find-bugs

Claude Code Skills Collection

A growing collection of AI agent skills for software development workflows. Built for technical leads, TPMs, and developers who want Claude Code to help with planning, specification, and engineering tasks.

Contributions welcome! Found a way to improve a skill or have a new one to add? Open a PR.

Available Skills

TPM & Planning

Transform vision documents into traceable, testable specifications. See the TPM Planning Guide for the full methodology.

Skill	Description	Triggers
tpm-spec-trace-ids	Annotate vision docs with Feature IDs (F-nnn)	"annotate my vision doc," "add feature IDs," "create coverage index"
tpm-roadmap-slice	Extract features into Phase PRDs with requirements	"create phase PRD," "plan next quarter," "extract phase from vision"
tpm-spec-verify	Add QA requirements and acceptance criteria	"add QA plan," "add acceptance criteria," "enrich with test criteria"

Documentation

• TPM Planning Guide — Full methodology for the planning pipeline

Planning Pipeline:

flowchart TD
    A[Vision PRD] --> B[tpm-spec-trace-ids]
    B --> C[Annotated PRD + Coverage Index]
    C --> D[tpm-roadmap-slice]
    D --> E[Phase I PRD with Requirements]
    E --> F[tpm-spec-verify]
    F --> G[Phase I PRD with Acceptance criteria]
    G -->|Iterate| D

    style B fill:#4a9eff,color:#fff
    style D fill:#4a9eff,color:#fff
    style F fill:#4a9eff,color:#fff

Product & Strategy

Tools for auditing and simplifying ideas, products, and systems.

Skill	Description	Use When
simplify	Radical Simplicity & Candor Audit	Asking for advice on radically simplifying an idea, product, architecture, or system

The simplify skill produces structured audit reports with phased YES/NO/DEFER decision lists. It exposes complexity and prepares batched decisions—it does not execute changes.

GTM & Strategy

Go from a messy product idea to a structured go-to-market plan, then develop brand creative direction — all driven by structured workflows with phase gates and opinionated defaults.

Skill	Description	Use When
idea-to-icp	Take a messy business idea and structure it into GTM primitives: Product, ICP segments, value prop, beachhead market, and channel strategy	"decompose my idea", "help me find my ICP", "who should I sell to", "idea to ICP", "structure my go-to-market"
creative-direction	Develop 3-5 distinct brand creative treatments from GTM data — tone, visual mood, messaging, and taglines	"creative direction", "brand treatments", "brand tone", "creative brief", "brand identity direction"

GTM Pipeline:

flowchart TD
    A[Messy Product Idea] --> B[idea-to-icp]
    B --> C[GTM Decomposition: Product + ICP + Value Prop + Channels]
    C --> D[creative-direction]
    D --> E[Brand Creative Direction: Tone + Visual Mood + Messaging]

    style B fill:#4a9eff,color:#fff
    style D fill:#4a9eff,color:#fff

Code Quality & Bug Detection

Adversarial multi-agent systems for finding bugs with high confidence.

Skill	Description	Use When
find-bugs	Three-agent adversarial bug review (search → adversary → judge)	"find bugs", "review code for bugs", "adversarial code review"

Find Bugs Pipeline:

flowchart TD
    A[Target: src/] --> B[Search]
    B -->|bugs.json| C[Adversary]
    C -->|contested.json| D[Judge]
    D --> E[verdict.json]

    B -.->|"+1/+5/+10 scoring"| B
    C -.->|"+score/-2x penalty"| C
    D -.->|"ground truth bluff"| D

    style B fill:#e74c3c,color:#fff
    style C fill:#f39c12,color:#fff
    style D fill:#27ae60,color:#fff

The pipeline exploits asymmetric incentives to produce three distinct epistemic postures:

• Search: Overclaiming (rewards thoroughness)
• Adversary: Aggressive skepticism (rewards precise disproval)
• Judge: Calibrated judgment (rewards accuracy)

Their intersection yields high-fidelity results with reduced false positives.

Usage:

/find-bugs src/

Output:

.find-bugs/
├── bugs.json          # All potential bugs found
├── contested.json     # Adversary's challenges
└── verdict.json       # Final calibrated verdicts

Self-Improvement & Analysis

Tools for root cause analysis, retrospectives, and optimizing autonomous session performance.