How do I install the Reverse Engineering Bootstrap skill?

Run npx skillmds@latest add tuana-vn/reverse-engineering-bootstrap in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Reverse Engineering Bootstrap safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Reverse Engineering Bootstrap?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Reverse Engineering Bootstrap free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Reverse Engineering Bootstrap?

tuana-vn (@tuana-vn) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Reverse Engineering Bootstrap by tuana-vn

Name: Reverse Engineering Bootstrap
Author: tuana-vn

Reverse Engineering Bootstrap

Initialize 4.0 repository-backed reverse-engineering memory, workflow state, investigation coverage, baseline identity, and broad candidate reconnaissance without prematurely promoting architecture claims.

tuana-vn 16fc44a 2.4 KB Updated Sep 17, 2026

File contents

Reverse Engineering Bootstrap — 4.0

Goal

Create the persistent workspace and broad investigation map before deep tracing.

Create / Ensure

Under docs/reverse-engineering/:

00_current_understanding.md
00_evidence_ledger.md
00_master_decision_matrix.md
00_hypotheses.md
00_open_questions.md
workflow_state.yaml
00_investigation_coverage.md
CURRENT_STATE_TDD.md  # may remain a clearly marked scaffold until synthesis
diagrams/
models/
reviews/

Baseline Identity

Record repository, branch, HEAD commit, and relevant build/module identity when available.

Broad Reconnaissance

Identify candidate locations for:

inbound interfaces
startup/bootstrap
service/business logic
integrations/adapters/gateways
selectors/factories/providers/registries/DI
configuration sources/loaders/defaults
persistence/DAO/ORM/schema/migrations
external boundaries
error/retry/fallback
lifecycle/concurrency
security/auth
observability/audit
tests
architecture docs

Do not infer active behavior from names alone.

Investigation Coverage

Initialize a matrix:

Domain	Applicable?	Candidate Source Areas	Depth	High-Impact Gap?	Notes

Depth values:

NOT_APPLICABLE
DISCOVERED
TRACED
VERIFIED
GAP_HIGH
GAP_MEDIUM
GAP_LOW
EXTERNALLY_BLOCKED

Open Question Schema

Use:

Q-ID	Question	Impact	Closure State	Search Performed	Evidence Needed	External Dependency	Next Action

Impact:

CRITICAL
HIGH
MEDIUM
LOW

Closure state:

SOURCE_SEARCH_PENDING
SOURCE_SEARCH_IN_PROGRESS
SOURCE_EXHAUSTED
EXTERNALLY_BLOCKED
RESOLVED_VERIFIED
RESOLVED_REJECTED
NOT_APPLICABLE

Candidate Findings

write candidates to 00_hypotheses.md
unresolved questions to 00_open_questions.md
candidate evidence rows to 00_evidence_ledger.md
keep canonical baseline empty/minimal until promotion

Stop Condition

Stop after workspace, broad topology, coverage map, candidate claims, and prioritized investigation questions exist.

Bootstrap is reconnaissance, not full-system understanding.

---name: reverse-engineering-bootstrapdescription: Initialize 4.0 repository-backed reverse-engineering memory, workflow state, investigation coverage, baseline identity, and broad candidate reconnaissance without prematurely promoting architecture claims.---# Reverse Engineering Bootstrap — 4.0## GoalCreate the persistent workspace and broad investigation map before deep tracing.## Create / EnsureUnder `docs/reverse-engineering/`:```text00_current_understanding.md00_evidence_ledger.md00_master_decision_matrix.md00_hypotheses.md00_open_questions.mdworkflow_state.yaml00_investigation_coverage.mdCURRENT_STATE_TDD.md # may remain a clearly marked scaffold until synthesisdiagrams/models/reviews/```## Baseline IdentityRecord repository, branch, HEAD commit, and relevant build/module identity when available.## Broad ReconnaissanceIdentify candidate locations for:- inbound interfaces- startup/bootstrap- service/business logic- integrations/adapters/gateways- selectors/factories/providers/registries/DI- configuration sources/loaders/defaults- persistence/DAO/ORM/schema/migrations- external boundaries- error/retry/fallback- lifecycle/concurrency- security/auth- observability/audit- tests- architecture docsDo not infer active behavior from names alone.## Investigation CoverageInitialize a matrix:| Domain | Applicable? | Candidate Source Areas | Depth | High-Impact Gap? | Notes ||---|---|---|---|---|---|Depth values:```textNOT_APPLICABLEDISCOVEREDTRACEDVERIFIEDGAP_HIGHGAP_MEDIUMGAP_LOWEXTERNALLY_BLOCKED```## Open Question SchemaUse:| Q-ID | Question | Impact | Closure State | Search Performed | Evidence Needed | External Dependency | Next Action ||---|---|---|---|---|---|---|---|Impact:```textCRITICALHIGHMEDIUMLOW```Closure state:```textSOURCE_SEARCH_PENDINGSOURCE_SEARCH_IN_PROGRESSSOURCE_EXHAUSTEDEXTERNALLY_BLOCKEDRESOLVED_VERIFIEDRESOLVED_REJECTEDNOT_APPLICABLE```## Candidate Findings- write candidates to `00_hypotheses.md`- unresolved questions to `00_open_questions.md`- candidate evidence rows to `00_evidence_ledger.md`- keep canonical baseline empty/minimal until promotion## Stop ConditionStop after workspace, broad topology, coverage map, candidate claims, and prioritized investigation questions exist.Bootstrap is reconnaissance, not full-system understanding.

Frequently asked questions