brand-language-codifier

Use when the user asks to "codify our brand voice", "define naming rules for our products and tiers", or "write the tone-of-voice guide with banned phrases"; produces the brand-level voice canon (register, tone spectrum, banned-phrase list, few-shot examples drawn only from the brand's own published material) and the naming tax (product / feature / tier naming rules plus approved and banned terms) that seeds the narrative-registry canon and that every channel's voice adaptation points up to. Not for per-platform voice adaptation — use channel-registry's voice-dossier; not for finished copy or blog posts — use content-writer; not for the message hierarchy itself — use message-system-architect; not for claim adjudication — use offer-claims-registry. 品牌语气/词汇表/命名税/禁用词/品牌语言规范

Quality

83%

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

73%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 well-structured, procedurally clear skill body with strong workflow gating and validation, suited to its instruction-only nature. Its main weaknesses are heavy verbatim repetition that inflates token cost and the absence of a concrete example for its central registry-events propose payload.

Suggestions

Consolidate the repeated 'authorized operation: propose request to registry-events.py' phrasing into one canonical statement and cross-reference it, removing the 5+ verbatim restatements across Skill Contract, Instructions, and Save Results.

Add a short concrete example of the registry-events.py propose-request payload (operation, target file, fields) so the skill's central write action is copy-paste ready rather than described only by reference.

Trim the restated dual-mode voice+naming framing from the intro and Instructions since it already appears in the opening paragraph and Skill Contract.

Dimension	Reasoning	Score
Conciseness	The body is accurate and well-targeted but repeats the same phrases verbatim many times — 'authorized operation: propose request to registry-events.py' appears 6+ times and the dual-mode voice+naming framing is restated across the intro, Skill Contract, and Instructions — which could be tightened to a single canonical statement plus cross-references.	3 / 5
Actionability	Provides concrete memory paths, file references (registry-events.py, scripts/connectors/firecrawl.py), a labeled term taxonomy (Measured/User-provided/Estimated), and a 7-step procedure, but never shows the actual propose-request payload format that is the skill's central write operation.	4 / 5
Workflow Clarity	The 7 steps are clearly sequenced with explicit validation checkpoints — a NEEDS_INPUT gate in step 1, a shipped-canon contradiction check in step 6 with feedback routing to re-version rather than in-place edit, defined 'Done when' criteria, and termination rules (visited-set, max-depth:3, ambiguity stop).	5 / 5
Progressive Disclosure	Well-organized into clear sections with a one-level-deep Reference Materials list pointing to external skills/protocols; no local bundle files exist so inlining is appropriate, but the repeated inlined content represents a minor organization gap.	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, specific description that clearly states what it produces, when to use it via natural quoted triggers, and how it differs from neighboring skills. Its only weakness is moderate synonym breadth in trigger terms.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete deliverables — 'voice canon (register, tone spectrum, banned-phrase list, few-shot examples)' and 'naming tax (product / feature / tier naming rules plus approved and banned terms)' — with comprehensive coverage of the skill's outputs.	5 / 5
Completeness	Explicitly answers both what ('produces the brand-level voice canon... and the naming tax') and when ('Use when the user asks to...') with concrete trigger phrases, plus explicit exclusion boundaries.	5 / 5
Trigger Term Quality	Includes three quoted natural user phrasings ('codify our brand voice', 'define naming rules for our products and tiers', 'write the tone-of-voice guide with banned phrases') plus relevant keywords, but lacks synonym breadth that would mark comprehensive coverage.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (brand voice + naming tax) and explicitly disambiguates from four adjacent skills ('Not for per-platform voice adaptation... not for finished copy... not for the message hierarchy... not for claim adjudication'), minimizing conflict risk.	5 / 5
	Total	19 / 20 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: 2 missing, 2 deeper-than-1-level	Warning

	Total	12 / 16 Passed

Repository: aaron-he-zhu/aaron-marketing-skills
Path: narrative/architect/brand-language-codifier/SKILL.md
Commit: 888dd38

Reviewed: 3 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.