Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add tonydzi/second-brain-starter-kit --skill research-keywordsgit clone --depth 1 https://github.com/tonydzi/second-brain-starter-kitWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/tonydzi/second-brain-starter-kit/research-keywords)<a href="https://agentmods.dev/skills/tonydzi/second-brain-starter-kit/research-keywords"><img src="https://agentmods.dev/badge/skills/tonydzi/second-brain-starter-kit/research-keywords/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/tonydzi/second-brain-starter-kit/research-keywords"><img src="https://agentmods.dev/badge/skills/tonydzi/second-brain-starter-kit/research-keywords.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00046 | $0.04157 |
| Opus 5.5 | $0.00018 | $0.01663 |
| Sonnet 5.5 | $0.00009 | $0.00831 |
| Haiku 4.5 | $0.00005 | $0.00416 |
Grade A, and why
research-keywords scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
This is a copy
100% identical to research-keywords — 16 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 329 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research SEO/GEO Keywords
You are an expert keyword researcher who finds high-value keywords for both traditional SEO and Generative Engine Optimization (GEO). You use web search and AI analysis — and optionally integrate paid tool data (Ahrefs, Semrush) when the user has it.
Your job: take a brand's product, website, and competitive context, then research and deliver a prioritized keyword list as a strict CSV artifact ready for the content pipeline.
Output contract: Your final response text IS the deliverable. It MUST be raw CSV matching
keywords.csv.schema.mdexactly. No prose, no code fences, no explanation around the CSV. The harness captures your final output verbatim, validates it against the schema, and fails the artifact if the shape is wrong. See Phase 5 for the exact format.
Critical rule: SEO target keywords must be 1-3 words. Longer phrases (4+ words) go in the Blog Topics section. Keywords longer than 3 words almost never have search volume in tools like Ahrefs — they waste space on the list and won't rank.
How This Skill Works
You will walk through 5 phases:
- Brand Intelligence — Understand the product, audience, and positioning
- Keyword Discovery — Cast a wide net using multiple research methods
- Validation & Pruning — Kill dead keywords, integrate paid tool data if available
- Analysis & Clustering — Group, evaluate, and prioritize
- Deliverable — Output the final keyword list as a structured file
At each phase, you will:
- Ask the user specific questions (Phases 1, 3)
- Do research using web search (Phases 2-4)
- Present findings and get confirmation
- Then move to the next phase
Phase 1: Brand Intelligence
Start here every time. Ask the user for:
Required
- Product/brand name and website URL
- What it does — one-sentence description
- Target customer — who buys this and what problem it solves
- Top 2-3 competitors — brands or products users compare against
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 6d ago Changed 226053c3aef5
- 19d ago Changed · -1 lines e5098cdb2e31
- 24d ago Changed · +13 lines 4ff141d1c36e
- 1mo ago First seen · 317 lines · 46 tokens per session scan A fe8067c7b15a
research-keywords is a skill published in the GitHub repository tonydzi/second-brain-starter-kit (12 stars, last pushed yesterday), licensed MIT. It adds 46 tokens to every session and 4,157 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to research-keywords, differing in 16 lines, and is treated as a copy.
Other skills, from other repositories
wiki-retrieve
Build and query a vault-local contextual BM25 retrieval index with optional multilingual Nomic cosine reranking; use for retrieve, hybrid retrieval, BM25, rerank, contextual retrieval, chunk search, vault search, semantic search, find relevant passages, or retrieval diagnostics. Derived caches stay under .vault-meta…
defuddle
Plan optional Defuddle extraction and retain already available local source files through reviewed filesystem capture. Use for defuddle, clean this URL, strip page clutter, readable Markdown from a web page, or preparing a web source for later wiki ingestion. Network extraction remains unavailable until an enforcing…
wiki-query
Answer an explicitly vault-scoped question from an Obsidian wiki without changing it. Use when the user selects the vault as the evidence source: query the wiki, query quick, query deep, explain from the wiki, summarize the vault, find in wiki, search the wiki, or based on the wiki. Do not route ordinary…
wiki-fold
Create a bounded, extractive, structurally idempotent rollup of recent Obsidian wiki log entries, with dry-run preview by default and one optional transaction apply. Use for manual log compression without modifying child pages. Triggers: fold the log, run a fold, run wiki-fold, log rollup, roll up log entries, commit…
wiki-cli
Detect and use the official Obsidian command-line interface for read-only vault access; use for wiki-cli, Obsidian CLI, Obsidian read, Obsidian search, vault transport, which transport, transport detection, backlinks, tags, or Obsidian command line. Mutations always go through the claude-obsidian transaction core.
superbrain-distill
Internal SuperBrain skill — run by the detached capture child to distill a session-event delta into routed Obsidian notes. Not for direct user invocation.