narrative-baseline-mapper

Use when the user asks to "map what our surfaces say today", "inventory our current messaging", or "find the gap between what we say and what we mean"; produces the narrative baseline — a surface-by-surface inventory of what every owned touchpoint (homepage, pricing, docs, decks, social bios, email footers) claims RIGHT NOW, each line labeled Measured / User-provided / Estimated, plus a per-surface gap read vs the intended message and the drift-baseline snapshot the Evaluate phase measures future drift against. Not for authoring the canon — use message-system-architect; not for scoring the surfaces or running the vetoes — use narrative-quality-auditor. 现状叙事盘点/各触点口径/意图差距/漂移基线

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

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.

A well-structured, highly actionable skill body with a clear sequenced workflow, verification checklist, and clean one-level-deep reference navigation. Its main weakness is repeated boilerplate (claim-submission phrasing and scope-guard restatements) that inflates length without adding new information.

Suggestions

Consolidate the repeated registry-events.py / "authorized operation: propose" claim-submission phrasing into one canonical statement in the Skill Contract, then reference it tersely from Instructions and Save Results to cut redundancy.

State the canon/non-canon scope boundary once in the Scope guard and link out, rather than restating the message-system-architect / narrative-registry handoff in multiple sections.

The repeated "this skill never writes memory/narrative-registry/" disclaimer appears in both Skill Contract and Save Results — keep a single authoritative instance to tighten conciseness.

Dimension	Reasoning	Score
Conciseness	The body is dense and domain-specific (no basic-concept padding), but the registry-events.py / "authorized operation: propose" boilerplate repeats across the Scope guard, Skill Contract, Instructions, and Save Results sections, and the canon-handoff scope guard is restated multiple times — it could be tightened. It is not the lean every-token-earns-its-place level 3.	2 / 3
Actionability	Concrete, executable guidance throughout: named scripts (firecrawl.py, wayback.py), exact memory paths, fixed label set (Measured/User-provided/Estimated), and a fixed gap taxonomy (aligned/drifted/contradictory/silent). Per the scoring note, absence of code in this instruction-only skill is not penalized when guidance is this actionable.	3 / 3
Workflow Clarity	A clearly sequenced 7-step Instructions block with an explicit "Done when" verification checklist and per-step guards (e.g. "If neither exists, say so... do not invent"), matching the clear-sequence-with-validation anchor.	3 / 3
Progressive Disclosure	Well-organized sections (Quick Start, Skill Contract, Data Sources, Instructions, Reference Materials, Next Best Skill) with a Reference Materials list of one-level-deep links each accompanied by a one-line description — easy navigation, no nested-reference indirection.	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.

A strong, third-person description with explicit natural-language triggers, concrete enumerated actions, and clear boundary-setting against sibling skills. It cleanly answers both what the skill does and when to invoke it.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions — "a surface-by-surface inventory", "each line labeled Measured / User-provided / Estimated", "a per-surface gap read", and "the drift-baseline snapshot" — matching the multiple-specific-actions anchor rather than the domain-only level 2.	3 / 3
Completeness	Explicitly answers both what (produces the narrative baseline inventory + gap read + drift snapshot) and when ("Use when the user asks to..."), with explicit triggers — not the level-2 case where 'when' is only implied.	3 / 3
Trigger Term Quality	Embeds natural user phrasings ("map what our surfaces say today", "inventory our current messaging", "find the gap between what we say and what we mean") that a user would plausibly say, giving good coverage rather than just jargon.	3 / 3
Distinctiveness Conflict Risk	Carries a clear niche and explicit disambiguation ("Not for authoring the canon — use message-system-architect; not for scoring... use narrative-quality-auditor"), making wrong-skill triggering unlikely.	3 / 3
	Total	12 / 12 Passed

Validation

75%

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 — 12 / 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: 27 suspicious	Warning
referenced_paths_exist	Referenced path issues: 4 missing, 4 deeper-than-1-level	Warning

	Total	12 / 16 Passed

Repository: aaron-he-zhu/aaron-marketing-skills
Path: narrative/trace/narrative-baseline-mapper/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.