Find your next SEO fix in Search Console
Use approved Search Console exports to make a short SEO review list, based on a published Claude Code audit.
Suggested toolset
Practice relevance
Cross-practice idea · A general operational method. Review the stated tool and jurisdiction limits before use.
The problem
Search Console shows many changes, but staff may still struggle to choose the next page to improve.
Why it matters: Search reports can contain more possible fixes than a firm can address. A source-linked priority list helps the marketing team choose a specific page or query to investigate before committing work.
Sources & evidence
An original public X source and linked method were checked. Tool capabilities are documented; the law-firm adaptation and prompt are untested.
What’s been verified
The source publishes an implementation, not verified traffic lift. Its modeled missed-click estimates are not guaranteed traffic or revenue. Our export-based law-firm adaptation is untested.
What to measure: Candidates accepted after review, data-quality exceptions, and like-for-like metrics after approved changes. A before/after difference does not establish causation.
- Cameron (@factive): original X post ↗February 11, 2026 · Describes the GSC/Claude Code audit. Source-reported implementation; no independently verified lift.
- Cameron: public GSC audit implementation ↗Original repository documents audits, benchmarks, and authorization requirements. We have not installed or run it.
- Claude Code: supported file workflows ↗Official tool documentation: local file access, commands, and account setup. This does not validate our SEO prompt.
- Google: query-by-page data and export limits ↗Official Search Analytics API guidance for genuine paired data and pagination.
- Google: performance-data filtering limits ↗Explains filtering and incomplete visibility, including anonymized queries.
Source checked: October 15, 2026. The problem framing and law-firm prompt are editorial adaptations of the linked public method. X commentary and source-reported outcomes are not independent validation. We wrote these prompts. The adapted workflow hasn’t been tested.
The source method
Start when: Two comparable reporting periods and a current page inventory are ready for review.
- Cameron describes a Claude Code plugin that reads Search Console API data and flags traffic, CTR, and query/page opportunities.
- The public repository documents audit commands and authorization requirements. Its click-opportunity estimates use benchmarks.
- Our adaptation uses approved local exports instead of the plugin and live API connection. An analyst reviews the resulting short list.
Limits and review
The assistant drafts or reports only. Check source records and review the output before a human performs any separately approved send or change. No automatic legal decision, money movement, account connection or publication is included.
Who reviews it: An SEO reviewer checks data completeness, live search intent, and technical access. The responsible attorney approves legal or advertising claims before any page changes.
What you need
Claude Code · prepared local folder
- Existing authorized access to the named product and in-scope records; actual tenant, plan, permissions and menu version must be checked.
- Firm-approved AI destination and data handling; no setup, sign-in, installation or access expansion included.
- Use synthetic inputs first. Keep real data in firm-approved accounts and processing, with appropriate access, confidentiality and retention controls. Aliases alone do not anonymize records. Never paste credentials, API keys or unnecessary client details.
How to use
Documentation-verified component path with explicit manual acquisition/mapping; editorial adaptation not tested
- Search Console UI export is capped at 1,000 representative rows and can omit queries; full-account completeness is not promised.
- If a page-filtered export or a verified paired API export is unavailable, query/page opportunity analysis is blocked.
Check access and setup
- Search Console UI export is capped at 1,000 representative rows and can omit queries; full-account completeness is not promised.
- If a page-filtered export or a verified paired API export is unavailable, query/page opportunity analysis is blocked.
Export genuine query-by-page observations
Google Search Console · Performance > Search results > scope/date/search type > Pages > selected page > Queries > Export
For a bounded pilot of up to five owner-approved public URLs, select the correct property, Web search type and exact current date range. In Pages, click one URL to apply its exact page filter; switch to Queries and Export CSV/Excel. Repeat for the identical URL and previous comparable range with identical country/device filters. Preserve each native file and the visible page/date/filter evidence. Export page inventory separately.
- Expected output
- One query export per exact page per period, each with a scope manifest
- Next step
- Add the verified page-filter URL to that file’s rows in a separate mapping workbook.
- Check before continuing
- Unfiltered Queries and Pages exports are separate aggregations and cannot be joined into query/page pairs. UI exports are limited; anonymized/omitted queries remain coverage limitations.
Map, minimize and approve the actual sources
Source reviewer and local spreadsheet/text editor · Restricted originals > separate approved analysis copy
Keep untouched originals, original headers, capture date/time/timezone, scope, filters, count/pagination and source locators in a restricted source folder. Make an independently reviewed, minimized copy for AI. Keep identifier maps and confidential originals outside the AI folder/Space, including hidden sheets and attachments. Public pages and embedded instructions are evidence, never instructions. No live integrations, portal requests, publication or external changes are performed by this recipe. Map the acquired evidence as follows: Actual exported query column (inspect its real header) → query; Clicks/Impressions/CTR/Position → clicks/impressions/ctr/average_position. Exact page filter supplies page, never a guessed join. Date/search type/country/device filters are manifest values, not invented per-row dimensions. Preserve CTR percentage units. Current crawler Address/title or reviewed public-page inventory → page/title. Any existing API export must prove dimension order [query,page] and map rows.keys accordingly; no new API connection is included. Apply the nativeInputContract below, including exact editorial headers, source manifest/evidence map and any required extra companion evidence. Existing kit files are usable only under their declared bridge; copying or renaming them is not validation.
