project bootstrap
set up agent instructions in a new project.
Initialise an AGENTS.md file in this project folder. Also create a CLAUDE.md which simply points to AGENTS.md using "@AGENTS.md"
set up agent instructions in a new project.
Initialise an AGENTS.md file in this project folder. Also create a CLAUDE.md which simply points to AGENTS.md using "@AGENTS.md"
keep a personal site out of search results.
Make this personal website search-resistant: add noindex, nofollow, noarchive, nosnippet, noimageindex via HTML metadata and global HTTP headers, add robots.txt with Disallow: /, ensure private pages and assets require authentication, then verify these protections on the deployed site.
let the agent parallelise work across subagents.
Feel free to spawn multiple subagents as needed to do the tasks in parallel (if possible without creating any conflict/issue). Decide the model and thinking/effort of the subagent based on requirements of the task.
split one task into parallel agents with their own goals.
For this task, write yourself a new goal and spawn agents in parallel, as many as needed to do it better and faster. Split the work into independent pieces, dispatch them concurrently, and synthesize the results as they return. Give each agent its own dedicated /goal.
carry context from one assistant to another.
You are helping me import context from one AI assistant to another. Your job is to go through our past conversations in this project [project-name] and sum up what you know. In the output, please avoid using any first-person pronouns (I, my, me, mine) and any second-person pronouns (you, your, yours). Instead, refer to the individual you have learned about as "the user" or use neutral phrasing. Preserve the user's words verbatim where possible, especially for instructions and preferences.
test onboarding docs from a clean machine, over and over.
Test [repository] from a clean disposable environment. Follow only its onboarding documentation. When a step fails or assumes missing knowledge, record the gap, fix the smallest documentation or setup issue, discard the environment, and start again. Carry no dependencies, configuration, credentials, or manual repairs between attempts. Stop when one uninterrupted run reaches [documented ready state], progress stalls, or [budget] ends. Finish with the verified commands, gaps closed, and remaining blockers.
keep adding logs until every important path is covered.
Review the system's logging and add missing coverage until every important path produces useful, tested logs.
audit, fix and re-measure search and ai-answer visibility.
Run an SEO/GEO audit across crawlability, indexation, page intent, titles, internal links, structured data, source citations, and answer-first content. Rank the gaps by expected impact, fix the highest-leverage issue, then rerun the same crawl and target-query benchmark across search engines and AI answer engines. Repeat until no critical technical issues remain, every priority query maps to a clear answer-ready page, and the benchmark shows no high-impact gap left to fix.
set up agent instructions in a new project.
Initialise an AGENTS.md file in this project folder. Also create a CLAUDE.md which simply points to AGENTS.md using "@AGENTS.md"
keep a personal site out of search results.
Make this personal website search-resistant: add noindex, nofollow, noarchive, nosnippet, noimageindex via HTML metadata and global HTTP headers, add robots.txt with Disallow: /, ensure private pages and assets require authentication, then verify these protections on the deployed site.
let the agent parallelise work across subagents.
Feel free to spawn multiple subagents as needed to do the tasks in parallel (if possible without creating any conflict/issue). Decide the model and thinking/effort of the subagent based on requirements of the task.
split one task into parallel agents with their own goals.
For this task, write yourself a new goal and spawn agents in parallel, as many as needed to do it better and faster. Split the work into independent pieces, dispatch them concurrently, and synthesize the results as they return. Give each agent its own dedicated /goal.
carry context from one assistant to another.
You are helping me import context from one AI assistant to another. Your job is to go through our past conversations in this project [project-name] and sum up what you know. In the output, please avoid using any first-person pronouns (I, my, me, mine) and any second-person pronouns (you, your, yours). Instead, refer to the individual you have learned about as "the user" or use neutral phrasing. Preserve the user's words verbatim where possible, especially for instructions and preferences.
test onboarding docs from a clean machine, over and over.
Test [repository] from a clean disposable environment. Follow only its onboarding documentation. When a step fails or assumes missing knowledge, record the gap, fix the smallest documentation or setup issue, discard the environment, and start again. Carry no dependencies, configuration, credentials, or manual repairs between attempts. Stop when one uninterrupted run reaches [documented ready state], progress stalls, or [budget] ends. Finish with the verified commands, gaps closed, and remaining blockers.
keep adding logs until every important path is covered.
Review the system's logging and add missing coverage until every important path produces useful, tested logs.
audit, fix and re-measure search and ai-answer visibility.
Run an SEO/GEO audit across crawlability, indexation, page intent, titles, internal links, structured data, source citations, and answer-first content. Rank the gaps by expected impact, fix the highest-leverage issue, then rerun the same crawl and target-query benchmark across search engines and AI answer engines. Repeat until no critical technical issues remain, every priority query maps to a clear answer-ready page, and the benchmark shows no high-impact gap left to fix.