Tracely is a CI/CD system for AI agents that turns failed production traces into replayable regression tests. Development teams use it to detect and group agent failures, run the resulting cases on pull requests, and block changes that reproduce those failures. The catalogue entries provide skills for operating this trace-based testing and observability workflow.
Borrowing it
Nothing to install: this file belongs to Jwuthri/Tracely-ai. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Jwuthri/Tracely-ai/master/.claude/skills/keyword-clustering/SKILL.mdgit clone --depth 1 https://github.com/Jwuthri/Tracely-aiWrote 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/jwuthri/tracely-ai/keyword-clustering)<a href="https://agentmods.dev/skills/jwuthri/tracely-ai/keyword-clustering"><img src="https://agentmods.dev/badge/skills/jwuthri/tracely-ai/keyword-clustering/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/jwuthri/tracely-ai/keyword-clustering"><img src="https://agentmods.dev/badge/skills/jwuthri/tracely-ai/keyword-clustering.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 | $0.00017 | $0.00784 |
| Opus 5 | $0.00009 | $0.00392 |
| Sonnet 5 | $0.00003 | $0.00157 |
| Haiku 4.5 | $0.00002 | $0.00078 |
Grade A, and why
keyword-clustering 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 11d 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
86% identical to keyword-clustering — 9 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenSEO Keyword Clustering
Goal
Group keywords into page-level clusters and decide which existing or new page should target each cluster. This is a keyword mapping workflow, not just a semantic grouping exercise.
Required inputs
projectId- A keyword list, saved keyword tag, seed topic, or target domain
- Optional existing URLs/pages to map against
If keywords are not provided, use list_saved_keywords for saved sets, research_keywords for seed discovery, or get_ranked_keywords when the user starts from a target domain.
OpenSEO MCP tools
list_saved_keywords: fetch an existing keyword set, optionally filtered by tags.research_keywords: expand a seed when the user starts from a topic.get_ranked_keywords: gather exact ranking keywords and URLs when the user starts from a domain or page.get_search_console_performance: when Search Console is connected, pull real queries withdimensions: ["query","page"]to map terms to the pages already earning impressions and to surface cannibalization (one query splitting clicks across multiple URLs).get_serp_results: validate whether keywords belong on the same page by checking SERP overlap and intent.get_local_serp_results: use for local SEO clusters when Maps/local-pack intent should affect page mapping.save_keywords: optionally tag final clusters after user confirmation.
Workflow
- Gather the candidate keyword set.
- Use
get_search_console_performance(dimensions["query","page"]) when Search Console is connected to start from real queries and the pages already ranking for them. - Use
get_ranked_keywordsfor domain/page-driven clustering. - Use
search_local_businessesandget_local_serp_resultswhen proximity, local packs, or Google Business results determine whether terms belong on location pages.
- Use
- Remove duplicates, irrelevant terms, and terms that clearly require a different product or audience.
- Build clusters around intent and page type:
- Same SERP intent and similar ranking pages belong together.
- Different intent, buyer stage, or SERP format should be split.
- Similar words do not guarantee the same cluster.
- For important borderline terms, use a small
get_serp_resultsbatch to check overlap. - Assign each cluster to:
- Existing URL, if supplied and appropriate
- New page recommendation, if no existing page fits
- Do-not-target / later bucket, if weak or off-strategy
- Identify cannibalization risk when multiple pages would target the same intent. When Search Console is connected, confirm it from real data with
get_search_console_performance(dimensions: ["query","page"]) — the same query sending impressions to multiple URLs. - Ask before applying cluster tags with
save_keywords.
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.
- 11d ago First seen · 77 lines · 17 tokens per session scan A ff9ba08dddef
keyword-clustering is a skill published in the GitHub repository Jwuthri/Tracely-ai (1,404 stars, last pushed yesterday), licensed MIT. It adds 17 tokens to every session and 784 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 86% identical to keyword-clustering, differing in 9 lines, and is treated as a copy.
Other skills, from other repositories
Prompt Version Control Workflow
Sets up a prompt versioning system with naming conventions, diff tracking, A/B evaluation gates before promotion, and rollback triggers.
llm-tester
You are the LLM Tester, specializing in systematic prompt evaluation, red-teaming, and LLM output quality assurance. You replace "vibes-based" AI evaluation with rigorous, automated, and repeatable verification suites.
report-publisher
Publish an already validated report to an external release destination.
report-validator
Validate local report.json files without publishing or modifying them.
report-repair
Repair invalid local report.json files by inserting required report fields.
local-validator
Validate a local report.json file with a deterministic check-only script and no network access.