root-cause
Skill14 starsChanged 6 months agoMITView on GitHub
First-principles analysis — force the AI to reason from fundamental facts instead of pattern-matching from training data. Use for debugging (find the real root cause, not the surface symptom), architecture decisions (is this the right approach, or just a familiar one?), and solution design (should we really solve it this way?). Use when user says: "root-cause", "根因分析", "第一性原理", "first principles", "从本质出发", "为什么会这样", "治本不治标", "这个问题的本质是什么", "不要套方案", "重新推导", "think from scratch", "why does this really happen", or when the user is unsatisfied with a surface-level fix.
28 other projects use a version of this.
Adopted by
Most recently taken up by
- niksavis/basiclytheir own version, first seen Nov 15, 2026
- crbnos/carbontheir own version, first seen Nov 15, 2026
- niksavis/handilytheir own version, first seen Nov 8, 2026
- yuri-xyz/skillstheir own version, first seen Nov 8, 2026
- jocarrd/crux-agentstheir own version, first seen Nov 8, 2026
- lalulali/vespyrtheir own version, first seen Nov 6, 2026
Used with
Projects with it also use prove-it, grill and 10 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.
Neko-Catpital-LabsSkillprove-it
Shared evidence rule for investigating, diagnosing, debugging, proving, or explaining what happened or why for any problem or situation: do not assert something is fixed, working, passing, merged, or running unless you personally observed it this turn and can show what you saw; do not assert it was caused by X until a repro and controlled isolation prove that cause.
Also in 3 projects that use this
renatorozasSkillgrill
Adversarial code review. Don't let me ship until the changes pass your scrutiny.
Also in 4 projects that use this
sunnyclinches44Skillexplain
Explains code using real-world analogies and ASCII diagrams
Also in 5 projects that use this
jasonmichaelbell78-creatorSkillskill-audit
Interactive behavioral quality audit for individual skills. Evaluates against 12 quality categories (including T25 convergence loop and completion verification) to surface attention management issues and produce actionable decisions. Includes self-audit verification that all decisions were actually implemented. Uses convergence loops in its own discovery phase. Produces a decision record and updated skill files.
Also in 3 projects that use this
Microsoft AzureSkilldesign
Design rules and conventions for the API Center Portal. Use when editing detail pages, card components, badges, layout, navigation, sidebars, or headers. Covers badge styling, metadata placement, page navigation patterns, and layout alignment.
Also in 4 projects that use this
SentrySkillspec
Produce a verified spec — problem, desired outcome, and acceptance criteria — before building. Use when given a GitHub/Linear issue link, when starting from a fuzzy in-conversation idea, or asked to "figure out what to do" / "scope this" / "what should I build" — whenever the *what* isn't yet pinned down. Grills the ambiguities, checks the premise against the code, and produces acceptance criteria you sign off on — then hands to design-first.
Also in 3 projects that use this
Other versions28 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 28
- crbnos/carbon★ 2.8ksame name
- formancehq/ledger★ 1.5ksame name
- jjanczur/tyran★ 79same name
- Vesely/skills★ 28same name
- composio-community/support-skills★ 18same name
- lalulali/vespyr★ 11same name
- quocld/hephaestus-agent-skills★ 8same name
- nadirali1350/vetted★ 5same name
- Xnadir/vetted★ 5same name
- jocarrd/crux-agents★ 4same name
18 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 repository14 other files it gives its agents.
- app-icon-generatorSkill
- break-itSkill
- debug-modeSkill
- dev-launcherSkill
- diagram-proSkill
- image-uploadSkill
- localizeSkill
- mac-app-uninstallSkill
- mac-cleanup-diskSkill
- mac-cleanup-memorySkill
- mac-cleanup-processSkill
- macos-app-scaffoldSkill
- npm-safetySkill
- skill-scanSkill
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 26 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 23
Solution design: Before adopting an existing pattern, verify it's the right one
- Distinctive: line 67
If they agree — great, the conventional approach is validated.
“Common” is measured: kept by at least 6 in 10 of the 26 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
Root Cause — First-Principles Analysis
Force reasoning from fundamental facts. No analogies, no "this looks like X so do Y", no pattern-matching from similar codebases. Start from what is actually true and derive what should be done.
When to Use
- Debugging: The surface fix is obvious, but you suspect a deeper issue
- Architecture: Deciding between approaches — is the familiar pattern actually right for this case?
- Solution design: Before adopting an existing pattern, verify it's the right one
The Process
Step 1: Strip Away Assumptions
List every assumption baked into the current approach or the proposed fix. For each one, ask: is this actually true in our specific context, or are we just carrying it over from convention?
Print each assumption as:
⚠️ Assumption: [what we're taking for granted]
Evidence for: [does evidence support this?]
Evidence against: [anything contradicting it?]
Verdict: ✅ Holds / ❌ Doesn't hold / ❓ UnverifiedStep 2: Identify Fundamental Facts
List only what is provably true — from the code, the data, the logs, the runtime behavior. No "usually", no "typically", no "in most projects".
📌 Fact 1: [concrete observation with file:line or log evidence]
📌 Fact 2: [concrete observation with file:line or log evidence]
...Step 3: Derive the Answer from Facts
From the facts alone, reason forward:
- For bugs: what is the actual causal chain from trigger to symptom?
- For architecture: what does the data flow / responsibility boundary / actual constraint demand?
- For design: what solution follows from the real requirements, not from "how we did it last time"?
Step 4: Compare with the Obvious Answer
Now compare your first-principles derivation with whatever the "obvious" or "conventional" answer was:
🔍 Conventional approach: [what pattern-matching would suggest]
🔍 First-principles answer: [what the facts demand]
🔍 Delta: [where they differ and why it matters]If they agree — great, the conventional approach is validated. If they diverge — the delta is where the real insight lives.
Step 5: Recommend
State the recommendation clearly. If it differs from the obvious approach, explain why the first-principles answer is better with specific evidence, not just "it's more correct".
Hard Rules
- No "usually" / "typically" / "in most cases" — these are analogies in disguise. State what is true HERE.
- No solution before diagnosis — if this is a bug, you must trace the actual causal chain before proposing a fix.
- Challenge your own answer — after deriving the answer, spend 30 seconds trying to break it. If you find a flaw, iterate.
- Cite evidence — every claim must reference a file:line, a log entry, a data point, or a reproducible observation. "I believe" is not evidence.
Examples of First-Principles Thinking
| Surface answer | First-principles question | What you might find |
| "The API is slow, add a cache" | Why is it slow? What's the actual bottleneck? | The N+1 query is the real problem; a cache just hides it |
| "Add a retry for this flaky test" | Why does it flake? What's the timing dependency? | A race condition in setup that retry can't fix |
| "Use the same pattern as module X" | Does this module have the same constraints as X? | X was designed for batch processing; this is real-time — different pattern needed |
| "The config was changed, revert it" | Why was the config changed? What was the original intent? | The config change exposed a deeper routing issue that existed for months |
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.

