mr-wolv/skill_playground_bakr101_2026/assumption-and-bias-check

Claude Code and agent skill by mr-wolv/skill_playground_bakr101_2026

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Surface hidden assumptions, cognitive biases, blind spots, and overconfidence before a decision or output stands. Use when stakes are high, when a confident answer would be expensive to undo, when a plan rests on unstated premises, or when you want a second-pass integrity check on reasoning. Pairs with doubt-driven-development and analytical-thinking-patterns.

Install

npx vskill@latest install mr-wolv/skill_playground_bakr101_2026/assumption-and-bias-check

SKILL.md

The same SKILL.md was published earlier as mr-wolv/skill_playground_bakr101_2026/assumption-and-bias-check.

Assumption & Bias Check

Engineering failures rarely come from bad math; they come from an assumption nobody stated, a bias nobody noticed, or a confidence nobody earned. This skill is a structured adversarial pass over a decision, plan, or analysis to surface those gaps. It is technology-independent and composes with any engineering capability.

When to use

  • Before a high-stakes decision (production change, architecture choice, security

logic, irreversible operation).

  • When a plan's premises were never written down.
  • When you (or the user) feel unusually sure.
  • After a first draft of analysis, as a validation gate.

Check protocol

1. Extract explicit claims

List every factual claim and decision in the artifact. Separate stated from implied.

2. Surface hidden assumptions

For each claim, ask: "What must be true for this to hold that we have not said?" Common engineering traps:

  • "The dependency is stable." (version/compatibility risk)
  • "Traffic will be like last quarter." (no load change)
  • "They will use it as documented." (abuse/edge cases)
  • "This fixes the root cause." (correlation vs causation)
  • "We can roll back." (rollback untested)
3. Flag bias patterns
  • Confirmation bias — only evidence that supports the chosen approach sought.
  • Availability bias — recent similar incident over-weighted.
  • Sunk-cost — keeping a direction because effort is spent.
  • Anchoring — first number/estimate unduly fixes the range.
  • Optimism bias — timelines/risks underestimated.
  • Status-quo — defaulting to the existing design without reason.
4. Estimate confidence honestly

Assign a confidence level per claim with a reason:

  • High — verified, reproducible, owned.
  • Medium — plausible, partially checked.
  • Low — assumed, unverified, or contradicted by one signal.

Report where confidence is low but the decision treats it as high.

5. Emit the findings

ASSUMPTIONS (unstated):

  • "caching layer never misses" — unverified under load

BIAS FLAGS:

  • confirmation: only success paths tested

CONFIDENCE:

  • rollback works: Low (never rehearsed)

ACTION: do not ship until Low items are verified or mitigated

Relationship to sibling skills

  • doubt-driven-development — the in-flight adversarial posture; this skill is

the explicit assumption/bias/confidence inventory it can delegate to.

  • analytical-thinking-patterns — supplies the reasoning frameworks (first-

principles, systems) used to challenge assumptions.

  • thought-patterns — route to the metacognitive/creative resources here.
  • postmortem / failure-analysis — use this skill during the analysis to stop

repeating the same blind spots.

Quality bar

A check is useful only if it names specifics. "Consider your biases" is noise. "Confirmation bias: only the happy path was load-tested; the failure path is unverified" is actionable.

Security

  • Security scanPassed, 95 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

7-day trend score
5

Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/mr-wolv/skill_playground_bakr101_2026/assumption-and-bias-check/badge)](https://verified-skill.com/skills/mr-wolv/skill_playground_bakr101_2026/assumption-and-bias-check)

Something wrong with this skill or its page? Tell us.