morluto/rea

Fork 0

mirror of https://github.com/morluto/rea.git synced 2026-11-05 06:45:22 +00:00

[PR #7269] docs(skill): guide evidence-led online platform reconstruction #7801

New issue

Open

opened 2026-11-05 01:47:45 +00:00 by bsakaguchi · 0 comments

bsakaguchi commented

2026-11-05 01:47:45 +00:00

Owner

📋 Pull Request Information

Original PR: https://github.com/morluto/rea/pull/7269
Author: @ai-automating-com
Created: 10/26/2026
Status: 🔄 Open

Base: main ← Head: docs/platform-reconstruction-workflow

📝 Commits (1)

972d518 docs(skill): guide evidence-led online platform reconstruction

📊 Changes

2 files changed (+135 additions, -1 deletions)

View changed files

📝 .agents/skills/reverse-engineer-anything/SKILL.md (+9 -1)
➕ .agents/skills/reverse-engineer-anything/references/platform-reconstruction.md (+126 -0)

📄 Description

Summary

Online-platform reconstruction requests need a connected map of screens, roles, flows, data rules, and acceptance checks. Add a focused skill reference that turns REA evidence into an implementation handoff and separates behavioral verification from visual similarity and manually reported progress.

Change and scope

Route relevant requests from the skill entrypoint to the new guide. Cover scoped discovery, evidence-linked inventories, a working vertical slice, explicit mocks and unknowns, and checks of persisted effects and ownership. Use the existing passive-observation, browser-scenario, and AgentEnv workflows according to their actual contracts. Investigation alone does not authorize building, deployment, or consequential platform actions.

Documentation only: two authored skill files; no CLI/MCP contracts, providers, executable helpers, or generated outputs changed. A new provider/mutation scope decision is not applicable. Existing runtime and cleanup contracts remain the authority.

Documentation or usability only; no target interaction.

Validation performed

Skill-creator frontmatter/scaffold validation: passed.
Relative link and heading-anchor check for both changed documents: all 16 passed.
git diff --cached --check: passed before commit.
Manual source review against existing browser and environment guides: passive observation and declared scenario actions remain distinct; the guide does not promise recovery of inaccessible server implementation.
SkillSpector static scan of the full authored skill: failed with incomplete analysis (66.7% coverage). Findings affect pre-existing instruction/reference content, including unpinned package commands, plist/approval wording, table whitespace, and bounded parser/reference-resolution limits. The new reference received no findings. This does not establish a clean full-bundle security result, and the proposal was not installed or activated.

Runtime tests, full repository checks, and live-provider/agent behavioral evaluation were not run for this documentation-only proposal. Human review of instruction quality remains outstanding.

Author readiness

Human owner: @ai-automating-com

I reviewed the final diff and relevant existing code, understand the change and its edge cases, and take responsibility for the complete PR, including AI-assisted work.
I checked the evidence above, confirmed it supports the current change, and recorded meaningful validation gaps.
I declare this PR ready for initial maintainer review.

_{🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.}

## 📋 Pull Request Information **Original PR:** https://github.com/morluto/rea/pull/7269 **Author:** [@ai-automating-com](https://github.com/ai-automating-com) **Created:** 10/26/2026 **Status:** 🔄 Open **Base:** `main` ← **Head:** `docs/platform-reconstruction-workflow` --- ### 📝 Commits (1) - [`972d518`](https://github.com/morluto/rea/commit/972d5189e478736518e3ce564bb9170b12795eac) docs(skill): guide evidence-led online platform reconstruction ### 📊 Changes **2 files changed** (+135 additions, -1 deletions) <details> <summary>View changed files</summary> 📝 `.agents/skills/reverse-engineer-anything/SKILL.md` (+9 -1) ➕ `.agents/skills/reverse-engineer-anything/references/platform-reconstruction.md` (+126 -0) </details> ### 📄 Description ## Summary Online-platform reconstruction requests need a connected map of screens, roles, flows, data rules, and acceptance checks. Add a focused skill reference that turns REA evidence into an implementation handoff and separates behavioral verification from visual similarity and manually reported progress. ## Change and scope Route relevant requests from the skill entrypoint to the new guide. Cover scoped discovery, evidence-linked inventories, a working vertical slice, explicit mocks and unknowns, and checks of persisted effects and ownership. Use the existing passive-observation, browser-scenario, and AgentEnv workflows according to their actual contracts. Investigation alone does not authorize building, deployment, or consequential platform actions. Documentation only: two authored skill files; no CLI/MCP contracts, providers, executable helpers, or generated outputs changed. A new provider/mutation scope decision is not applicable. Existing runtime and cleanup contracts remain the authority. - [x] Documentation or usability only; no target interaction. ## Validation performed - Skill-creator frontmatter/scaffold validation: passed. - Relative link and heading-anchor check for both changed documents: all 16 passed. - `git diff --cached --check`: passed before commit. - Manual source review against existing browser and environment guides: passive observation and declared scenario actions remain distinct; the guide does not promise recovery of inaccessible server implementation. - SkillSpector static scan of the full authored skill: failed with incomplete analysis (66.7% coverage). Findings affect pre-existing instruction/reference content, including unpinned package commands, plist/approval wording, table whitespace, and bounded parser/reference-resolution limits. The new reference received no findings. This does not establish a clean full-bundle security result, and the proposal was not installed or activated. Runtime tests, full repository checks, and live-provider/agent behavioral evaluation were not run for this documentation-only proposal. Human review of instruction quality remains outstanding. ## Author readiness Human owner: @ai-automating-com - [ ] I reviewed the final diff and relevant existing code, understand the change and its edge cases, and take responsibility for the complete PR, including AI-assisted work. - [ ] I checked the evidence above, confirmed it supports the current change, and recorded meaningful validation gaps. - [ ] I declare this PR ready for initial maintainer review. --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>

bsakaguchi added the

pull-request

label

2026-11-05 01:47:45 +00:00

No milestone

No project

No assignees

1 participant

Notifications

Due date

The due date is invalid or out of range. Please use the format "yyyy-mm-dd".

No due date set.

Dependencies

No dependencies set.

Reference

morluto/rea#7801

No description provided.

Rows
Columns