first-principles
Skill0 starsChanged 39 days agoMITView on GitHub
Guides first-principles analysis through decomposition, assumption auditing, recombination, and experiments. Use when the user requests first-principles thinking, D.A.R.E., or challenges inherited assumptions behind a difficult problem.
30 other projects use a version of this.
Adopted by
Most recently taken up by
- m1nga/first-principlestheir own version, first seen Nov 8, 2026
- shetengteng/skillix-hubtheir own version, first seen Nov 8, 2026
- ZhouYinLong-lab/Dog-Skillstheir own version, first seen Nov 8, 2026
- MasihMoafi/skillstheir own version, first seen Nov 3, 2026
- eliasstravik/skillstheir own version, first seen Nov 1, 2026
- agentcrew-academy/harness-starter-kittheir own version, first seen Nov 1, 2026
Used with
Projects with it also use second-order-thinking, inversion and 2 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
itzcullSkillsecond-order-thinking
Use second-order thinking to examine consequences beyond immediate effects. Use when evaluating decisions across time horizons, asking what happens next, or avoiding short-sighted optimization.
Also in 3 projects that use this
- itzcullSkill
inversion
Use inversion to solve problems by reasoning backward from failure, bad outcomes, or the opposite of success. Use when identifying risks, running premortems, or escaping overly idealized thinking.
Also in 3 projects that use this
Ingramradical235Skillpre-mortem
Pre-mortem analysis, scenario planning, future state narratives, and contingency frameworks. Use before finalizing any Strategy Kernel, when planning major initiatives, or when preparing Plan B triggers.
Also in 3 projects that use this
MicrosoftSkillhandoff
Compact the current conversation into a handoff document for another agent to pick up.
Also in 3 projects that use this
Other versions30 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 30
- agentcrew-academy/harness-starter-kit★ 41same name
- reshadat/first-principles-destructor★ 24same name
- kirillgreen/skills★ 23same name
- eliasstravik/skills★ 22same name
- ironyjk/strategy-frameworks★ 14same name
- deciqAI/knowledge-skills★ 13same name
- jackjin1997/ClawForge★ 12same name
- ccomkhj/skills★ 10same name
- docxology/codomyrmex★ 10same name
- MasihMoafi/skills★ 8same name
20 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository18 other files it gives its agents.
- agent-instructions/AGENTS.mdAGENTS.md
- AGENTS.mdAGENTS.md
- codebase-designSkill
- code-reviewSkill
- domain-modelingSkill
- gh-axiSkill
- git-grouped-commitSkill
- grill-with-docsSkill
- improve-codebase-architectureSkill
- learnSkill
- prototypeSkill
- retroSkill
- show-meSkill
- tddSkill
- teachSkill
- wayfinderSkill
- xiaohongshu-postSkill
- youtube-subtitlesSkill
The file
We split this skill into the rules it gives an agent
2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 21 edited versions we read keep these.
2
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 14
Default to one stage per response, starting with Decompose.
- Distinctive: line 20
Read each reference only when its stage begins.
“Common” is measured: kept by at least 6 in 10 of the 21 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
First Principles
Apply Sandeep Swadia's D.A.R.E. framework. Respond in the user's language.
Scope and pacing
Extract the problem, desired outcome, success criteria, and constraints from context. Ask only for gaps that materially affect the current stage. Obtain the user's choice before replacing their problem with a deeper one.
Default to one stage per response, starting with Decompose. Deliver its output, invite corrections or continuation, and wait. If the user requests a complete analysis, run all stages in order with separate outputs.
Honor requests for a specific stage, reusing prior outputs or user-supplied equivalents. Ask for missing prerequisites rather than inventing them. Preserve explicit user constraints.
Routing
Read each reference only when its stage begins.
| Stage | Input | Reference | Output |
| D: Decompose | Chosen problem | decompose.md | Component map |
| A: Audit | Component map | audit.md | Ranked assumption register |
| R: Recombine | Audited facts, constraints, and unknowns | recombine.md | Candidate solutions |
| E: Experiment | Candidates and their assumptions | experiment.md | Tests and decision criteria |
Evidence and continuity
Distinguish user claims, verified facts, inferences, and unknowns. Verify against inspected evidence and state its scope. Use conversation and authorized local materials first; source retrieval is unnecessary. Research when requested or required for verification.
Carry relevant findings and unresolved questions into the next stage. Revise affected conclusions when new evidence arrives. Save analysis to files only when requested.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.