CtrlK
BlogDocsLog inGet started
Tessl Logo

geo-content-planning

Reads existing brand DNA, keywords.csv, and prompts.csv, then produces a plan.csv — a strictly-schema'd content architecture telling the next pipeline step which pages to create, for which keyword/prompt clusters, and in what build order.

69

Quality

83%

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

100%

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

The body is a tight, fully-actionable instruction set: concrete CSV contract, a complete valid example, and an explicit pre-emit validation checklist over a clear 8-step workflow. It assumes Claude's competence, avoids concept-explanation fluff, and is well-organized as a single-file skill.

DimensionReasoningScore

Conciseness

The body is lean and instructional — enum values, field rules, and a full example earn their tokens without explaining concepts Claude already knows. Not level 2 because there is no padded exposition; the example block is justified as the exact output contract rather than verbosity.

3 / 3

Actionability

Provides fully executable guidance — exact header, field order, 11-field rule, quoting rules, cross-reference resolution rules, page-type enums, and a copy-paste-ready full example output. Not level 2 because it is concrete and complete rather than pseudocode or partial.

3 / 3

Workflow Clarity

An 8-step sequenced workflow is capped by an explicit pre-emit validation checklist (the 'Before emitting — checklist' gating cross-references, field counts, subsection rules, and dedup). Not level 2 because the validation checkpoint is explicit and acts as an error gate before the batch emit.

3 / 3

Progressive Disclosure

A single-purpose skill with no external bundle files, organized into clearly labeled sections (Workflow, Strict CSV Format, Example, Checklist). Per the rubric's simple-skills note, a well-organized single-file skill with no needed references scores 3. Not level 2 because content is appropriately sectioned rather than a monolithic wall.

3 / 3

Total

12

/

12

Passed

Description

67%

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 specific and well-differentiated, clearly stating the inputs, the output artifact, and what the plan prescribes. Its main weakness is the absence of an explicit 'Use when...' trigger clause, which leaves the activation context implicit and caps completeness at 2.

Suggestions

Add an explicit trigger clause such as 'Use when planning the GEO content architecture from brand DNA, keywords.csv, and prompts.csv into a build plan' to satisfy the 'when' half of completeness.

Surface a couple of natural-language activation terms a user might actually say (e.g. 'content plan', 'page build order') alongside the file-name jargon to improve trigger_term_quality.

Keep the existing third-person, concrete-action phrasing — it is already strong on specificity and distinctiveness.

DimensionReasoningScore

Specificity

Lists multiple concrete actions in third person — 'Reads existing brand DNA, keywords.csv, and prompts.csv, then produces a plan.csv' and specifies pages, keyword/prompt clusters, and build order. Not level 2 because it goes beyond naming the domain to enumerating specific inputs, the output artifact, and what the output prescribes.

3 / 3

Completeness

Clearly answers 'what does this do', but there is no 'Use when...' clause or equivalent explicit trigger for 'when should Claude use it'. Per the rubric guideline, a missing explicit trigger caps completeness at 2; not level 3 because the 'when' is entirely absent.

2 / 3

Trigger Term Quality

Domain terms appear ('brand DNA', 'keywords.csv', 'prompts.csv', 'plan.csv', 'keyword/prompt clusters', 'build order') but these are pipeline-internal file names and jargon rather than natural phrasing a user would say. Not level 3 because there is no coverage of common natural-language variations, and not level 1 because the terms are at least relevant to the task.

2 / 3

Distinctiveness Conflict Risk

Niche is distinct — a GEO content-planning pipeline step that emits a schema-strict plan.csv from specific named inputs. Unlikely to trigger for unrelated skills. Not level 2 because the named artifacts (plan.csv, keywords.csv, prompts.csv) and strict-schema framing make it highly specific.

3 / 3

Total

10

/

12

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
onvoyage-ai/gtm-engineer-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.