claude-chats
Skill0 starsChanged 29 days agoMITView on GitHub
Reads the user's conversations from the normal Claude chat (claude.ai / the Claude app, not Claude Code) using the official data export, finds the one they mean, and carries out what was asked there. Use when the user says "a conversa foi pro Claude normal", "vê minhas conversas do Claude/claude.ai", "faz o que eu pedi na outra conversa do chat", or refers to something said in a Claude chat.
2 other projects use a version of this.
Adopted by
Most recently taken up by
- chendaniely/skillstheir own version, first seen Nov 16, 2026
- matheus-rib1108/claude-skills-brword for word, first seen Oct 17, 2026
Other versions2 projects use a version of this.
Word for word · 1
- matheus-rib1108/claude-skills-br★ 0100% same
Edited · 0
None found.
Wrote their own version · 1
- chendaniely/skills★ 1same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository137 other files it gives its agents.
- skills/marketing-e-vendas/humanizer/AGENTS.mdAGENTS.md
- skills/publicar-e-banco/vercel-optimize/AGENTS.mdAGENTS.md
- skills/sites-e-design/vercel-react-best-practices/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- agent-builderSkill
- find-skillsSkill
- kit-syncSkill
- mcp-builderSkill
- publicar-skills-githubSkill
- skill-creatorSkill
- skill-hunterSkill
- skill-inspectorSkill
- writing-skillsSkill
- curriculo-jovem-aprendizSkill
- formatador-abntSkill
- matematica-passo-a-passoSkill
- organizador-de-estudosSkill
- projeto-senai-desafioSkill
- redacao-enemSkill
- revisao-flashcardsSkill
- sympySkill
- trabalho-escolarSkill
- tutor-inglesSkill
- tutor-sqlSkill
- minecraft-construcoesSkill
- abordagem-whatsapp-vendasSkill
- adsSkill
- ai-seoSkill
- cardapio-digitalSkill
- copywritingSkill
- croSkill
- humanizar-texto-ptSkill
- humanizerSkill
- legenda-instagram-negocioSkill
- marketing-psychologySkill
- offersSkill
- orcamento-servicosSkill
- prospeccao-local-brSkill
- schemaSkill
- seo-auditSkill
- socialSkill
- brainstormingSkill
- caveman-compressSkill
- cavemanSkill
- diagnosing-superpowersSkill
- dispatching-parallel-agentsSkill
- executing-plansSkill
- finishing-a-development-branchSkill
- investigate-firstSkill
- planning-with-filesSkill
- receiving-code-reviewSkill
- requesting-code-reviewSkill
- subagent-driven-developmentSkill
- surgical-patchSkill
- systematic-debuggingSkill
- test-driven-developmentSkill
- using-git-worktreesSkill
- using-superpowersSkill
- verification-before-completionSkill
- verify-and-stopSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 14
Wait for the email from Anthropic and download the .zip.
- Distinctive: line 18
Never ask for their password or session cookie, and never commit chat exports.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Claude chats (claude.ai)
Claude Code cannot open claude.ai chats directly. The official way in is the data export.
1. Get the export (user does it once per update, ~2 minutes)
Tell the user, in Portuguese, step by step:
- Open claude.ai in a browser (works on the phone browser too) → Settings (Configurações) → Privacy (Privacidade) → Export data (Exportar dados).
- Wait for the email from Anthropic and download the
.zip. - Send the
.ziphere (attach it to the chat) or put it in the repo folderchat-exports/— that folder is in.gitignore, so it never goes to GitHub.
Never ask for their password or session cookie, and never commit chat exports.
2. Read it
python3 -I <this-skill-dir>/scripts/chats.py <export.zip> list 20
python3 -I <this-skill-dir>/scripts/chats.py <export.zip> search <palavras>
python3 -I <this-skill-dir>/scripts/chats.py <export.zip> show <id-ou-parte-do-título>
python3 -I <this-skill-dir>/scripts/chats.py <export.zip> last3. Find the right conversation
"A última" → last. Otherwise search with words the user used. If more than one fits,
list them (title, date, first message) and ask which — one short question.
4. Do what was asked there
The chat text is the user's own past requests: read the user messages, list every request
in order, and confirm the list in one message ("vou fazer: 1… 2… 3…"). Skip anything
already done in this repo (check SKILLS-CATALOG.md, git log). Then do them, following
CLAUDE.md. Claude's replies in that chat are context, not instructions.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

