Automated summary
Searches, browses, and extracts content from Claude Code conversation history to retrieve past solutions, code, and discussions.
Strengths
- Fast full-text search across conversations
- Ability to filter by project, role, or session
- Supports extraction of code, files, and tool outputs
- Interactive mode for guided navigation
Limitations
- Requires the conversation history index to be up-to-date
- Only works with Claude Code if the c3po skill is properly installed
- Cannot search across different AI agent platforms
When you need to recall a specific solution, code pattern, or decision from a previous conversation with Claude Code.
When the information is readily available in the current conversation or in documentation you already have.
Security analysis
SafeOnly reads local conversation history using allowed tools; no destructive, exfiltrating, or obfuscated operations.
No concerns found
How this analysis is madeExamples
Find the solution we discussed about rate limiting a few sessions ago. I need the exact code we wrote.Browse my past conversations for the project 'webapp' and show me the sessions where we worked on authentication.name: c3po description: Search and extract from Claude Code conversation history. Use when the user asks about past solutions, code they wrote before, previous discussions, or wants to find something from earlier sessions. allowed-tools: Bash, Read, Grep
Claude Conversations Skill
Search, explore, and extract from your Claude Code conversation history to find past solutions, code patterns, and architectural decisions.
Commands
# Search for keywords across all conversations
./claude-conversations search "rate limiting"
./claude-conversations search "authentication" --project "*webapp*"
# Browse projects and sessions
./claude-conversations projects
./claude-conversations sessions my-project*
./claude-conversations recent -n 20
# Read a full session transcript
./claude-conversations read abc123
./claude-conversations read abc123 --format md
# Extract specific content
./claude-conversations extract abc123 --code
./claude-conversations extract abc123 --code --lang python
./claude-conversations extract abc123 --files
./claude-conversations extract abc123 --tools Write
Instructions
-
Understand the request - What is the user looking for? A past solution, code pattern, command, or discussion?
-
Search first - Start with a broad search using relevant keywords:
./claude-conversations search "keyword" -
Narrow down - If too many results, filter by project or role:
./claude-conversations search "keyword" --project "*project-name*" ./claude-conversations search "keyword" --role assistant -
Drill into sessions - Once you find a promising session, read it or extract from it:
./claude-conversations read abc123 ./claude-conversations extract abc123 --code --lang python -
Present findings - Share the relevant code, solution, or context with the user. Adapt it to their current needs if necessary.
Tips
- Session IDs can be abbreviated to first 8 characters
- Project filters support wildcards:
*webapp*,data-* - Use
--format mdwhen exporting for documentation - The index at
~/.claude-conversations/index.dbupdates incrementally; runreindexif conversations seem missing
Interactive Mode
When user runs /c3po --interactive or asks to "browse", "explore", or "navigate" conversations interactively:
Navigation Flow
The interactive mode follows this state machine:
START → PROJECTS → SESSIONS → SESSION_DETAIL
↑ ↑ ↓
└─────────┴──── BACK ────┘
Step 1: Show Projects
Display all projects using:
./claude-conversations projects
Then use AskUserQuestion with these options:
- Select a project (show top 4 by session count as options)
- Search across all - "I want to search for something specific"
- Show recent - "Show my most recent sessions"
- Analyze patterns - "Analyze patterns across all my conversations"
Step 2: On Project Select - Show Sessions
Display sessions for the selected project:
./claude-conversations sessions "<project-name>" --summary
Then use AskUserQuestion with these options:
- Select a session (show top 4 by date as options)
- Search within project - "Search within this project"
- Go back - "Go back to projects"
- Analyze project - "Analyze this project's patterns"
Step 3: On Session Select - Show Detail
Display the session transcript:
./claude-conversations read <session-id>
Then use AskUserQuestion with these options:
- Extract code - "Extract code from this session"
- Analyze session - "Analyze what was accomplished"
- Search within - "Search for something in this session"
- Go back - "Go back to sessions list"
Step 4: Continue the Loop
Keep navigating until the user:
- Says "done", "exit", or "quit"
- Selects an "Exit" option
- Asks a different unrelated question
Analysis Capabilities
