docs(skill): clarify ASAR inventory-first routing and provider selection - #10505

Summary

Fixes #10501.

Clarify skill routing for large Electron app.asar targets: inventory first with open_binary + inspect_artifact(detail: "summary"), pass narrowed source_paths to analyze_javascript_application, use integrity_policy: "record-and-continue" when .unpacked companions were re-signed after packing, and select an explicit provider_id (or call binary_session({})) when multiple deep providers may be configured.

Problem and expected behavior

Skill v62 routed ASAR/Electron trees straight to analyze_javascript_application without size/scope guards, omitted integrity_policy for post-packing re-signed .unpacked binaries, and documented provider_id for ida/kuna but not multi-provider ghidra/hopper ambiguity. Agents then hit whole-ASAR host deadlines, artifact_integrity_mismatch, and capability_unavailable (selection_reason: "ambiguous"). Expected: progressive-disclosure routing guards in SKILL.md with details in references/javascript-applications.md.

Change and scope

Authored skill only (.agents/skills/reverse-engineer-anything/ plus regenerated .cursor-plugin/skills/ mirror):

1. SKILL.md ASAR bullet — inventory-first + source_paths for large packages; integrity_policy: "record-and-continue" when retaining contradictions.
2. SKILL.md native open_binary bullet — explicit provider_id or binary_session({}) when multiple deep providers may be present.
3. references/javascript-applications.md — large-ASAR inventory pattern next to the existing detail: "summary" note; Electron .unpacked integrity policy guidance.

No runtime, catalog, or provider behavior changes.

Follow the contribution scope.
Unresolved scope, authority, side effects, or required verification block
integration. Link the required maintainer scope decision for new providers or
capabilities involving target execution, injection, mutation, or protection
recovery; ordinary fixes within existing boundaries may state "not applicable".
Draft PRs may leave the scope decision pending and the readiness and merge checklists
unchecked. Maintainers can help resolve open questions.

Contract and boundary impact

• Semantic owner and earliest changed stage: authored skill instructions; agent routing consumers of ASAR/Electron and multi-provider open_binary guidance.
• Contribution scope fit and linked maintainer decision: documentation within existing tool contracts; not applicable.
• CLI and MCP/tool-catalog contract: none.
• Provider, bridge, target-format, or platform compatibility: none (documents existing integrity_policy and provider selection behavior).
• Evidence, artifact, provenance, or reconstruction contract: none.
• Target selection, authority, upstream behavior, and cleanup details (if applicable): none.
• Generated metadata (docs/public/product-catalog.json), package, or installation impact (CI generates and validates ignored catalogs and skills/; edit authored instructions in .agents/skills/reverse-engineer-anything/ and never commit build outputs): Cursor plugin skill mirror regenerated; no package version change.

Expected effects (check known effects; use documentation-only on its own).
Unchecked items do not establish absence; leave uncertainties visible.

• Read existing files or captured data.
• Launch or attach to a process.
• Inject instrumentation or run scripts/code.
• Change process memory, registers, files, or configuration.
• Contact network services.
• Recover protected code or work around protections.
• Documentation or usability only; no target interaction.
• Not sure yet; investigation or maintainer guidance needed.

Evidence and regression coverage

• Tests added or updated: none (documentation-only).
• Base reproduction or other evidence: source comparison of skill v62 vs issue [Docs] Skill v62: clarify ASAR inventory-first routing, integrity_policy, and multi-provider open_binary selection #10501 expected content; integrity_policy / multi-provider behavior already covered by existing MCP boundary tests (asarUnpackedExtractionMcp, Electron integrity paths).
• User-visible CLI/MCP output (if applicable): none.
• Remaining proof gaps: no live Electron .app re-run in this PR; wording follows contracts already enforced in tests and guides.

Validation performed

• node scripts/generate-cursor-plugin-skill.mjs --check — passed
• npm run check:fast — typecheck and lint passed

Compatibility, safety, and release

• Breaking changes or migration steps: none.
• Real Hopper/Ghidra, browser, or OS coverage: not required for documentation-only routing clarification.
• Package or release metadata impact: none (skill text only; version metadata unchanged).
• Security, privacy, process, or containment review: none; documents existing read-only observation options.

Author readiness

Human owner: @BeqaKs

• 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.

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.
• The PR has one focused outcome and the title follows type(scope): outcome.
• Related issue is linked, or the reason for not linking one is stated above.
• Tests cover changed observable behavior and meaningful failure paths.
• Owning docs, contracts, and generated metadata are updated where needed.
• User-visible CLI/MCP changes include representative output.
• I checked the final diff for secrets, unrelated cleanup, and unsupported claims.