seo-keyword
Run keyword research, classify by search intent, cluster into topical groups, and prioritize for content production. Use this skill whenever the user asks to do keyword research, find target keywords, identify ranking opportunities, classify search intent, build a topical map, or plan a content strategy around what people search for. Triggers on keyword research, keyword strategy, search intent, keyword clustering, topic clusters, keyword difficulty, search volume, ranking opportunity, content gap, what should I write about, target keyword, primary keyword, secondary keyword, long-tail. Also triggers when planning a content calendar or new site without keywords yet defined.
65
78%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/seo-keyword/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 an excellent skill description that clearly articulates specific capabilities, provides comprehensive trigger terms covering natural user language, and explicitly states both what the skill does and when to use it. The description is well-structured with a capability summary, a 'Use this skill whenever' clause, and an extensive trigger term list that minimizes the chance of being overlooked or confused with other skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Run keyword research, classify by search intent, cluster into topical groups, and prioritize for content production.' These are clear, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (run keyword research, classify by search intent, cluster into topical groups, prioritize for content production) and 'when' with an explicit 'Use this skill whenever...' clause plus a detailed 'Triggers on' list covering many scenarios. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say, including 'keyword research', 'search intent', 'keyword clustering', 'topic clusters', 'keyword difficulty', 'search volume', 'what should I write about', 'long-tail', 'content gap', and 'content calendar'. These are highly natural phrases a user would actually type. | 3 / 3 |
Distinctiveness Conflict Risk | The description carves out a very clear niche around SEO keyword research and content strategy planning. The specific trigger terms like 'keyword difficulty', 'search volume', 'topical map', and 'ranking opportunity' are highly distinctive and unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
57%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured keyword research skill with a clear 4-stage framework and logical workflow. Its main weaknesses are the lack of validation checkpoints in the workflow (e.g., spot-check intent classifications, verify cluster coherence before scoring) and the absence of concrete worked examples showing the scoring and prioritization in action. The content is moderately concise but could trim explanations of concepts Claude already understands.
Suggestions
Add explicit validation checkpoints to the workflow, e.g., 'After step 4, spot-check 10 keywords against actual SERPs to verify intent classification accuracy before clustering.'
Include a concrete worked example showing 3-5 real keywords going through classification, clustering, and scoring with actual numbers to demonstrate the priority formula.
Trim explanations of basic concepts Claude already knows (e.g., what informational vs transactional intent means) and instead focus the intent table purely on the signals and page-type mappings.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is generally well-written but includes some unnecessary explanation that Claude would already know (e.g., explaining what informational vs transactional intent means, defining what seed terms are). The 'When to use' and 'When NOT to use' sections add value but the overall content could be tightened by ~20-30%. | 2 / 3 |
Actionability | The framework and workflow provide structured guidance with specific targets (200-500 keywords, 20-50 clusters, scoring formula), but there are no executable code examples, no concrete CSV generation commands, and the priority scoring formula is described abstractly rather than with a worked example showing real numbers. | 2 / 3 |
Workflow Clarity | The 8-step workflow is clearly sequenced and the 4-stage framework provides good structure. However, there are no validation checkpoints — no step says 'verify your intent classifications by spot-checking 10 keywords against actual SERPs' or 'validate clusters by confirming SERP overlap before scoring.' For a multi-step process that builds on prior steps, missing validation caps this at 2. | 2 / 3 |
Progressive Disclosure | The skill provides a clear overview with well-signaled one-level-deep references to keyword-research-template.md and intent-classification-guide.md. The main content stays at the right level of detail for an overview, with detailed examples and templates appropriately delegated to reference files. | 3 / 3 |
Total | 9 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- rampstackco/claude-skills
- Commit
8e70d03
- 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.