clawdotnet/openclaw.net/history-explorer
Claude Code and agent skill by clawdotnet/openclaw.net
- community
Checking that the SKILL.md file is still in the repository.
Inspect recent session conversation turns and meta-run history. Returns structured JSON summaries of turn counts, role distribution, tool usage, meta-skill executions, and co-occurrence patterns. Use this before running meta-skill-creator or when the user asks about recent history, past tool usage, or session activity.
Install
npx vskill@latest install clawdotnet/openclaw.net/history-explorerSKILL.md
History Explorer
Read-only helper that inspects OpenClaw.NET session history for downstream workflows (especially meta-skill-creator).
What It Does
Parses a JSON session snapshot and returns structured analytics:
| Key | Description | |
|---|---|---|
turns | Turn count, role distribution (user vs assistant), time span, recent turn previews | |
tools | Tool invocation frequency, top tools, tool co-occurrence in the same turn | |
meta_runs | Meta-skill execution history: skill name, status, step counts, failure codes | |
co_occurrences | Skill/tool pairs that appear together across turns | |
placeholder | Emitted when no session data is available; downstream workflows treat this as a signal to rely on user intent only |
Input Contract
The script expects JSON session data on stdin. The calling agent should pipe a JSON object matching the Session schema — specifically:
Output Contract
Always returns a JSON object. When session data is available, includes the requested analytics keys. When unavailable or unparseable, returns a single placeholder key so downstream workflows degrade deterministically.
When to Use
- Before running
meta-skill-creator: feed co-occurrence and meta-usage data
into the creator's proposal draft
- When the user asks "what skills did I use recently" or "show my session history"
- When debugging: inspect recent tool failures or meta-run error codes
- When the agent needs to recall conversation context from earlier turns
Limitations
- Read-only; never mutates session state
- Depends on the agent passing session JSON via stdin; does not access the
persistence layer directly
window_daysfiltering is best-effort on thetimestampfield- Session snapshots may be truncated by the agent for token budget reasons
Security
- Security scanPassed, 90 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingsrc/OpenClaw.Gateway/skills/history-explorer/SKILL.md
Popularity
- Repository stars
- 480
- Repository forks
- 98
- 7-day trend score
- 31
Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/clawdotnet/openclaw.net/history-explorer)