S4h Probability Confidence Calibration

Tests whether stated confidence levels match available evidence — catching overconfidence and underconfidence. Use when asked to 'calibrate my confidence', 'am I overconfident', 'confidence check', 'how sure should I be', or 'is this as certain as it seems'.

242 stars 25 forksTesting & QA

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add human-avatar/skills-for-humanity --skill s4h-probability-confidence-calibration
Manual install
git clone --depth 1 https://github.com/human-avatar/skills-for-humanity.git /tmp/skills-for-humanity
mkdir -p ~/.claude/skills
cp -r /tmp/skills-for-humanity/skills/s4h-probability-confidence-calibration ~/.claude/skills/s4h-probability-confidence-calibration

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Probability Confidence Calibration

Overconfidence is the most documented and costly bias in judgment. People who say they are 90% confident are right far less than 90% of the time. But underconfidence is also costly — excessive hedging prevents commitment and action when evidence is actually sufficient. Calibration is not about being less confident; it is about having confidence levels that match the available evidence.

---

## Your Process

**Step 1: State the Claim and Current Confidence**
Name the specific claim — not a vague domain but a specific, falsifiable statement — and state the current confidence level as a percentage.

**Framing check:** Confirm the specific claim and confidence level before continuing. State what you've identified — the actual claim being evaluated and its stated confidence percentage — in one sentence, then use `AskUserQuestion`:
- **Question:** "I'm reading this as: [your one-sentence framing of the specific claim and confidence level, e.g. 'You believe X with 85% confidence and want to know if that's calibrated to the evidence']. Is that right?"
- **Header:** "Framing"
- **Options:**
  - **Yes — proceed** — framing is correct
  - **Adjust** — one element is off; user will correct it before you continue
  - **Reframe** — different situation than read; incorporate the correction before proceeding

**Step 2: Audit Supporting Evidence**
List the evidence supporting the claim. For each piece: classify its strength:
Read the full skill on GitHub

Details

Skill name
s4h-probability-confidence-calibration
Path
skills/s4h-probability-confidence-calibration/SKILL.md
License
MIT
Repo updated
15 July 2026

FAQ

What does the S4h Probability Confidence Calibration skill do?

Tests whether stated confidence levels match available evidence — catching overconfidence and underconfidence. Use when asked to 'calibrate my confidence', 'am I overconfident', 'confidence check', 'how sure should I be', or 'is this as certain as it seems'.

How do I install the S4h Probability Confidence Calibration skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add human-avatar/skills-for-humanity --skill s4h-probability-confidence-calibration. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is S4h Probability Confidence Calibration popular?

It lives in human-avatar/skills-for-humanity, which has 242 GitHub stars and 25 forks, and is included in 1 curated skill list.

Related skills

S4h

242

human-avatar/skills-for-humanity

Master orchestration skill. Takes any situation in plain English, identifies the underlying goal, designs a multi-skill reasoning workflow, and executes it sequentially — feeding each skill's output into the next. Use when you say 'help me think through this', 'I need to figure out what to do', 'where do I start', or any time you want structured thinking applied end-to-end rather than routed to a single tool.

Testing & QAIn 1 list25

S4h Aesthetic

242

human-avatar/skills-for-humanity

Entry point for the aesthetic toolkit. Routes to the right aesthetic skill based on your situation. Use when you say 'aesthetic', 'check the design', 'does this feel right', 'is this elegant', 'is this too complex', 'what pattern is this', 'find the simpler version', or want an aesthetic lens applied without knowing which specific tool fits.

OtherIn 1 list25

S4h Aesthetic Coherence Check

242

human-avatar/skills-for-humanity

Tests whether the parts of something form a unified whole — finding the jarring inconsistencies that accumulate when different contributors work without a shared vision. TRIGGERS: 'coherence check', 'does this feel unified', 'something feels off', 'inconsistent', 'check the whole', 'does this hang together'.

Testing & QAIn 1 list25

Idea Validator

116

aakashg/pm-claude-skills

Use when the user asks to validate a product idea, stress-test an idea, evaluate whether an idea is good, or decide whether to build something. Do NOT use for prioritizing an existing backlog or reviewing a shipped feature — those need RICE scoring or a design review instead.

Testing & QA35

S4h Logic Fixer

242

human-avatar/skills-for-humanity

Take broken reasoning — a flawed argument, contradictory spec, unsound plan, or invalid inference — diagnose exactly what's wrong, and produce a corrected version. Use when you have reasoning that doesn't hold and you want it fixed, not just critiqued. TRIGGERS: 'fix this reasoning', 'repair this argument', 'this logic is broken, fix it', 'make this argument sound', 'my reasoning is circular, help', any situation where broken reasoning needs to be made valid rather than just flagged. Pairs with logic-argument-validation (which diagnoses) and logic-council (which pressure-tests) — this skill fi

Testing & QAIn 1 list25

Test

155

serpro69/claude-toolbox

Guidelines describing how to test the code. Use whenever writing new or updating existing code, for example after implementing a new feature or fixing a bug.

Testing & QAIn 1 list30

Browse the most popular Claude skills, all testing & qa skills, or write your own with the skills generator.