CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

marketing-council

When the user wants several expert takes on a marketing decision, or asks what a famous marketer would say about it: a simulated board (Seth Godin, David Ogilvy, April Dunford, Byron Sharp, and more), each grounded in their documented frameworks, where they disagree, and a recommendation. To execute, hand off to the relevant skill.

Quality

90%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

92%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.

An excellent instruction-style skill body: concrete, sequenced, and honest about its own failure modes, with a well-executed progressive-disclosure structure over twelve verified dossier files. The single weakness is mild redundancy between the Grounding Rules, Anti-Patterns, and opening framing, which costs a little token efficiency.

Suggestions

Consolidate the overlap between Grounding Rules and Anti-Patterns (simulation labeling, name-flavored generic advice) into one section to trim a few tokens without losing the checks.

DimensionReasoningScore

Conciseness

Efficient and dense — the bench, session modes, and question-fit mappings are compact tables, and nothing explains concepts Claude already knows. Minor trimmable redundancy: the simulation-labeling and no-generic-advice points each appear in both Grounding Rules and Anti-Patterns, and the intro paragraph restates the grounding caveat. Fits 'efficient; minor instances that could be trimmed' better than the every-token-earns-its-place anchor 5.

4 / 5

Actionability

Fully executable instruction guidance: a complete copy-paste output template, a seating table mapping ten question types to specific advisors and designated dissenters, per-take paragraph counts, concrete research-pass fallbacks with a citation format example, and a named save location for custom advisors. This is the instruction-skill equivalent of copy-paste-ready code.

5 / 5

Workflow Clarity

Clear end-to-end sequence (context check → clarify → mode → seat → protocol → output) with explicit checkpoints and feedback loops: 'If research contradicts a dossier, trust the research and note the correction', 'Re-seat with a real dissenter' for the agreeing-council failure, and the Anti-Patterns list as an error-recovery checklist. Not a destructive or batch operation, so no validation cap applies.

5 / 5

Progressive Disclosure

Clean overview with well-signaled one-level-deep references: twelve advisor dossiers in references/advisors/ (all verified present on disk) linked from the bench table with the instruction to 'load only the seated advisors' files', plus references/advisor-template.md for the custom-advisor extension path. No nested references, nothing inlined that belongs in a separate file.

5 / 5

Total

19

/

20

Passed

Description

87%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 description: it states concrete deliverables, opens with an explicit 'When the user wants…' trigger clause, and occupies a distinct niche via the named-advisor simulation framing. The only weaknesses are minor — a handful of natural marketing synonyms and capability details (modes, research pass) are omitted.

Suggestions

Add one or two natural trigger synonyms (e.g., 'marketing advice', 'expert opinions', or 'marketing council') to broaden the natural-phrasing coverage.

Consider naming the session modes (quick take / council / full council) or the research pass in the description to make the capability list more comprehensive.

DimensionReasoningScore

Specificity

Names several concrete deliverables — 'a simulated board… each grounded in their documented frameworks, where they disagree, and a recommendation. To execute, hand off to the relevant skill' — but coverage has minor gaps (no mention of session modes, seating, or the research pass). Fits the 'several specific actions; minor gaps' anchor better than the comprehensive anchor 5 or the 1-2-action anchor 3.

4 / 5

Completeness

Explicitly answers both what ('a simulated board… each grounded in their documented frameworks, where they disagree, and a recommendation') and when ('When the user wants several expert takes… or asks what a famous marketer would say about it') with concrete trigger phrases — a clear anchor-5 match, well above the 'when could be more specific' anchor 4.

5 / 5

Trigger Term Quality

Strong natural phrasing users would actually say ('several expert takes on a marketing decision', 'asks what a famous marketer would say') plus advisor names (Godin, Ogilvy, Dunford, Sharp) that serve as direct triggers. A few common variations are missing ('marketing advice', 'positioning', 'expert council'), so it sits just below the comprehensive-synonyms anchor.

4 / 5

Distinctiveness Conflict Risk

Clear niche — persona simulation of named famous marketers with a disagreement map — with distinct triggers ('what would X say') and minimal conflict risk against generic marketing skills.

5 / 5

Total

18

/

20

Passed

Validation

87%

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

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 12 deeper-than-1-level

Warning

referenced_paths_exist

Referenced path issues: 12 deeper-than-1-level

Warning

Total

14

/

16

Passed

Repository

coreyhaines31/marketingskills

Path

skills/marketing-council/SKILL.md

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.