How do I install the Mapear skill?

Run npx skillmds@latest add talhamah56/mapear 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 Mapear safe to use?

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

Which AI agents work with Mapear?

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 Mapear free to use?

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

Who published Mapear?

talhaMah56 (@talhamah56) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Mapear by talhamah56 — Agent Skill

Name: Mapear
Rating: 4.2 (5 reviews)
Author: talhaMah56

Mapear

Use to map an existing (brownfield) codebase and produce docs/architecture/assessment.md — stack, architecture, implicit bounded contexts, maturity across the 5 axes, debts/risks, and historical decisions to become retroactive ADRs. Re-running updates the assessment. Runs standalone when the codebase changes or to analyze an unfamiliar repo. Trigger with /mapear.

talhaMah56 Updated Sep 22, 2026

File contents

Translation note: Originally authored in Portuguese (pt-BR) by Igor Uehara (igoruehara/spec-driven, MIT). Translated to English by this hub to keep the repository language consistent. Original content unchanged in meaning; see the upstream repo for the pt-BR source.

Skill: Map the current state (as-is)

Produces a portrait of a project already in progress. First read the code, then ask only what the code does not reveal. It is idempotent: re-running updates docs/architecture/assessment.md.

Process

Automated mapping: identify stack, folder structure, architecture style, couplings, tests/CI, logs/metrics/tracing. Infer the implicit bounded contexts from the code organization. In large repos, delegate the scan to an exploration subagent (see docs/engineering/_templates/subagent.template.md) to keep the context lean.
External inputs (if any): if GitHub/cloud/observability MCPs are connected (validated account), use them to enrich the as-is. Cite the source.
Gap interview (AskUserQuestion): current business intent and North Star; biggest pains/risks today; domain terms that confuse the team; what MUST NOT break; team context and size.
Gap analysis: compare the as-is with the SDD standard across the 5 axes (tech stack, architecture, infrastructure, quality, observability). Mark risk (low/medium/high).
Historical decisions: list structural choices already made without a record → they become retroactive ADRs (status: accepted, recording the historical rationale).

Outputs

docs/architecture/assessment.md (use docs/architecture/_templates/assessment.template.md).
List of retroactive ADRs to create in docs/architecture/adr/.

Next step

Feed the assessment + gaps back into the 5 axes and your project roadmap.
Standalone: use /tech-debt (to prioritize the mapped debts) or /camada-agentica.

---name: mapeardescription: Use to map an existing (brownfield) codebase and produce docs/architecture/assessment.md — stack, architecture, implicit bounded contexts, maturity across the 5 axes, debts/risks, and historical decisions to become retroactive ADRs. Re-running updates the assessment. Runs standalone when the codebase changes or to analyze an unfamiliar repo. Trigger with /mapear.---> **Translation note:** Originally authored in Portuguese (pt-BR) by Igor Uehara ([igoruehara/spec-driven](https://github.com/igoruehara/spec-driven), MIT). Translated to English by this hub to keep the repository language consistent. Original content unchanged in meaning; see the upstream repo for the pt-BR source.# Skill: Map the current state (as-is)Produces a portrait of a project **already in progress**. First **read the code**, then ask only what the code does not reveal. It is **idempotent**: re-running updates `docs/architecture/assessment.md`.## Process1. **Automated mapping:** identify stack, folder structure, architecture style, couplings, tests/CI, logs/metrics/tracing. Infer the **implicit bounded contexts** from the code organization. In large repos, **delegate the scan to an exploration subagent** (see `docs/engineering/_templates/subagent.template.md`) to keep the context lean.2. **External inputs (if any):** if GitHub/cloud/observability MCPs are connected (validated account), use them to enrich the as-is. Cite the source.3. **Gap interview** (`AskUserQuestion`): current business intent and North Star; biggest pains/risks today; domain terms that confuse the team; what MUST NOT break; team context and size.4. **Gap analysis:** compare the as-is with the SDD standard across the 5 axes (tech stack, architecture, infrastructure, quality, observability). Mark risk (low/medium/high).5. **Historical decisions:** list structural choices already made without a record → they become **retroactive ADRs** (status: accepted, recording the historical rationale).## Outputs- `docs/architecture/assessment.md` (use `docs/architecture/_templates/assessment.template.md`).- List of retroactive ADRs to create in `docs/architecture/adr/`.## Next step- Feed the assessment + gaps back into the 5 axes and your project roadmap.- Standalone: use `/tech-debt` (to prioritize the mapped debts) or `/camada-agentica`.

Frequently asked questions