CtrlK
BlogDocsLog inGet started
Tessl Logo

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

67

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

75%Weight 40%Scale 1-5

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

A solid, well-structured instruction skill with concrete paths, a clear classification scheme, and explicit sequencing plus acceptance and termination criteria. The main gaps are recurrent phrasing that could be tightened and the absence of a concrete example baseline document.

Suggestions

Factor the recurring "[needs source] ... authorized operation: propose request to registry-events.py" phrasing into a single defined reference to reduce repetition.

Add a short example of the expected baseline document (an inventory table + one or two gap reads) to lift actionability toward 5.

Deduplicate the scope-guard content between the top "Scope guard" paragraph and the Reference Materials / Next Best Skill sections.

DimensionReasoningScore

Conciseness

Prose is lean and assumes competence, avoiding explanation of known concepts, but the "[needs source] via authorized operation: propose request to registry-events.py" phrasing recurs 4+ times and the scope guard overlaps Reference Materials and Next Best Skill — minor tightening possible. Not 5 due to noticeable repetition; not 3 because the writing is otherwise efficient.

4 / 5

Actionability

Instruction-only skill with concrete guidance: enumerated surfaces, exact classification scheme (aligned/drifted/contradictory/silent), exact file paths, and the rule that a gap read must quote the line. Mostly actionable; not 5 because no example baseline document is provided. Per scoring_notes, absence of code is not penalized for instruction-only skills.

4 / 5

Workflow Clarity

A clear 7-step sequence with "Done when" acceptance criteria and "Stop when" termination, plus ask-before-write and never-adjudicate safety checks. Most checkpoints present; not 5 because validation is an acceptance gate rather than an explicit validate->fix->retry loop. The destructive-operation cap does not apply since writes only occur on confirmation.

4 / 5

Progressive Disclosure

Well-organized into clearly signaled sections with one-level-deep references in a dedicated Reference Materials section, and it acts as an overview pointing to detail files. No local bundle files exist to score against; cross-skill references are clearly signaled but their targets are external to this bundle, keeping it at 4 rather than 5.

4 / 5

Total

16

/

20

Passed

Description

92%Weight 40%Scale 1-5

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, well-structured description that clearly states what it does and when to use it, enumerates concrete actions and surfaces, and cleanly distinguishes itself from sibling skills via explicit handoffs. Trigger-term quality is very good but could add more synonym variations.

Suggestions

Add a few more synonym trigger variations (e.g. "audit our messaging", "current-state narrative") to push trigger-term coverage toward anchor 5.

Consider trimming the trailing CJK summary clause if the English description already conveys the same meaning, to reduce redundancy.

DimensionReasoningScore

Specificity

Enumerates concrete actions across all owned touchpoints (homepage, pricing, docs, decks, social bios, email footers) with a labeling scheme (Measured / User-provided / Estimated) and gap read plus drift baseline — comprehensive coverage matching anchor 5.

5 / 5

Completeness

Explicitly answers both what ("produces the narrative baseline — a surface-by-surface inventory... gap read... drift-baseline snapshot") and when ("Use when the user asks to...") with concrete trigger phrases.

5 / 5

Trigger Term Quality

Quotes several natural phrases users would actually say ("map what our surfaces say today", "inventory our current messaging", "find the gap between what we say and what we mean") — strong coverage but lacks the synonym/extension breadth of anchor 5.

4 / 5

Distinctiveness Conflict Risk

Clear niche with explicit negative-triggers routing canon authoring to message-system-architect and scoring to narrative-quality-auditor, minimizing conflict risk.

5 / 5

Total

19

/

20

Passed

Validation

75%

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

Validation12 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

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
Reviewed

Table of Contents

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.