macOS View Refactor
robinebers/openusage
Refactor macOS SwiftUI views and scenes into stable structure.
Invoke only when the user explicitly requests a WiFi Lens knowledge-boundary audit or the active task names that audit as a required deliverable.
Install Protect Knowledge Boundary
$ npx skills add ShiinaLabs/wifi-lens --skill protect-knowledge-boundary -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install ShiinaLabs/wifi-lens protect-knowledge-boundary --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/ShiinaLabs/wifi-lens.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/protect-knowledge-boundary .claude/skills/protect-knowledge-boundary && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "protect-knowledge-boundary" agent skill from https://github.com/ShiinaLabs/wifi-lens/tree/master/.agents/skills/protect-knowledge-boundary into .claude/skills/protect-knowledge-boundary/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "protect-knowledge-boundary", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/ShiinaLabs/wifi-lens/tree/master/.agents/skills/protect-knowledge-boundaryType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add ShiinaLabs/wifi-lens --skill protect-knowledge-boundary -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install ShiinaLabs/wifi-lens protect-knowledge-boundary --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ShiinaLabs/wifi-lens.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/protect-knowledge-boundary .agents/skills/protect-knowledge-boundary && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "protect-knowledge-boundary" agent skill from https://github.com/ShiinaLabs/wifi-lens/tree/master/.agents/skills/protect-knowledge-boundary into .agents/skills/protect-knowledge-boundary/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "protect-knowledge-boundary", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add ShiinaLabs/wifi-lens --skill protect-knowledge-boundary -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install ShiinaLabs/wifi-lens protect-knowledge-boundary --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ShiinaLabs/wifi-lens.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/protect-knowledge-boundary .cursor/skills/protect-knowledge-boundary && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "protect-knowledge-boundary" agent skill from https://github.com/ShiinaLabs/wifi-lens/tree/master/.agents/skills/protect-knowledge-boundary into .cursor/skills/protect-knowledge-boundary/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "protect-knowledge-boundary", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/ShiinaLabs/wifi-lens.git --path .agents/skills/protect-knowledge-boundary--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add ShiinaLabs/wifi-lens --skill protect-knowledge-boundary -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install ShiinaLabs/wifi-lens protect-knowledge-boundary --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ShiinaLabs/wifi-lens.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/protect-knowledge-boundary .gemini/skills/protect-knowledge-boundary && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "protect-knowledge-boundary" agent skill from https://github.com/ShiinaLabs/wifi-lens/tree/master/.agents/skills/protect-knowledge-boundary into .gemini/skills/protect-knowledge-boundary/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "protect-knowledge-boundary", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install ShiinaLabs/wifi-lens protect-knowledge-boundaryInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add ShiinaLabs/wifi-lens --skill protect-knowledge-boundary -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/ShiinaLabs/wifi-lens.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/protect-knowledge-boundary .github/skills/protect-knowledge-boundary && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "protect-knowledge-boundary" agent skill from https://github.com/ShiinaLabs/wifi-lens/tree/master/.agents/skills/protect-knowledge-boundary into .github/skills/protect-knowledge-boundary/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "protect-knowledge-boundary", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add ShiinaLabs/wifi-lens --skill protect-knowledge-boundary -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install ShiinaLabs/wifi-lens protect-knowledge-boundary --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ShiinaLabs/wifi-lens.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/protect-knowledge-boundary .opencode/skills/protect-knowledge-boundary && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "protect-knowledge-boundary" agent skill from https://github.com/ShiinaLabs/wifi-lens/tree/master/.agents/skills/protect-knowledge-boundary into .opencode/skills/protect-knowledge-boundary/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "protect-knowledge-boundary", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
protect-knowledge-boundary- GitHub stars
- 118
- Token cost
- ~1.6k tokens
- SKILL.md length
- 784 words
- Files
- 8 (incl. scripts, references)
- Skills in repo
- 3
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Invoke only when the user explicitly requests a WiFi Lens knowledge-boundary audit or the active task names that audit as a required deliverable.
- Works in 6 steps: Treat the root repository as public and… → Split the change into modules and review… → Trace the relationships around each… → …
- Explicitly requests a WiFi Lens knowledge-boundary audit
- SKILL.md covers Default invocation policy, Required context, Workflow and Review map, plus 3 more sections
- Runs Python scripts from its folder
What it does
Protect Knowledge Boundary is an agent skill from ShiinaLabs/wifi-lens. Invoke only when the user explicitly requests a WiFi Lens knowledge-boundary audit or the active task names that audit as a required deliverable. This skill is opt-in only; do not run it automatically for documentation, Agent assets, Pro changes, commits, pushes, refactors, or reviews.
Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 11 other files, including scripts and reference files (for example `agents/openai.yaml`, `references/boundary-policy.md` and `scripts/check_public_knowledge.py`).
It sits in Mobile, covering Refactoring and iOS development. It works with macOS and SwiftUI. The repository describes itself as: Native open-source network diagnostics app for macOS with built-in Wi-Fi analysis. The licence is Apache-2.0.
When your agent uses it
- Explicitly requests a WiFi Lens knowledge-boundary audit
- The active task names that audit as a required deliverable
Example prompts
- “/protect-knowledge-boundary”
Requirements
- Python 3
Workflow steps
6 steps, taken from the first numbered list in SKILL.md.
- Treat the root repository as public and WiFiLensPro/ as a separate private
- Split the change into modules and review every changed file individually.
