[PR #6386] [CLOSED] docs(skill): state the setup install limit once #7327

Closed
opened 2026-11-01 21:47:05 +00:00 by bsakaguchi · 0 comments
Owner

📋 Pull Request Information

Original PR: https://github.com/morluto/rea/pull/6386
Author: @PedroPaduelo
Created: 10/22/2026
Status: ❌ Closed

Base: main ← Head: docs/6378-setup-install-limit-once


📝 Commits (1)

  • 0da46e7 docs(skill): state the setup install limit once

📊 Changes

1 file changed (+1 additions, -2 deletions)

View changed files

📝 .agents/skills/reverse-engineer-anything/SKILL.md (+1 -2)

📄 Description

Summary

The authored reverse-engineer-anything skill stated the setup install limit twice, a few lines apart in the "Connect only when needed" section. This removes the repeated sentence so the rule appears once, next to the setup procedure it constrains.

Fixes #6378

Problem and expected behavior

.agents/skills/reverse-engineer-anything/SKILL.md carried two statements of the same rule:

  • "REA setup never installs or upgrades Node.js, npm, Homebrew, Java, Ghidra, IDA, JADX, Kuna, Binwalk, or Unblob." (line 71)
  • "REA setup never installs or upgrades unrelated software, including Node.js, npm, Homebrew, Java, Ghidra, IDA, JADX, Kuna, Binwalk or Unblob." (line 91)

The second restates the first. Agents load this skill, so the duplicate spends context and reads as two separate rules; the second copy also drops the Oxford comma the first uses. Expected behavior is one statement of the rule.

Change and scope

Remove the second statement. The surviving one keeps the full tool list and stays directly under the numbered setup-repair procedure, where a reader reaches it while repairing configuration. No behavior, contract, or capability changes.

Contribution scope: documentation only. Not applicable for a linked maintainer scope decision.

Contract and boundary impact

  • Semantic owner and earliest changed stage: the authored skill source .agents/skills/reverse-engineer-anything/SKILL.md; no runtime stage changes.
  • Contribution scope fit and linked maintainer decision: not applicable — documentation only, no new provider, capability, target format, or target execution.
  • CLI and MCP/tool-catalog contract: none.
  • Provider, bridge, target-format, or platform compatibility: none.
  • Evidence, artifact, provenance, or reconstruction contract: none.
  • Target selection, authority, upstream behavior, and cleanup details: not applicable.
  • Generated metadata (docs/public/product-catalog.json), package, or installation impact: none. skills/ is a generated, ignored output; it is regenerated by npm run build:cached and validated by npm run docs:check. Only the authored instruction source is edited.

Expected effects: documentation or usability only; no target interaction.

Evidence and regression coverage

  • Tests added or updated: none. The change removes prose only; no observable behavior changes.
  • Base reproduction or other evidence: source inspection of the authored skill. git blame shows the duplicate sentence was introduced together with the tool-list expansion in c1fd496e6a, while the first statement already existed.
  • User-visible CLI/MCP output: not applicable.
  • Remaining proof gaps: the packaged skill output was regenerated and validated locally, but not compared against a published bundle.

Validation performed

  • npm ci — installed 552 packages from the lockfile.
  • npm run typecheck — passed.
  • npm run build:cached — passed; regenerated skills/.
  • npm run docs:check — passed, including tests/conformance/readmeConsistency.test.ts (1 file, 9 tests).
  • npm run check:fast — passed (typecheck, lint).
  • npm run format:check — passed (5123 files).

Compatibility, safety, and release

  • Breaking changes or migration steps: none.
  • Real Hopper/Ghidra, browser, or OS coverage: not applicable — no target interaction and no provider path touched.
  • Package or release metadata impact: none. The packaged skill loses one sentence; no version, schema, or metadata change.
  • Security, privacy, process, or containment review: none.

Author readiness

Human owner:

  • 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.

These declarations are left for the human owner to complete.

Before merge

  • This PR addresses a concrete problem or an agreed enhancement.
  • Material scope and authority questions are resolved, and any required maintainer scope decision covers the final diff.
  • This PR has one focused outcome and the title follows type(scope): outcome.
  • Related issue is linked (Fixes #6378).
  • Tests cover changed observable behavior and meaningful failure paths. — Documentation only, so no behavior test applies; npm run docs:check and the README/skill consistency conformance test cover the edited text.
  • Owning docs, contracts, and generated metadata are updated where needed. — The owning authored skill source is updated; generated metadata is produced and validated by CI and stays uncommitted.
  • User-visible CLI/MCP changes include representative output. — No user-visible CLI or MCP contract change.
  • I checked the final diff for secrets, unrelated cleanup, and unsupported claims.

