AI Summary1. Run 2-3 tool calls 2. Write findings to REVERSE.md immediately — do NOT batch all investigation before writing 3. Add new addresses to labels.csv (addr,name,comment)
Install
Copy this and paste it into Claude Code, Cursor, or any AI assistant:
I want to install the "re" skill in my project. Please run this command in my terminal: # Install skill into your project mkdir -p .claude/skills/re-skill && curl --retry 3 --retry-delay 2 --retry-all-errors -o .claude/skills/re-skill/SKILL.md "https://raw.githubusercontent.com/vgrichina/re-skill/main/SKILL.md" Then restart Claude Code (or reload the window in Cursor) so the skill is picked up.
Description
Reverse engineering session: disassemble, annotate, extract assets, build emulator, port to web. Use when working on a binary RE project with REVERSE.md and tools/ directory.
Live context
• Open tasks: !grep -m 10 '\[ \]' REVERSE.md 2>/dev/null || true • Dead ends: !head -50 dead_ends.md 2>/dev/null || true • Sessions: !ls re_loop_sessions/ 2>/dev/null | tail -5 || true
Dispatch
$ARGUMENTS given -> bootstrap new project • Read phases.md, reverse_template.md, dead_ends_template.md, re_loop_template.sh • Scaffold: REVERSE.md, labels.csv, dead_ends.md, tools/ dir, re_loop.sh (fill config block) • Identify binary header -> fill Ph1 in REVERSE.md • Add first tasks to ## Next Tasks -> ### RE Investigation no $ARGUMENTS -> continue from REVERSE.md • Read CLAUDE.md for platform conventions, tool prefix, binary path • Pick top unchecked task from ## Next Tasks • Skim re_loop_sessions/*.txt (last 3) to avoid repeating work • Read dead_ends.md to avoid known dead-end approaches
Task categories
RE investigation (tools/dis.py, xref.py, search_bytes.py, decode_tables.py) • Run 2-3 tool calls • Write findings to REVERSE.md immediately — do NOT batch all investigation before writing • Add new addresses to labels.csv (addr,name,comment) • Repeat: more tool calls -> write, until task fully understood • Mark [x], add new [ ] discoveries Web port fix (web/ files) • Read the relevant web/ file first • Apply fix — values are already documented in REVERSE.md • Update REVERSE.md to note what changed • If new asset type decoded -> add section to web/catalog.html Documentation (docs/ directory) • docs/architecture_exe.md — binary layout, segment/bank boundaries, call graph with entry points + file offsets, module map, per-turn execution flow, data flow, shared data regions • docs/architecture_web.md — JS module graph with exports + dependencies, EXE->web mapping table, game loop flow, state machine with transitions Both files must exist before the project is considered complete.
Knowledge base
labels.csv accumulates across sessions. All disasm tools load it automatically. • Flat (DOS/unpacked): offset,name,comment — offset with 0x prefix e.g. 0x25DE9,main,entry point • Banked ROM (NES/GB): bank,addr,name,comment — addr hex no prefix e.g. 0,C070,Reset, • DS-relative (DOS): DS:offset_hex,name,comment e.g. DS:0xCEAC,dt_physics,timestep The comment column is optional but encouraged for non-obvious addresses.
Discussion
Health Signals
My Fox Den
Community Rating
Sign in to rate this booster