debugger-driven-analysis
Drive runtime analysis with debugger-first workflows for breakpoint planning, register and memory observation, and static-to-dynamic correlation.
Skill by mattmre
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/mattmre-debugger-driven-analysis
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/debugger-driven-analysis
What's inside
- Skill name
debugger-driven-analysis- Description
- Drive runtime analysis with debugger-first workflows for breakpoint planning, register and memory observation, and static-to-dynamic correlation. Use when static analysis is insufficient or runtime behavior must be confirmed.
- License
- MIT
- Metadata
- source: evokore
- Instructions
- 48 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Debugger-Driven Analysis Use runtime evidence to resolve questions that static analysis cannot answer cleanly: unpacking, argument decoding, branch conditions, environment checks, IPC, crypto state, and anti-analysis behavior. ## Workflow 1. Start from a concrete question, not "debug everything." 2. Choose the debugger mode: - x64dbg for Windows user-mode binaries - WinDbg for deeper Windows/system scenarios - pwndbg-like workflows for low-level register/stack discipline 3. Set a minimal breakpoint plan: - process entry / unpacking point - suspicious imported APIs - target functions identified in static recon - memory write / allocation pivots when needed 4. Capture: - arguments and calling convention state - register snapshots before/after call - buffers, decoded strings, and memory changes - control-flow decisions at critical branches 5. Feed confirmed runtime facts back into static naming, signatures, and comments. ## Tool Families to Prefer - `binary_analysis_*x64dbg*` - `binary_analysis_*windbg*` - `binary_analysis_*session*` - `binary_analysis_*report*` If the exact prefixed names are unclear, use `discover_tools` with `x64dbg debugger winDbg reverse engineering`. ## Debugger Heuristics 1. Break on semantic pivots, not every instruction. 2. Snapshot before patching or forcing branches. 3. Record the minimum evidence needed to answer the current hypothesis. 4. Correlate every important dynamic observation to a static function or address. ## Deliverable Format - Question being tested - Breakpoints and why they were chosen - Runtime observations - Static addresses/functions updated from those observations - Recommended next action
From mattmre/EVOKORE-MCP-PUBLIC, MIT.
More from mattmre/EVOKORE-MCP-PUBLIC
- 0.514score
zoom-out
mattmre
Use when an agent needs to go up a layer of abstraction — map calling modules, identify the seam at which a change should land, and check whether the bug or…
SkillCFreshness: C★ 3Claude Code +9 - 0.514score
ghidra-core-recon
mattmre
Perform first-pass binary reconnaissance using Ghidra-oriented workflows for functions, strings, imports, exports, and symbols.
SkillCFreshness: C★ 3Claude Code +9 - 0.514score
ubiquitous-language
mattmre
Use when crystallizing a domain glossary for a single bounded context — extract canonical terms from replay JSONL, evidence JSONL, and src/ identifiers, then…
SkillCFreshness: C★ 3Claude Code +9 - 0.511score
tailored-resume-generator
mattmre
Analyzes job descriptions and generates tailored resumes that highlight relevant experience, skills, and achievements to maximize interview chances
SkillCFreshness: C★ 3Claude Code +9 - 0.510score
improve-codebase-architecture
mattmre
Use when surfacing architectural friction inside a single EVOKORE bounded context and proposing deepening refactors (shallow modules, leaky seams, low…
SkillCFreshness: C★ 3Claude Code +9 - 0.489score
brand-guidelines
mattmre
Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel.
SkillCFreshness: C★ 3Claude Code +9 - 0.486score
theme-factory
mattmre
Toolkit for styling artifacts with a theme.
SkillCFreshness: C★ 3Claude Code +9
Signals
- Stars
- 3
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- May 21, 2026 (5 months ago)
- Last release
- May 22, 2026 (5 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/mattmre/EVOKORE-MCP-PUBLIC
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from mattmre
- 0.514score
zoom-out
mattmre
Use when an agent needs to go up a layer of abstraction — map calling modules, identify the seam at which a change should land, and check whether the bug or…
SkillCFreshness: C★ 3Claude Code +9 - 0.514score
ghidra-core-recon
mattmre
Perform first-pass binary reconnaissance using Ghidra-oriented workflows for functions, strings, imports, exports, and symbols.
SkillCFreshness: C★ 3Claude Code +9 - 0.514score
ubiquitous-language
mattmre
Use when crystallizing a domain glossary for a single bounded context — extract canonical terms from replay JSONL, evidence JSONL, and src/ identifiers, then…
SkillCFreshness: C★ 3Claude Code +9 - 0.511score
tailored-resume-generator
mattmre
Analyzes job descriptions and generates tailored resumes that highlight relevant experience, skills, and achievements to maximize interview chances
SkillCFreshness: C★ 3Claude Code +9 - 0.510score
improve-codebase-architecture
mattmre
Use when surfacing architectural friction inside a single EVOKORE bounded context and proposing deepening refactors (shallow modules, leaky seams, low…
SkillCFreshness: C★ 3Claude Code +9 - 0.489score
brand-guidelines
mattmre
Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel.
SkillCFreshness: C★ 3Claude Code +9
Cite this page
debugger-driven-analysis skill. Agent Mart. https://agentmart.dev/skills/mattmre-debugger-driven-analysis (last updated 2026-10-24)