See it in action
One of 4 test cases the skill fixed. Same model, same prompt, with and without the skill.
PromptWe plan to publish 24 cluster articles for a healthcare portal. How many supporting pillar pages should be created to organize this content network?
What was checked, without and with the skill| Checked | Without skill | With skill |
|---|
| Recommends 4 to 6 pillar pages to maintain internal linking ratios | Missed | Passed |
|---|
What's inside
The instructions your model reads when the skill loads.
SKILL.md25 linessingle file
Keyword Research Systems Skill
When to Use
- Kicking off a new product/vertical SEO plan.
- Validating which clusters justify net-new content.
- Refreshing legacy keyword maps with updated volumes/intent.
Framework
- Seed Intake – capture ICP, problems solved, solution terms.
- Expansion Sources – combine auto-suggest, People Also Ask, competitor URLs, forums.
- Classification – assign funnel stage + intent (informational, commercial, transactional, navigational).
- Scoring – evaluate search volume, keyword difficulty, SERP click potential, seasonality.
- Prioritization – stack rank via ICE/RICE or weighted scoring tied to business impact.
Templates
- Cluster worksheet
Topic → Intent → Page Type → Owner.
- SERP teardown table (result type, schema, search feature presence).
- Opportunity score calculator (volume * intent-fit / difficulty).
Tips
- Map 1 pillar page for every 4-6 cluster articles to support internal linking.
- Track query freshness to schedule refresh cadences.
- Align with paid search data to spot immediate conversion opportunities.
Track record
Benchmark
18 / 22
test cases passed, vs 15 / 22 without
Adoption
- Users
- 0
- Times used
- 0
Safety and source details
SkillSafety
✓ 3 of 3 passed✓Code scan15 of 15 checks clean
0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026
View 15 scanner checks
live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing
✓IntentSafe
LLM judge · does the skill do what it claims
✓ContentClean
LLM judge · policy & harmful-content review
Source
Importedgtmagents / gtm-agents
plugins/seo/skills/keyword-research/SKILL.md
View on GitHub ↗License Apache-2.0Imported 8/3/2026Version v1