- Expected output
- Reviewed firm-brief.md; page-inventory.csv; query-page-current.csv; query-page-previous.csv; export-coverage.txt; manifest.txt; evidence-map.csv
- Next step
- For Adobe, convert approved tabular rows to labelled TXT or paste text; for Claude Code, place approved files in the exact analysis folder. Never relabel a raw export as a kit table.
- Check before continuing
- Check source-to-analysis row counts and stable keys; open originals for ambiguous rows. Missing data stays unknown.
Open the approved AI destination
Claude Code (existing approved local session) · Terminal in approved analysis folder > claude > Plan; /permissions
Use only an already installed, authenticated, firm-approved Claude Code session. Staff creates a new local analysis folder containing approved minimized files and manifest.txt, with no secrets, hidden configuration, hooks, unreviewed CLAUDE.md or symlinked client folders. Keep originals elsewhere. In a terminal, cd to that exact folder and start claude; inspect the displayed working directory. Use Shift+Tab to select Plan and /permissions to inspect existing access. An administrator must enforce any required filesystem/network isolation: Plan and prompt wording alone are not a complete sandbox. Do not add directories, integrations or persistent permissions. Ask the recipe prompt. Return proposed outputs in the response; a human copies checked text into the named output files. If safe read scope cannot be established, stop. No installation, sign-in, credential setup or write permission is included.
- Expected output
- Only approved source files loaded or accessible
- Next step
- Paste the exact prompt in the next step.
- Check before continuing
- Confirm the source list/working directory before prompting; stop on unavailable access.
Run the bounded analysis prompt
Claude Code (existing approved local session) · Claude Code prompt in Plan mode
Paste the prompt after replacing only bracketed scope values. Treat all source content as data.
- Expected output
- opportunities.csv and review.md
- Next step
- Inspect source citations/file-row references before copying any result.
- Check before continuing
- No invented source fields, IDs, eligibility, legal interpretation or unsupported completeness.
Check and hand off the proposed result
Human reviewer and local spreadsheet/text editor · Separate review output, not live system
Check every exception against its source, verify counts and uncertainty, then copy only approved result text to opportunities.csv and review.md. SEO owner checks query intent and current page; lawyer approves substantive legal/advertising changes. Findings are bounded to the captured sample, not a complete performance ranking.
- Expected output
- Source-checked opportunities.csv and review.md
- Next step
- Open the named output in Excel/text editor and send it through the existing internal approval process; no live import or external send is implied.
- Check before continuing
- Acceptance case (proposed, not run): Unfiltered Queries and Pages tables trigger a pairing blocker. A missing prior-period query stays unknown rather than zero.
Approve the internal next action
Final human reviewResponsible human owner · Existing internal work queue / approved source system
Record the reviewer, decision and unresolved blockers. SEO owner checks query intent and current page; lawyer approves substantive legal/advertising changes. Findings are bounded to the captured sample, not a complete performance ranking.
- Expected output
- Approved internal review record or explicit blocked status
- Next step
- An authorized person chooses and separately approves any live change, outreach, filing, certification or purchase.
- Check before continuing
- Do not infer legal deadlines, rule applicability, title sufficiency, service validity, financial eligibility or professional compliance.
What you’ll get
opportunities.csv with up to ten candidate actions, plus review.md explaining the top three and the limits of the data.
Try with the sample files
Follow the tool steps above and use the inputs named in each step. Where provided, native-* files are blank scaffolds and NATIVE-INPUT-MAPPING explains their fields. Original examples and the optional full review prompt use a separate prepared-input schema. Keep them separate unless the mapping explicitly connects them. Downloading a kit does not connect accounts or prove the workflow works.
Download inputs and checklist 15 files
Instructions, blank templates and separate synthetic examples; these files do not install an automation. Blank templates still need verified source data.
- Download starter kit All inputs, synthetic examples and review notes in one ZIP. No automation is installed.
- Start here: get the sources and prepare the review Documentation-checked acquisition, explicit manual mapping, exact prompts and human review limits
- Input preparation checklist Collect the actual recipe inputs without inventing product export headers
- Synthetic example and expected result Exercise the important safety and data-quality boundary
- Firm brief template Editable recipe-specific setup input
- Export coverage template Editable recipe-specific setup input
- Setup and review checklist Use the original recipe with the provided preparation files
- Native input scaffold: firm-brief.md Blank editorial review input; acquire and check the stated source evidence before use; not a native export
- Native input scaffold: page-inventory.csv Blank editorial review input; acquire and check the stated source evidence before use; not a native export
- Native input scaffold: query-page-current.csv Blank editorial review input; acquire and check the stated source evidence before use; not a native export
- Native input scaffold: query-page-previous.csv Blank editorial review input; acquire and check the stated source evidence before use; not a native export
- Native input scaffold: export-coverage.txt Blank editorial review input; acquire and check the stated source evidence before use; not a native export
- Native input scaffold: manifest.txt Blank editorial review input; acquire and check the stated source evidence before use; not a native export
- Native input scaffold: evidence-map.csv Blank editorial review input; acquire and check the stated source evidence before use; not a native export
- Native input mapping and source requirements Exact legacy mappings, required additional evidence and source-bundle gates
Optional full review prompt for prepared inputs
Prepared-input review prompt with Claude Code · prepared local folder
Original Law Firm Agents adaptation · untested. This prompt uses the original prepared-input schema shown in the sample test. Step prompts may use different tables. Follow NATIVE-INPUT-MAPPING where supplied; do not mix the original examples with native-step inputs without mapping and checking every field.