OpenParable
Skip to content
← Back to skills

Canvas Update

Productivity
canvas-update

Canvas Update is an Agent Skill for productivity published in the majiayu000/claude-skill-registry repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.

Update canvas sections with new evidence. Ensures canvas stays current as the single source of truth.

View on GitHub ↗
QUICK START

How to use this skill

Bring this guide into your coding agent with a prompt tailored to the tool you use.

  1. Open your project in Codex.
  2. Copy and paste the prompt below.
  3. Review files and risks before approving any action.
Prompt to paste
Inspect the Agent Skill at https://github.com/majiayu000/claude-skill-registry/blob/HEAD/skills/workflow/canvas-update/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/canvas-update, but wait for my approval before writing files or running scripts.

Copying this prompt does not install or run the skill. Review third-party files before use.

Canvas Update

Rules

  1. Never update without evidence -- every canvas change must have a source
  2. Maintain cross-file consistency -- if you update opportunities.yml, check if north-star.yml or gist.yml need updates too
  3. Log the update -- add an entry to decision-log.md explaining what changed and why

Which Canvas File for Which Information

Information TypeCanvas FileSource
Purpose, mission, whypurpose.ymlSinek
North Star metric, inputsnorth-star.ymlNorth Star Framework
BVSSH health scoresbvssh-health.ymlSmart
Value chain, competitivelandscape.ymlWardley
Team structureteam-shape.ymlSkelton
User opportunities, OSTopportunities.ymlTorres
User needs mapuser-needs.ymlAllen
Goals, ideas, stepsgist.ymlGilad
Service quality scoresservices.ymlDowne
Go-to-market, positioninggo-to-market.ymlLauchengco
Delivery performancedora-metrics.ymlForsgren
Security threatsthreat-model.ymlOWASP
Privacy assessmentprivacy-assessment.ymlGDPR/PbD
Trust architecturetrust-signals.ymlDigital Trust
Jobs to be donejobs-to-be-done.ymlChristensen
Bounded contextsbounded-contexts.ymlEvans (DDD)
Value stream mapvalue-stream.ymlRother & Shook (VSM)
Content delivery metricscontent-metrics.ymlv0.11.0
AI tool delivery metricsai-tool-metrics.ymlv0.11.0
Service delivery metricsservice-metrics.ymlv0.11.0
Human task trackinghuman-tasks.ymlv0.11.0
Archived/discarded solutionsarchived-solutions.ymlv0.12.0
Leaf lifecycle calibrationcycle-history.ymlv0.12.0
Adaptive thresholdsthresholds.ymlv0.12.0

Workflow

  1. Identify which canvas file(s) need updating
  2. Read current state
  3. Make the update with evidence citation
  4. Check cross-file consistency
  5. Log in decision-log.md

Counter-Argument Check (Bias Mitigation)

Before applying the canvas update, draft a one-line counter-argument: "What's the strongest case AGAINST this update — what evidence or perspective would invalidate it?" If you can't articulate one, run /devils-advocate before proceeding.

This addresses the bias cluster documented in corrections.md (L5 sycophancy 2026-04-20, eval overfitting 2026-04-30, sharper-framing-isn't-righter 2026-05-03). Common shape: agent prefers what feels right over what evidence supports under competing pressure (be helpful vs. be honest, sharpen framing vs. preserve evidence base). The counter-argument step forces the missing perspective explicit, so the bias surfaces before it lands in canvas.

Especially important when interpolating user-supplied content (already untrusted per security-trust.md#prompt-injection-defense) AND when increasing a confidence value — both contexts where the agent is most likely to default toward the optimistic read.