prompt-gap-to-publish
Use this skill whenever a user wants to turn AI Visibility data into published content — whether they say "find content gaps", "what should we write about", "which topics have low visibility", "help me get cited by AI models", "create a blog post from our AI Visibility gaps", "we're losing to competitors on these prompts", or any variation where they want to go from AI visibility weakness to a draft article, landing page, or FAQ. This skill connects directly to Amplitude AI Visibility data (topics, prompts, visibility scores, citations, competitor data, full LLM responses and sources) and produces a publish-ready content brief plus full article draft. If the user mentions CMS (WordPress, Webflow, Contentful, Sanity, HubSpot, Ghost, Shopify), also trigger this skill to push the draft directly. Trigger even if they just say something vague like "what content should we create?" in an AI Visibility context.
76
70%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./content-marketing-skills/skills/prompt-gap-to-publish/SKILL.mdQuality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong, well-crafted description that excels across all dimensions. It provides extensive trigger terms covering both specific and vague user requests, clearly articulates the full pipeline from data analysis to content publishing, and occupies a distinct niche around Amplitude AI Visibility. The only minor weakness is verbosity — it could be slightly more concise while retaining the same information — but this doesn't meaningfully hurt its effectiveness as a skill selector.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: finding content gaps, analyzing visibility scores/citations/competitor data, producing content briefs, drafting articles/landing pages/FAQs, and pushing drafts to CMS platforms. Very detailed about what it does. | 3 / 3 |
Completeness | Clearly answers both 'what' (connects to Amplitude AI Visibility data, produces content briefs and article drafts, pushes to CMS) and 'when' (explicit trigger phrases and scenarios including vague requests in AI Visibility context). The 'Use this skill whenever...' opening directly addresses when to trigger. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would say: 'find content gaps', 'what should we write about', 'which topics have low visibility', 'help me get cited by AI models', 'create a blog post', 'we're losing to competitors', 'what content should we create?' — plus specific CMS names (WordPress, Webflow, etc.). | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — it's specifically scoped to Amplitude AI Visibility data and the pipeline from visibility gaps to published content. The combination of AI Visibility analysis + content generation + CMS publishing creates a clear niche unlikely to conflict with generic content writing or analytics skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
39%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill has excellent workflow structure with a clear 7-step process and appropriate safety guardrails (draft-only publishing, user confirmation). However, it is significantly over-verbose — the CMS discovery and publishing sections repeat similar patterns six times each, and conversational scripts are unnecessarily prescriptive for Claude. The lack of any supporting bundle files means all content is crammed into one long document, hurting both conciseness and progressive disclosure.
Suggestions
Extract CMS-specific setup instructions (Step 0) and publishing details (Step 6) into a separate CMS_REFERENCE.md file, leaving only a summary table and reference link in the main skill.
Remove conversational script suggestions (the quoted dialogue lines) — Claude can generate appropriate conversational responses without being told exactly what to say.
Add a concrete example of an MCP tool call with actual parameters (e.g., `get_ai_visibility_topics({orgBrandId: '...', reportId: null})`) to improve actionability.
Consolidate the six CMS recommendation blocks into a compact table with columns: CMS | Plugin name | Required credentials | Setup time, rather than repeating the same conversational pattern six times.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~300+ lines. Step 0 alone is massive, with lengthy CMS-specific setup instructions that Claude could infer or that could be in a separate reference file. The conversational script suggestions ('Here's what to say...') are overly prescriptive for Claude. Much of the CMS guidance repeats the same pattern six times with minor variations. | 1 / 3 |
Actionability | The skill provides specific MCP tool names (e.g., `list_ai_visibility_org_brands`, `get_ai_visibility_topics`) and concrete field mappings for each CMS, which is good. However, there are no executable code examples, no actual API call examples with parameters, and the content generation guidance is descriptive rather than templated. The opportunity heuristic thresholds (relevancy > 60%, visibility < 40%) are concrete and useful. | 2 / 3 |
Workflow Clarity | The workflow is clearly sequenced (Steps 0-6) with logical progression from CMS discovery → brand identification → data pull → analysis → content generation → publishing. It includes validation checkpoints (confirming with user before pushing to CMS, never publishing without explicit instruction, always outputting Markdown fallback). The feedback loops are appropriate — ask before pushing, confirm CMS type, wait for user pick on opportunity. | 3 / 3 |
Progressive Disclosure | Everything is in a single monolithic file with no references to supporting documents. The CMS-specific setup instructions (Step 0) and CMS-specific publishing details (Step 6) could easily be split into a CMS_REFERENCE.md. The content writing tips could be a separate WRITING_GUIDE.md. The content type guide table could be externalized. No bundle files exist to support this skill. | 1 / 3 |
Total | 7 / 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.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- amplitude/builder-skills
- Commit
221ffaa
- 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.