AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Root Cause

skill-masterleopold-anty-framework-root-cause · by masterleopold

Structured root cause analysis using WHERE (MECE decomposition) then WHY (causal structure diagrams) pipeline. Includes coin-flip detection, logical-leap detection, and vicious cycle intervention. Use when buffer enters YELLOW/RED, when metrics stall, or when Actions execute but don't produce results.

No reviews yet
0 installs
33 views
0.0% view→install

Install

$ agentstack add skill-masterleopold-anty-framework-root-cause

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-masterleopold-anty-framework-root-cause)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
5mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Root Cause? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Root Cause Analysis (WHERE -> WHY)

When to Apply

  • Buffer enters YELLOW or RED zone
  • Actions executed but metrics not moving (Layer 1 OK, Layer 2 stalling)
  • Significant KPI decline detected
  • Review engine Question 5 triggers (was root-cause analysis correct?)
  • Any time "why isn't this working?" is asked

Core Framework

Stage 1 — WHERE (Locate the Problem)

MECE decomposition of the underperforming Goal into Drivers, identifying which specific Driver(s) are stalling.

Goal buffer: YELLOW (45% consumed, 34% progress)

WHERE analysis (MECE decomposition by Driver):
  Social growth:      45% of target   Low post frequency -> Low engagement
  -> Low follower growth -> Less audience feedback -> No content ideas
  (loop restarts)

Intervention (4-Step Process)

  1. Identify the loop in the causal graph
  2. Evaluate each node for intervention viability:
  • Controllable by us? (exclude external factors)
  • Executable at low cost?
  • High ripple effect when broken?
  1. Project the virtuous cycle that results from intervention
  2. Generate concrete Actions via 3-option choice
Best intervention point: "No content ideas" (controllable, low cost, high ripple)

Projected virtuous cycle:
  Content ideas from research -> Higher post frequency ->
  Better engagement -> Follower growth -> More feedback ->
  More content ideas (positive loop)

Decision Rules

  1. WHERE before WHY — always locate the gap before investigating causes
  2. MECE decomposition — WHERE analysis must be mutually exclusive, collectively exhaustive
  3. Verification status is mandatory — every causal node must be tagged
  4. Hypotheses must be tested — don't build Actions on unverified hypotheses
  5. Action targets on verified nodes — only target verified, controllable causes
  6. Vicious cycles get priority — breaking a negative loop has outsized impact

Anti-Patterns to Detect

| Anti-Pattern | Signal | Response | |---|---|---| | Coin-flip cause | Cause is negation of problem | "This restates the problem. What's the specific mechanism?" | | Logical leap | Gap in causal chain | "Insert 'therefore' between these nodes. There's a missing step." | | Skipping WHERE | Jumping to WHY without locating gap | "First, which specific Driver is stalling? MECE decompose." | | Unverified action targets | Building Actions on hypotheses | "This cause is unverified. Verify before investing resources." | | Ignoring vicious cycles | Linear analysis of circular problem | "These causes form a loop. Breaking the cycle has outsized impact." | | Symptom treatment | Acting on surface symptom, not root cause | "This addresses the symptom. Let's drill one more layer to the mechanism." |


Anticipative Execution Reminder

When applying this framework, produce the FULL output immediately. Do not ask the founder which parts to analyze or which options to consider. Infer from business context, present the complete deliverable, and let the founder react to concrete work — not abstract choices.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.