developer-keyword-research skill (samber): find what developers search for
Builds a ranked keyword map for a developer product from what developers actually search, using your own data over tool volume.
- Installs
- 12.4K
- on skills.sh
- Stars
- 7
- on GitHub
- Files
- 5
- besides SKILL.md
- Updated
- Nov 2026
- last repo commit
developer-keyword-research turns scattered evidence of what developers ask into an evidence-backed keyword map that other people can write against. It harvests first-party demand (search console queries at position 5-20, docs-site search logs, support tickets, issues, error counters), clusters error strings, expands by query family, judges winnability and routes each cluster to one target page. It ranks by outcome per page-hour and refuses queries it says cannot be won.
It triggers on "what developers actually search for", "an error-message keyword list" or "which docs pages to create from search demand". It bundles no scripts. SKILL.md says it does not write the pages, and sends on-page and technical SEO to docs-seo.
Good for
- Docs and DevRel teams choosing which pages to write next
- Support leads with a ticket queue full of repeat error messages
- Product teams launching an SDK who need pages to ship with it
Install developer-keyword-research
Claude Code
- 1
Copy this prompt.
Install the developer-keyword-research skill in Claude Code. Run this command: /plugin marketplace add samber/developer-relations-skills /plugin install developer-relations-skills@developer-relations-skills Then check that it loaded and tell me how to use it.
- 2
Paste it into Claude Code. It shows the change and asks before running it.
The README recommends installing the whole collection because its skills reference each other, and developer-keyword-research names other skills in the collection to hand work to. The whole-collection routes add all 93 skills in the repo (counted from the git tree); the repo holds no hooks, agents, commands or MCP server files, and 14 of its skills bundle a script. Pick one route per agent.
From the project README. Source.
What's in the skill
When it loads
Builds a prioritized keyword list for technical search queries (error strings, "how to X in Y" tasks, integration intents, comparisons, migrations) mined from docs search logs, support tickets, issue trackers and first-party query data rather than keyword-tool volume. Use whenever the user asks what developers actually search for, wants keywords for a developer tool, API, SDK or docs site, an error-message keyword list, demand sizing for a technical topic, or which docs pages to create from search demand - even if they never say "keyword". Does not write the pages. Do NOT use for on-page or docs-site SEO - use samber/developer-relations-skills@docs-seo.
Sections in SKILL.md
- Interview
- Workflow
- Pulling the striking-distance set
- The merge test
- Query families
- Demand evidence
- Winnability
- Invocation examples
- Output
- Scope
- Ranked clusters
- Company-adoption set
- Fix first
- Do not target
- Backlog
- Pass threshold
Key facts
- Skill version
- 1.0.2 (SKILL.md metadata)
- Installs on skills.sh
- 12,430 (Nov 2, 2026)
- Last repo commit
- Nov 1, 2026
- Audits on skills.sh
- Gen Agent Trust Hub: pass, Socket: pass, Snyk: warn
What it includes
Asks 9 questions, including which data sources you can actually pull from.
InterviewRuns ten steps from framing scope to a keyword map checked against a threshold.
Ten steps from framing scope to a keyword map checked against a pass threshold.
WorkflowPulls queries at average position 5-20 and joins them to landing pages.
Pulls queries at average position 5-20 from a search console export and joins them to landing pages.
Striking-distance setCounts shared top-ten results to decide between one page and several.
Counts shared top-ten results to decide one page or several: 7-10 one page, 4-6 one cluster, 2-3 cross-link, 0-1 unrelated.
Merge testCovers eight families, from error strings and reference lookups to comparisons.
Eight families from error strings and reference lookups to migration, comparison and concept pages.
Query familiesRanks eight sources, from first-party query data down to keyword-tool volume.
Eight sources from first-party query data to keyword-tool volume, harvested in efficiency order.
Demand evidence tiersNames the incumbent and the weakness to beat, and refuses three unwinnable categories.
WinnabilityProduces a report with scope, ranked clusters, a company-adoption set and a backlog.
A markdown report with scope, ranked clusters, a company-adoption set, fix first, do not target and backlog.
OutputRequires six checks, including evidence on every keyword and a do-not-target list.
Six checks, including at least one evidence item per keyword and a non-empty do-not-target list.
Pass threshold
From the official docs
Permissions
Low risk
developer-keyword-research is analysis instructions with no scripts, and it may save notes to devrel-context.md.
What it can do
- Read your data
- Create and change things
- Delete things
- Read-only mode
Watch out for
Support tickets and logs go into the conversation
SKILL.md draws demand evidence from support tickets, issue trackers, docs-search logs and error telemetry. Scrub customer content before pasting it, as SKILL.md itself advises. github.com
It may save notes to devrel-context.md
SKILL.md tells Claude to keep task and project context in devrel-context.md when memory lives in a file, or in the memory system your tool already uses. Check the file before you commit it. github.com
The whole-set install adds 93 skills, 14 with scripts
The README says to install every skill. The git tree has 93 skill folders, and 14 of them hold .py or .sh files. This skill bundles no scripts, and the tree holds no hooks, agents or MCP config files. github.com
Technical details
| Turning on read-only | SKILL.md describes no read-only mode. |
|---|---|
| Sign-in and keys | SKILL.md names no account, key or token. |
| Scopes |
|
Questions
What does developer-keyword-research do?
It builds a prioritized keyword list for technical search queries such as error strings and how-to tasks. Every keyword carries evidence with a source, count, date and a measured, user-provided or estimated label.
How do I install it?
Use the install box at the top. The README says to install every skill in the repo, because the skills point to each other. The box shows the whole-set route for each app.
Does it need a keyword tool or API key?
SKILL.md names no key. It ranks on your own data and uses keyword-tool volume only as a tiebreaker. It tells Claude to write N/A rather than invent a number when a source returns nothing.
What data do I need to give it?
Whatever the interview finds you can pull: a search console export, docs-site search logs, support-ticket subjects, issue-tracker questions or error-code counters. If a source is unavailable, SKILL.md has it downgrade that tier rather than guess.
Is it safe to install?
The skill bundles no scripts. Support tickets, search queries and logs you paste go into your conversation, and SKILL.md says customer content you cannot scrub or quote deletes the support-ticket source. The whole-set install adds 93 skills, 14 of which bundle scripts.
How is it different from docs-seo?
This skill decides which queries to target. SKILL.md routes on-page and docs-site SEO to samber/developer-relations-skills@docs-seo, and error page content to developer-troubleshooting-docs.
Information
updated Nov 2, 2026
- Repository
- samber/developer-relations-skills
- Folder
skills/developer-keyword-research
Sources
Docs, issue trackers and discussions this page is built from.
Show all 3Hide
- README · github.com
- developer-keyword-research SKILL.md · github.com
- LICENSE · github.com