← Back to Skills Marketplace
What Did You Do
by
OpenAuthority
· GitHub ↗
· v1.0.1
· MIT-0
133
Downloads
2
Stars
0
Active Installs
2
Versions
Install in OpenClaw
/install whatdidyoudo
Description
Reconstruct and display a plain-language log of recent agent tool calls, actions taken, and decisions made.
Usage Guidance
This skill appears to do what it says and does not request extra credentials or install code. However, it reconstructs logs from the agent's conversation context and session metadata and relies on redaction rules written in prose. Before you install or use it for sensitive sessions: (1) confirm how your platform stores conversation/session metadata and who can access it; (2) test the skill in a safe session (with fake secrets) to verify redaction behavior; (3) prefer the platform's structured audit log (the SKILL.md links to an OpenAuthority plugin) for forensic needs because this skill is a narrative reconstruction, not an authoritative tamper-proof audit; and (4) avoid invoking it immediately after operations that handled high-value secrets unless you have strong assurance about redaction and storage policies.
Capability Analysis
Type: OpenClaw Skill
Name: whatdidyoudo
Version: 1.0.1
The 'whatdidyoudo' skill is designed to provide transparency by summarizing the agent's recent tool calls and actions for the user. It includes a robust redaction policy in SKILL.md to prevent the accidental disclosure of secrets, API keys, or sensitive environment variables, and it does not perform any external network requests or file system modifications.
Capability Assessment
Purpose & Capability
Name and description match the actual behavior: an instruction-only skill that reads the model's conversation context and OpenClaw session metadata to produce a human-readable action log. It does not request unrelated credentials, binaries, or config paths.
Instruction Scope
The SKILL.md explicitly says the skill reconstructs the log from the model's conversation context and session metadata and lists redaction rules. That is within scope for a 'what did you do' feature. However, because the skill is instruction-only and depends on the model to redact secrets, there is residual risk that secrets or sensitive arguments present in the conversation or metadata could be included if redaction fails or patterns are incomplete.
Install Mechanism
No install spec and no code files — lowest-risk delivery. Nothing will be written to disk or fetched at install time.
Credentials
The skill declares no environment variables, credentials, or config paths. This aligns with its stated purpose and is proportionate.
Persistence & Privilege
always is false and the skill does not request persistent privileges or to modify other skills. Default autonomous invocation remains enabled (platform default), which is reasonable for a user-invoked inspection tool.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install whatdidyoudo - After installation, invoke the skill by name or use
/whatdidyoudo - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.1
Version 1.0.1 introduces a clear redaction policy to enhance user privacy and security:
- Added a dedicated "Redaction Policy" section outlining how sensitive data (API keys, passwords, secrets, file contents) is handled and redacted in logs.
- Clarified that secrets and credential-like values are replaced with [REDACTED] in the output.
- No changes to commands or core functionality.
v1.0.0
Initial release of the **whatdidyoudo** skill — provides a plain-language reconstruction of the agent’s recent actions.
- Supports `/whatdidyoudo` to review the last 20 actions, with summaries of tool calls and decisions.
- Offers filters for action count (`/whatdidyoudo <n>`), time (`/whatdidyoudo since <time>`), file operations only (`/whatdidyoudo files`), or a high-level session summary (`/whatdidyoudo summary`).
- Draws only from the current session’s context ― not a full audit log or permanent record.
- Useful for transparency: see file ops, tests, tool invocations, and errors in your current session.
Metadata
Frequently Asked Questions
What is What Did You Do?
Reconstruct and display a plain-language log of recent agent tool calls, actions taken, and decisions made. It is an AI Agent Skill for Claude Code / OpenClaw, with 133 downloads so far.
How do I install What Did You Do?
Run "/install whatdidyoudo" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is What Did You Do free?
Yes, What Did You Do is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does What Did You Do support?
What Did You Do is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created What Did You Do?
It is built and maintained by OpenAuthority (@openauthority); the current version is v1.0.1.
More Skills