gemini-history-analyzer
An agent skill by daymade, from daymade/claude-code-skills. Tags: analysis, data, generative, history, research.
What it does
Analyze Google Takeout exports of Gemini conversation history. Use when the user mentions Gemini takeout, Gemini export, Gemini history, Gemini conversation analysis, Google Takeout zip analysis, or drags a takeout zip into the project. Also use when the user asks to "analyze my Gemini data", "what did I talk to Gemini about", or wants to extract insights from Gemini chat logs.
Install
With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:
npx skills add daymade/claude-code-skills --skill gemini-history-analyzerOr copy the skill folder into Claude Code's skills directory by hand (~/.claude/skills for every project, or .claude/skills inside one):
git clone --depth 1 https://github.com/daymade/claude-code-skills
cp -r claude-code-skills/gemini-history-analyzer ~/.claude/skills/gemini-history-analyzerSafety box score
Grade C, moderate risk: 33 of 100 risk points, rated 2026-10-19. The grade rates what the skill and its scripts can reach on the machine of whoever installs it, across eight categories from shell execution to secrets access. How the score works.
This skill unpacks and analyzes Google Takeout Gemini history archives using shell commands, and it can optionally write memory files and delete the extracted workspace. The main risks are local environment changes from Homebrew installation, recursive cleanup of extracted data, and handling of sensitive personal content in the archive.
| Category | Level | Why |
|---|---|---|
| Code & shell execution | 1 (low) | It relies on shell commands like `unar`, `find`, `grep`, and `du` for extraction and analysis, but it does not ship a binary or evaluate downloaded code. |
| Network access | 1 (low) | The only clear network use is `brew install unar 2>/dev/null || true`, which may fetch a dependency from package repositories; the skill otherwise stays local. |
| Filesystem reach | 2 (moderate) | It reads and writes local files, may create memory files under `.claude/projects/<path>/memory/`, and explicitly ends with `rm -rf <extract-dir>` for cleanup. |
| Secrets & credentials | 1 (low) | The skill is designed to inspect archives that may contain PII and sensitive documents, with a dedicated `PII / Sensitive Content` section and examples like resumes and contact lists. |
| Privilege & persistence | 2 (moderate) | `brew install unar` modifies the user's environment and installs software, so it can change the machine beyond the project directory. |
| Instruction hijack surface | 0 (none) | There are no instructions to ignore safeguards, hide actions, or follow remote content; the file is straightforward analysis guidance. |
| Irreversible actions | 1 (low) | It can autonomously create/update memory files and perform cleanup deletion after analysis, but it does not post, deploy, message, or act externally. |
| Transparency | 0 (none) | The skill is plain Markdown with visible commands and no binaries, obfuscated blobs, or unpinned remote installers. |
Before installing
- Read `SKILL.md` and decide whether you want the optional memory-file behavior enabled.
- If you care about isolation, run it in a scratch directory and verify `rm -rf <extract-dir>` points only at that temp folder.
- Check whether `unar` is already installed before allowing `brew install unar`.
- Assume the Takeout archive may contain sensitive personal documents and review the generated report before sharing it.
Rated 2026-10-19 by an automated review of 1 file from the skill's repository.
Source
- Repository
- daymade/claude-code-skills (all skills from this repository)
- Path
- gemini-history-analyzer/SKILL.md
- Branch
- main
- Updated
- 2026-09-20
Related skills
- competitor-profiling — When the user wants to research, profile, or analyze competitors from their URLs.
- prospecting — When the user wants to find, qualify, and build a list of prospects to reach out to — across B2B SaaS, general B2B, or local small businesses.
- recall — Reconstruct your recent working context from your own chat history, live state, and the shared record (user reports, prior fixes, incidents).
- arena — Spawn N parallel candidates at the same task, pick a base, graft the strongest parts of the losers into it.
- customer-research — When the user wants to conduct, analyze, or synthesize customer research.
- exploring-data-catalog — Full inventory and audit of AWS Glue Data Catalog assets across S3 Tables, Redshift-federated, and remote Iceberg catalogs.