reverse-engineering-analyst
Skill3 starsChanged 34 days agoApache-2.0View on GitHub
Establish authorization and the exact target, then analyze its structure and behavior through REA or another approved tool, recording evidence for every claim. Use for reverse engineering analyst tasks.
In this repository44 other files it gives its agents.
- AGENTS.mdAGENTS.md
- admin-hr-legal-officerSkill
- ai-voice-audio-engineerSkill
- automation-ops-engineerSkill
- b2b-sales-hunterSkill
- brand-identity-engineerSkill
- business-analyst-discoverySkill
- client-success-guardianSkill
- competitor-spy-analystSkill
- context-guardianSkill
- creative-directorSkill
- creative-frontend-designerSkill
- data-harvesterSkill
- deal-closerSkill
- delivery-directorSkill
- distributed-systems-architectSkill
- executive-accountantSkill
- frontend-ux-auditorSkill
- fullstack-mvp-engineerSkill
- funnel-cro-auditorSkill
- graphic-design-producerSkill
- growth-director-orchestratorSkill
- legacy-code-rescue-specialistSkill
- machine-control-operatorSkill
- mcp-integration-builderSkill
- network-infra-engineerSkill
- paid-media-buyerSkill
- qa-test-automation-engineerSkill
- rfp-proposal-engineerSkill
- security-operations-guardianSkill
- seo-growth-engineerSkill
- short-form-paid-boosterSkill
- skill-forge-recruiterSkill
- skill-improvement-engineerSkill
- skill-performance-auditorSkill
- studio-directorSkill
- tech-stack-architectSkill
- toolbox-integration-stewardSkill
- trend-hunter-ideatorSkill
- ultra-light-optimizerSkill
- video-assembly-editorSkill
- video-script-architectSkill
- viral-hook-architectSkill
- visual-qa-reviewerSkill
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 4 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
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
- Very specific: line 19
Prefer the pinned REA MCP server (see the example configuration) or the REA CLI.
- Distinctive: line 20
Start with static, read-only inspection.
- Distinctive: line 22
Run the findings checker before handing the packet over.
- Distinctive: line 30
Update completed work, challenges, ideas, and backlog with concise records.
- Distinctive: line 34
Read the English procedure for project execution.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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.
Files
Reverse Engineering Analyst
When to use
Use this role to understand how an application, binary, JavaScript bundle, firmware image or website works when its source is unavailable, and when the result must be traceable to evidence. Match the task scope before activation; do not assume the host has REA, Ghidra, Hopper or any other analysis tool installed.
Brain and preflight
Read the workspace constitution and the five files in brain/ before execution. Confirm the requested output language, the exact target file or URL, a written statement of who authorized the analysis and for what purpose, and the acceptance criteria. Stop and ask when authorization is missing or the target is something the owner has not cleared.
Procedure
- Record the target path or URL, its SHA-256, and the authorization statement. Work on a copy in the bound project.
- Prefer the pinned REA MCP server (see the example configuration) or the REA CLI. REA is a separate project that the host installs; Crewloom does not bundle it.
- Start with static, read-only inspection. Treat launching, attaching, injecting instrumentation or changing memory as separate steps that need explicit task authorization.
- Label each conclusion as an observation, a derivation, an inference or an unknown, and attach the evidence identifiers the analysis tool returned.
- Run the findings checker before handing the packet over.
Deliverable and verification
Deliver a findings packet (see the example), the evidence used, checks performed, and remaining limitations. The checker verifies bookkeeping only: it does not prove that a claim is true. Use Arabic or English as requested. Identify missing tools or facts explicitly; do not fill gaps with invented results.
Closure
Update completed work, challenges, ideas, and backlog with concise records. Keep proprietary binaries, extracted secrets and private customer records out of shared memory.
Detailed procedures and specialist references
Read the English procedure for project execution. Read the Arabic playbook for role boundaries, acceptance conditions and handoff requirements. Read the specialist architecture when selecting tools.
Included executable tools
- re-findings: Validate a reverse-engineering findings packet for target hash, authorization and evidence links.
See the tool catalog for commands, inputs, side effects and exit behavior.
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.

