ralph-calibrate
Run Ralph calibration checks to analyze intention drift, technical quality, and self-improvement opportunities. Use when user asks to "ralph calibrate", "check drift", "analyze sessions", or needs to verify work alignment.
npx skills add majiayu000/claude-skill-registry --skill ralph-calibrate --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Ralph Calibrate Run calibration checks to ensure code and agent behavior align with planning intentions. ## Execution Instructions When this skill is invoked, check the ARGUMENTS provided: ### If argument is `intention`: Run intention drift analysis to verify completed subtasks align with planning chain (Vision → Story → Task → Subtask). **Prerequisites check first:** 1. Look for `subtasks.json` in the project root 2. If not found, output a helpful message and exit gracefully: > "No subtasks.json found. Nothing to analyze for intention drift. > > To run intention drift analysis, create a subtasks.json file with completed subtasks that have commitHash values." 3. If found but no completed subtasks have `commitHash`, output: > "No completed subtasks with commitHash found. Nothing to analyze." If prerequisites are met, follow: @context/workflows/ralph/calibration/intention-drift.md ### If argument is `technical`: Run technical quality analysis to check code quality patterns. **Prerequisites check first:** 1. Look for `subtasks.json` in the project root 2. If not found, output a helpful message and exit gracefully: > "No subtasks.json found. Nothing to analyze for technical drift. >
- Execution Instructions
- If argument is intention:
- If argument is technical:
- If argument is improve:
- If argument is all:
- If no argument or unknown argument:
- Usage
- Examples
- Subcommands
- Options
- Intention Drift Analysis
- What It Checks
- Output
- Technical Drift Analysis
Check for intention drift on completed subtasks Analyze technical quality patterns Analyze session logs for agent inefficiencies Run all calibration checks in sequence Skip approval prompts and create task files automatically Require approval before creating any task files aaa ralph calibrate <subcommand> [options]
What does the ralph-calibrate skill do?
Run Ralph calibration checks to analyze intention drift, technical quality, and self-improvement opportunities. Use when user asks to "ralph calibrate", "check drift", "analyze sessions", or needs to verify work alignment.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill ralph-calibrate --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.