Skip to content

sergekostenchuk/seo-llm-skill-cluster / skills/semantic-core-architect

semantic-core-architect

Verified

Build evidence-labeled semantic cores for SEO, LLM-readable architecture, and site information design. Use this skill when the user asks for semantic core, query clusters, search intents, audience segments, entity/topic maps, language or locale priorities, competitor/source evidence, pillar-topic planning, or a structured handoff before URL architecture and internal linking. It must mark unknown search volume, difficulty, and ranking data as unknown instead of inventing metrics.

validation-report.md

View on GitHub
# Semantic Core Architect Validation Report

date: 2026-06-11
task: T-004
skill_path: `./skills/semantic-core-architect`

## Result

Status: pass.

## Commands

```bash
python3 <codex-skills-dir>/senior-skill-architect/scripts/lint_production_skill.py ./skills/semantic-core-architect --json
```

Result: pass, 0 errors, 0 warnings.

```bash
python3 -m json.tool ./skills/semantic-core-architect/evals.json
```

Result: valid JSON.

```bash
ruby -e 'require "yaml"; YAML.load_file(ARGV[0]); YAML.load_file(ARGV[1]); puts "yaml-ok"' ./skills/semantic-core-architect/assets/semantic-core.template.yaml ./skills/semantic-core-architect/assets/entity-topic-map.template.yaml
```

Result: valid YAML.

```bash
python3 ./plans/seo-llm-skill-cluster/scripts/lint_skill_cluster.py . --report ./plans/seo-llm-skill-cluster/cluster-lint-report.json
```

Result: pass, 0 critical issues, 0 warnings.

## Eval Coverage

- Positive cases: 3.
- Negative cases: 3.
- Covered targets: AI news site, SaaS site, personal portfolio.
- Safety cases: invented volume/difficulty, final canonical ownership overreach, ambiguous audience.

## Notes

- Search volume, keyword difficulty, current rank, and assistant citation claims are explicitly represented as `unknown` unless evidence is available.
- Final URL/canonical decisions are handed off to `information-architecture-seo`.

brainstormingobra/superpowersYou MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or planning anything new, in software or out of it (a talk, a business, a renovation).Stars: 322kUpdated Claude CodeCodexVerifiedInstall
brand-guidelinesanthropics/skillsApplies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
frontend-designanthropics/skillsGuidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
mcp-builderanthropics/skillsGuide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).Stars: 198kUpdated Claude CodeCodexVerifiedInstall