🔄 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/6386 **Author:** [@PedroPaduelo](https://github.com/PedroPaduelo) **Created:** 10/22/2026 **Status:** ❌ Closed **Base:** `main` ← **Head:** `docs/6378-setup-install-limit-once` --- ### 📝 Commits (1) - [`0da46e7`](https://github.com/morluto/rea/commit/0da46e76a201471856ff6b7b1a08b9c07428b613) docs(skill): state the setup install limit once ### 📊 Changes **1 file changed** (+1 additions, -2 deletions) <details> <summary>View changed files</summary> 📝 `.agents/skills/reverse-engineer-anything/SKILL.md` (+1 -2) </details> ### 📄 Description ## Summary The authored `reverse-engineer-anything` skill stated the setup install limit twice, a few lines apart in the "Connect only when needed" section. This removes the repeated sentence so the rule appears once, next to the setup procedure it constrains. Fixes #6378 ## Problem and expected behavior `.agents/skills/reverse-engineer-anything/SKILL.md` carried two statements of the same rule: - "REA setup never installs or upgrades Node.js, npm, Homebrew, Java, Ghidra, IDA, JADX, Kuna, Binwalk, or Unblob." (line 71) - "REA setup never installs or upgrades unrelated software, including Node.js, npm, Homebrew, Java, Ghidra, IDA, JADX, Kuna, Binwalk or Unblob." (line 91) The second restates the first. Agents load this skill, so the duplicate spends context and reads as two separate rules; the second copy also drops the Oxford comma the first uses. Expected behavior is one statement of the rule. ## Change and scope Remove the second statement. The surviving one keeps the full tool list and stays directly under the numbered setup-repair procedure, where a reader reaches it while repairing configuration. No behavior, contract, or capability changes. Contribution scope: documentation only. Not applicable for a linked maintainer scope decision. ## Contract and boundary impact - Semantic owner and earliest changed stage: the authored skill source `.agents/skills/reverse-engineer-anything/SKILL.md`; no runtime stage changes. - Contribution scope fit and linked maintainer decision: not applicable — documentation only, no new provider, capability, target format, or target execution. - CLI and MCP/tool-catalog contract: none. - Provider, bridge, target-format, or platform compatibility: none. - Evidence, artifact, provenance, or reconstruction contract: none. - Target selection, authority, upstream behavior, and cleanup details: not applicable. - Generated metadata (`docs/public/product-catalog.json`), package, or installation impact: none. `skills/` is a generated, ignored output; it is regenerated by `npm run build:cached` and validated by `npm run docs:check`. Only the authored instruction source is edited. Expected effects: documentation or usability only; no target interaction. ## Evidence and regression coverage - Tests added or updated: none. The change removes prose only; no observable behavior changes. - Base reproduction or other evidence: source inspection of the authored skill. `git blame` shows the duplicate sentence was introduced together with the tool-list expansion in c1fd496e6a, while the first statement already existed. - User-visible CLI/MCP output: not applicable. - Remaining proof gaps: the packaged skill output was regenerated and validated locally, but not compared against a published bundle. ## Validation performed - `npm ci` — installed 552 packages from the lockfile. - `npm run typecheck` — passed. - `npm run build:cached` — passed; regenerated `skills/`. - `npm run docs:check` — passed, including `tests/conformance/readmeConsistency.test.ts` (1 file, 9 tests). - `npm run check:fast` — passed (typecheck, lint). - `npm run format:check` — passed (5123 files). ## Compatibility, safety, and release - Breaking changes or migration steps: none. - Real Hopper/Ghidra, browser, or OS coverage: not applicable — no target interaction and no provider path touched. - Package or release metadata impact: none. The packaged skill loses one sentence; no version, schema, or metadata change. - Security, privacy, process, or containment review: none. ## Author readiness Human owner: <!-- @PedroPaduelo --> - [ ] 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. These declarations are left for the human owner to complete. ## Before merge - [x] This PR addresses a concrete problem or an agreed enhancement. - [x] Material scope and authority questions are resolved, and any required maintainer scope decision covers the final diff. - [x] This PR has one focused outcome and the title follows `type(scope): outcome`. - [x] Related issue is linked (Fixes #6378). - [x] Tests cover changed observable behavior and meaningful failure paths. — Documentation only, so no behavior test applies; `npm run docs:check` and the README/skill consistency conformance test cover the edited text. - [x] Owning docs, contracts, and generated metadata are updated where needed. — The owning authored skill source is updated; generated metadata is produced and validated by CI and stays uncommitted. - [ ] User-visible CLI/MCP changes include representative output. — No user-visible CLI or MCP contract change. - [x] I checked the final diff for secrets, unrelated cleanup, and unsupported claims. --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>
bsakaguchi 2026-11-01 21:47:05 +00:00
Sign in to join this conversation.
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#7327
No description provided.