Calibrate — Data skill for Claude Code
Run the calibration pipeline for a single fixture, all active fixtures, or resume a failed run.
How to install Calibrate
Installs to ~/.claude/commands/let-sunny-canicode-calibrate.md
mkdir -p ~/.claude/commands && curl -fsSL https://raw.githubusercontent.com/let-sunny/canicode/HEAD/.claude/commands/calibrate.md -o ~/.claude/commands/let-sunny-canicode-calibrate.md Restart Claude Code, or start a new session, for it to be picked up.
What Calibrate does
Run the calibration pipeline for a single fixture, all active fixtures, or resume a failed run.
Input: $ARGUMENTS (fixture path, `--all`, or `--resume `)
Instructions
Run the calibration script:
npx tsx scripts/calibrate.ts $ARGUMENTS
The script (`scripts/calibrate.ts`) orchestrates:
- Analyze (CLI) —
calibrate-analyze - Design tree (CLI) — generate baseline + 6 stripped design-trees
- Convert (Agent, 7 parallel
claude -psessions) — baseline + 6 s
Alternatives in Data
- Context Mode — Benchmark Results — Benchmarked against real outputs from popular Claude Code MCP servers, Skills, and dev tools 5.6k ★
- Skill Production Pipeline — Claude-skills — Effective: 2026-03-07 Applies to ALL new skills, improvements, and deployments 5.3k ★
- Ars Full — ARS full pipeline — research → write → review → revise → finalize 4.5k ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Workflow Retry
Resume a blocked workflow pipeline run from the phase where it failed. Use after manually fixing a blocked art
Reform Pipeline
End-to-end reform pipeline in one command — scan the news for a modelable reform in a topic area, score and ve
Hms Calibrate
Calibrate an HEC-HMS basin model by adjusting parameters to match observed flow data.
Preview Product
Preview the current state of a product's UI. For web products, tries real preview (the running Flask app) firs
Show Profile
Print the active kit profile (two-role pipeline autopilot free) — read-only; reads the profile triad and repor
Switch Profile
Switch the active kit profile (two-role pipeline autopilot free) — rewrite the CLAUDE.md import line and .ai/k
Related Agents
Foundry Voss
Use this agent for agent quality calibration, SKILL.md creation and refinement, agent output evaluation, crew
Bench Reviewer
Reviews eval suite quality — fixture/rubric consistency, scoring accuracy, false positive traps, difficulty ca
Test Fixtures For Consistent Test Data
@pytest.fixture def valid_user(): return User( id="test-123", email="test@example.com", name="Test User", crea