Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Get Started Free →

First Principles Thinking · asgard-ai-platform | DecimalAI

productivityby asgard-ai-platform

First Principles Thinking

asgard-ai-platform/meta-first-principles

Source asgard-ai-platform/skills ↗License MIT

Apply first principles thinking to break problems down to fundamental truths and reason up from there.

SkillScore73Maintained

Automatic

Research pack

Last verified 8/28/2026

What it changes

Passed 16 of 22 test cases with the skill, and 9 of 22 without it.

Without skill41%

With skill73%

Checks it passed that the model alone missed

Categorizes raw metal spot prices as physical cost bounds.
Categorizes cloud provider hourly rental margins as convention.
Classifies imported equipment markups as operational conventions.

and 9 more in the full report

8 fixed8 passed either way5 still failing1 broke

Pass-rate lift: +32 pp
Tokens: +17%
Agent turns: 0%
Response time: -1%

Model gemini-3.6-flashMeasured 8/28/2026v116 of 22 cases passed with skill

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/asgard-ai-platform-meta-first-principles/SKILL.md https://app.decimal.ai/s/asgard-ai-platform-meta-first-principles/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add asgard-ai-platform-meta-first-principles, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/asgard-ai-platform-meta-first-principles/ and pins it in .decimal/skills.lock

decimalai skills add asgard-ai-platform-meta-first-principles

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/asgard-ai-platform-meta-first-principles/SKILL.md https://app.decimal.ai/s/asgard-ai-platform-meta-first-principles/SKILL.md

Raw file: /s/asgard-ai-platform-meta-first-principles/SKILL.md ↗ · machine-readable summary at /s/asgard-ai-platform-meta-first-principles.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 8 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 8

Prompt

Our engineering leadership believes our cloud infrastructure bill will always scale linearly with traffic and that $50,000 per month is the baseline cost for running our streaming service. I want to challenge this thinking. Could you perform a fundamental analysis on this problem? Please state the baseline assumption, provide a breakdown table comparing true physical limits against operational choices for each component, summarize the remaining fundamental facts, reason upward from those facts, and propose an alternative solution.

What was checked, without and with the skill
Checked	Without skill	With skill
Includes a 3-column decomposition table with headers Component, Cost/Fact, and Physics or Convention.	Missed	Passed
Classifies commercial cloud vendor margin or pricing models as convention rather than physical constraints.	Passed	Passed

case-01 · gemini-3.6-flash · 8/28/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md79 linessingle file

First Principles Thinking

Framework

IRON LAW: Assumptions Are Not Facts

Most "constraints" are assumed, not physical. "We can't do X" usually means
"We haven't seen anyone do X" or "The current method doesn't allow X."
First principles thinking distinguishes between:
- Physical laws (actual constraints: gravity, thermodynamics)
- Conventions (assumed constraints: "this is how it's done")

The Method

1. Identify the assumption: What do "everyone knows" or "everyone does"?

2. Break it down to fundamentals: What are the basic, irreducible facts?

Techniques: "Five Whys" (ask why 5 times), cost decomposition, physics-level analysis

3. Reason up from fundamentals: Given only the base facts, what's the best solution?

Example: Elon Musk on Battery Costs (2010s)

Convention: "Batteries cost $600/kWh. Electric cars will always be too expensive."
First principles: What are batteries made of? Cobalt, nickel, lithium, carbon, metals, polymers. What do these raw materials cost? ~$80/kWh at commodity prices.
Reasoning up: If we buy materials and build batteries ourselves, we can potentially reduce costs to near $80/kWh. The $520 gap is manufacturing inefficiency and supply chain markup, not physics.

Five Whys for Assumption Drilling

"Why is our product priced at $100?" — Because our COGS is $60 and we need 40% margin.
"Why is COGS $60?" — Because we use supplier X for component Y.
"Why do we use supplier X?" — Because we've always used them.
"Why haven't we looked at alternatives?" — Because the procurement team hasn't been asked to.
"Why not?" — There's no real reason. It's just convention.

→ Fundamental constraint found: the COGS includes an unexamined supplier relationship, not a physical constraint.

Cost Decomposition Template

Track record

Benchmark

16 / 22

test cases passed, vs 9 / 22 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

asgard-ai-platform / skills

meta-first-principles/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v1

Other skills for the same job

Published skills whose descriptions closely match this one, with their headline benchmark lift.

mohitagw15856/from-first-principlesStrip a problem down to what's actually true — the physics, economics, and human basics — and rebuild the answer from there, ignoring 'how it's normally done'. Use when asked to think from first principles, why is this done this way, challenge the assumptions here, or rebuild this from scratch. Produces the problem reduced to its fundamental truths, the inherited assumptions and conventions named and questioned, and a solution reasoned up from the basics — which often looks nothing like the defaClose match-20 pp pass-rate lift

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

First Principles Thinking

Framework

The Method

Example: Elon Musk on Battery Costs (2010s)

Five Whys for Assumption Drilling

Cost Decomposition Template

Track record

Benchmark

Adoption

SkillSafety

Source

Other skills for the same job

Related skills