agentleFS
davidmatousekdavidmatousek/tachi/.claude/skills/aod-lens/SKILL.md

aod-lens

Skill95 starsChanged 37 days agoApache-2.0View on GitHub

Routes to 14 structured thinking methodologies (lenses) for systematic analysis. Use this skill when you need to think through problems, apply thinking lenses, reason through decisions, or perform systematic analysis. Auto-selects appropriate lens based on context - 5 Whys for failures, Pre-Mortem for risks, First Principles for assumptions, Systems Thinking for architecture, Four Causes for understanding, Cargo Cult Detection for validation, Golden Mean for calibration.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Load: Read full methodology from docs/core_principles/[FILE]

    line 32
  2. Distinctive:

    Apply: Follow the step-by-step process and use template from that file

    line 33

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Thinking Lens Skill

Router that selects and applies thinking methodologies from docs/core_principles/.

Keyword → Lens Routing

KeywordsLensFile
"failed", "broke", "why did", "root cause"5 Whys01-FIVE_WHYS_METHODOLOGY.md
"assumptions", "fundamentally", "from scratch"First Principles02-FIRST_PRINCIPLES.md
"risks", "could go wrong", "before we start"Pre-Mortem03-PRE_MORTEM.md
"guarantee failure", "avoid", "anti-patterns"Inversion04-INVERSION.md
"prioritize", "most value", "80/20"Pareto Analysis05-PARETO_ANALYSIS.md
"architecture", "interact", "components"Systems Thinking06-SYSTEMS_THINKING.md
"consequences", "downstream", "side effects"Second-Order Effects07-SECOND_ORDER_EFFECTS.md
"blocked", "bottleneck", "dependencies"Constraint Analysis08-CONSTRAINT_ANALYSIS.md
"challenge", "critique", "wrong with this"Devil's Advocate09-DEVILS_ADVOCATE.md
"compare", "choose between", "options"Comparative Analysis10-COMPARATIVE_ANALYSIS.md
"trade-off", "giving up", "sacrifice"Opportunity Cost11-OPPORTUNITY_COST.md
"explain", "purpose", "why does this exist", "complete picture"Four Causes12-FOUR_CAUSES.md
"going through motions", "process theater", "cargo cult", "actually working", "vibe coding"Cargo Cult Detection13-CARGO_CULT_DETECTION.md
"how much", "balance", "calibrate", "sweet spot", "too much", "too little", "spectrum"Golden Mean14-GOLDEN_MEAN.md

Workflow

  1. Route: Match user keywords to lens using table above
  2. Load: Read full methodology from docs/core_principles/[FILE]
  3. Apply: Follow the step-by-step process and use template from that file

If ambiguous, ask:

"Would you like to focus on risks (Pre-Mortem), root cause (5 Whys), or trade-offs (Opportunity Cost)?"

Quick Reference

Problem TypeLens
Something failed5 Whys
Planning something riskyPre-Mortem
Choosing between optionsComparative Analysis
Understanding a systemSystems Thinking
Prioritizing workPareto Analysis
Understanding why something existsFour Causes
Checking if a practice is actually workingCargo Cult Detection
Finding the right balance/amountGolden Mean
Not surePre-Mortem (safest default)

Hand-offs

SituationRoute To
Need to fix code after analysisdebugger skill
Document root cause in KBretrospective skill
Security issue foundsecurity-pattern-scanner skill

Lens Index

See docs/core_principles/00-THINKING_LENSES_INDEX.md for complete guide.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.