per-skill handoff/routing detail (registry-events.py mechanics) into a shared reference like skill-contract.md and citing it, reducing repeated boilerplate in the body.

Dimension	Reasoning	Score
Conciseness	The body is mostly high-signal with no concept teaching, but the five-beat arc and the '[needs source] → claims.ndjson via registry-events.py' routing clause are each restated verbatim across four to five sections, which could be consolidated.	2 / 3
Actionability	Gives exact memory paths, an enumerated output contract, named beat definitions, a specific claim-routing protocol, and a labeling scheme — concrete and copy-ready despite being an instruction skill with no code.	3 / 3
Workflow Clarity	A numbered seven-step sequence with explicit validation gates (NEEDS_INPUT stop when no canon, ledger binding, canon-consistency/banned-word pass with a stop-on-contradiction feedback loop) and a done-when acceptance clause.	3 / 3
Progressive Disclosure	Clean section structure (Quick Start, Skill Contract, Instructions, Reference Materials, Next Best Skill) with well-labeled, one-level-deep references each annotated with what they provide; no nested reference chains.	3 / 3
	Total	11 / 12 Passed

Description

100%Weight 40%Scale 1-3

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is exemplary: it pairs verbatim natural-language triggers with a precise statement of the five-beat output, labels proof handling, and explicitly excludes four adjacent skills to avoid mis-routing. Voice is correctly third-person throughout.

Dimension	Reasoning	Score
Specificity	Enumerates multiple concrete actions — deriving the five-beat arc, mapping beats to a slide outline with claim IDs, labeling each proof beat Measured/User-provided/[needs source], and routing unverified ones to candidates — well beyond naming the domain.	3 / 3
Completeness	Explicitly states what it does (derives the pitch narrative as a slide-beat outline) and when to use it (a prominent 'Use when the user asks to...' clause), satisfying both halves with explicit triggers.	3 / 3
Trigger Term Quality	Leads with verbatim user utterances ('build our pitch deck narrative', 'write a fundraising story', 'structure the sales pitch narrative') plus CJK variants (路演叙事/融资故事/销售 pitch/幻灯节拍), giving natural, high-coverage triggers.	3 / 3
Distinctiveness Conflict Risk	Negative-scopes four sibling skills by name (sales-enablement-kit, message-system-architect / strategic-narrative-designer, offer-claims-registry) and excludes visual design, carving a clear, low-conflict niche.	3 / 3
	Total	12 / 12 Passed

Validation

81%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 33 suspicious	Warning

	Total	13 / 16 Passed

Repository: aaron-he-zhu/aaron-marketing-skills
Path: narrative/land/pitch-narrative-builder/SKILL.md
Commit: 4a77c48

Reviewed: 9 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.