devlog-skill

What This Skill Does

The devlog-skill provides OpenClaw agents with a structured, reliable method to maintain a chronological record of their development activities. By leveraging the dev-log-cli tool, the agent stores logs in a local SQLite database, ensuring that project context is preserved across sessions. This skill is essential for maintaining long-term memory regarding project milestones, blockers, and task completions, effectively acting as an external brain for your AI agent.

Installation

To integrate this skill, ensure that the dev-log-cli package is installed on the host machine. You can install the skill via the ClawHub command: clawhub install openclaw/skills/skills/crimsondevil333333/crimson-devlog-agent. The included setup.sh script will verify the availability of the CLI tool and configure the necessary pathing. Ensure your environment has pipx installed as it is the recommended method for handling the underlying CLI dependencies.

Use Cases

This skill is perfect for complex, multi-day coding projects. It helps agents track progress when switching between different tasks, provides a history of resolved bugs for future reference, and allows users to query past technical decisions. It is particularly useful for generating automated end-of-day progress reports or preparing status updates for team meetings based on the log entries recorded throughout the day.

Example Prompts

1. "Record a new log entry: Finished the OAuth2 integration for the API service, status is completed, project is Backend-Revamp."
2. "Show me the last 5 entries for Project Alpha and summarize the main blockers encountered."
3. "Search through my dev logs for any notes regarding the 'infinite loop' issue we fixed last month and explain how we resolved it."

Tips & Limitations

To maximize the effectiveness of the devlog-skill, encourage your agent to be descriptive with tags; adding context like 'feature', 'bug', or 'refactor' makes searching significantly faster. Be aware that this skill performs direct write operations to a local file system; ensure the agent has the appropriate permissions to the target directory. The primary limitation is that it does not automatically sync across remote machines unless the SQLite database file is located in a synced directory or repository. Use descriptive project names to keep the database organized as project volume increases over time.