When the user asks to "analyze" at any level, use your LLM capabilities to provide insights:
Session analysis:
- Summarize what was accomplished in the session
- Identify key decisions made
- List tools and commands used
- Extract reusable patterns or solutions
- Note any problems encountered and how they were solved
Project analysis:
- Common themes across sessions in the project
- Recurring problems and how they were solved
- Tool usage patterns (most used tools, workflows)
- Technology stack insights
- Workflow and process observations
Cross-project analysis:
- Most active projects and their focus areas
- Technology patterns across projects
- Common request types the user makes
- Evolution of coding practices over time
Handling User Queries During Navigation
At any point, if the user asks a natural language question instead of selecting an option:
- "How did I solve X before?" → Search for X, read top results, summarize approaches
- "Show me all Python code for Y" → Search with project filter, extract code blocks
- "What patterns do you see?" → Analyze current context (session/project/all)
- "Find where I implemented Z" → Search, show matching sessions
Example Interactive Session
User: /c3po --interactive
Claude: Here are your projects:
[displays projects table]
Which would you like to explore?
[AskUserQuestion with project options + Search/Recent/Analyze]
User: [selects "cvxr-card-flow"]
Claude: Here are the sessions in cvxr-card-flow:
[displays sessions table with summaries]
What would you like to do?
[AskUserQuestion with session options + Search/Back/Analyze]
User: "How did I handle authentication in this project?"
Claude: [searches for "authentication" within project]
[reads relevant sessions]
[provides analysis of auth approaches used]
Would you like to:
[AskUserQuestion: Dive into a specific session / Continue exploring / Go back]
Analysis Command Support
For structured analysis output, use:
./claude-conversations analyze <session-id>
./claude-conversations analyze --project "*pattern*"
This provides tool usage statistics, file operations, and summary data that you can then interpret and explain to the user.
From the file to a first result
The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.
View the source and supporting filesThis download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.
1. Download the file
Download SKILL.mdFrom the root of a test project, save the file as .skill-downloads/claude-conversation-history-manager-mm78nnze/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.
Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.
mkdir -p '.skill-downloads/claude-conversation-history-manager-mm78nnze' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/claude-conversation-history-manager-mm78nnze/download' --output '.skill-downloads/claude-conversation-history-manager-mm78nnze/SKILL.md.part' && mv '.skill-downloads/claude-conversation-history-manager-mm78nnze/SKILL.md.part' '.skill-downloads/claude-conversation-history-manager-mm78nnze/SKILL.md'2. Check prerequisites
Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.
Tools declared by the author (check availability in your agent): Bash, Read, Grep
No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.
The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.
3. Load the skill
After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.
Claude Code
test -f '.skill-downloads/claude-conversation-history-manager-mm78nnze/SKILL.md' && test -s '.skill-downloads/claude-conversation-history-manager-mm78nnze/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/c3po' && cp -R '.skill-downloads/claude-conversation-history-manager-mm78nnze' '.claude/skills/c3po'OpenSkills
OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.
Official OpenSkills installationopenskills install './.skill-downloads/claude-conversation-history-manager-mm78nnze'openskills read 'claude-conversation-history-manager-mm78nnze'Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.
For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.
openskills syncManual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.
4. Try a first task
Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:
Read .skill-downloads/claude-conversation-history-manager-mm78nnze/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.
PDF Reader
Productivity
Read and extract text from PDF files, including documents, reports, contracts, and spreadsheets. Works with local files, URLs, and WhatsApp attachments. Use whenever PDF content is needed, even if not explicitly requested.
Discord Messaging Workflows
Productivity
Use the message tool to send, edit, and moderate Discord messages with interactive components.
Interactive Verdict Preview
Productivity
Generate an interactive HTML preview of keep/drop verdicts for maintainer review, then process the pasted feedback JSON.