- Trace the relationships around each changed module in both directions
- Inspect Xcode project wiring manually. Review the relevant source groups,
- For every boundary-crossing edge, write a short PASS, REVIEW, or
- Report root and Pro results separately. Do not claim completion while any
What it can do on your machine
Read from SKILL.md and the folder at commit 4783d30. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 2 files in scripts/ (Python), which the agent can run.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Protect Knowledge Boundary loads about 1.6k tokens when it runs, and up to ~2.4k if it reads all its reference files. Until then it costs about 78 tokens; SKILL.md has 784 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
SKILL.md
The full file from ShiinaLabs/wifi-lens at commit 4783d30, republished under its Apache-2.0 licence (© ShiinaLabs). 784 words, ~1,568 tokens.
Download SKILL.mdSave it as
.claude/skills/protect-knowledge-boundary/SKILL.md (or your agent's skills folder). This skill also uses 7 other files; get the full folder from GitHub.- name
- protect-knowledge-boundary
- description
- Invoke only when the user explicitly requests a WiFi Lens knowledge-boundary audit or the active task names that audit as a required deliverable. This skill is opt-in only; do not run it automatically for documentation, Agent assets, Pro changes, commits, pushes, refactors, or reviews.
Protect Knowledge Boundary
Default invocation policy
OPT-IN ONLY. Do not run this skill automatically. Run it only when the user explicitly requests a knowledge-boundary audit or the active task names that audit as a required deliverable.
Do not infer permission to run it from a change touching WiFiLensCore, the
private Pro repository, edition composition, documentation, Agent assets, or
the OSS/Pro boundary. Do not run it before commits or pushes, after ordinary
code changes, during routine refactors, or during routine code review.
The Production Pro binary audit is a separate release invariant. Keep it in the release verification chain; this opt-in policy does not disable it.
Keep private Pro implementation knowledge inside the WiFiLensPro/ submodule while
allowing the public repository to index approved private entrypoints.
Required context
Read references/boundary-policy.md completely before reviewing or changing knowledge-boundary content. Do not load private Pro documentation or implementation into Agent context unless the task is explicitly Pro-scoped. The boundary decision must come from a manual review of modules, file locations, target membership, and dependency direction.
Workflow
When an explicitly requested audit is part of a task, follow the commit
verification guidance in .agents/references/collaboration-rules.md and the
user's instructions for running or skipping checks.
- Treat the root repository as public and
WiFiLensPro/as a separate private repository. Inspect their Git status and diffs separately. - Split the change into modules and review every changed file individually.
For each file, record its physical location, owning module, edition
(
OSS,shared contract, orPro), target membership, and role in the dependency graph. - Trace the relationships around each changed module in both directions: identify its callers, callees, imported contracts, composition entrypoint, resources, and tests. Confirm that the public side depends only on public or edition-neutral contracts, while private behavior remains behind the target-selected composition boundary.
- Inspect Xcode project wiring manually. Review the relevant source groups,
PBXSourcesBuildPhaseentries,OSS.xcconfig/PRO.xcconfig, resources, schemes, and test target membership. A private path appearing in Pro build wiring is not itself a leak; the question is which target receives the file and whether public source imports a private implementation. - For every boundary-crossing edge, write a short
PASS,REVIEW, orFAILdecision with the reason. An ambiguous module relationship isREVIEWand must not be silently inferred as safe. - Report root and Pro results separately. Do not claim completion while any changed module, target-membership edge, or dependency relationship remains unreviewed.
Review map
Use the public repository's existing architecture map as the starting point:
WiFiLensCore/Sources/WiFiLensCore/contains shared product implementation modules.WiFiLens/Sources/WiFiLens/App/EditionCompositionContext.swiftis the edition-neutral context passed across the composition seam.WiFiLens/Sources/WiFiLens/App/OSSEditionComposition.swiftis the public composition implementation and must remain safe for the OSS target.WiFiLens/Configs/OSS.xcconfigandWiFiLens/Configs/PRO.xcconfigselect the target-specific compilation entrypoints.WiFiLens.xcodeproj/project.pbxprojis the source of truth for target membership and for the public project's Pro build wiring.
For each changed module, follow its edges through the scanner/runtime, observation models and pipeline, presentation layer, and finally the edition-composition seam. Do not infer a private module's internal design from its filename, public references, or build success.
Show full SKILL.md (281 more words)Show less
Review record
Keep a compact record for each review. The record must be based on inspected files and project wiring, not on a scanner summary:
| File | Physical repository | Module | Edition | Target membership | Callers / callees / composition seam | Decision |
|---|---|---|---|---|---|---|
path | root or WiFiLensPro/ | concrete module | OSS, shared contract, or Pro | OSS / Pro / both / tests | inspected relationship and evidence | PASS, REVIEW, or FAIL |
Also list every edge that crosses an edition boundary and state why the edge is allowed, unresolved, or forbidden. A review is incomplete if a row or edge is omitted merely because the file did not fail an automated check.
Decision rules
PASS: every changed module and boundary edge has been manually reviewed; the file location, target membership, and dependency direction are clear.REVIEW: a module's ownership, target membership, or relationship is ambiguous. Stop and ask the user; do not infer permission to expose more context.FAIL: the review shows a public target receiving private implementation, public source importing a private concrete implementation, or private implementation knowledge being added to public assets.
Scripts in this directory are auxiliary lint or asset-integrity tools. Their
output cannot establish a boundary PASS and must never replace the manual
module-by-module review above.
Never fix a failure by weakening a rule, excluding a new path, updating hashes, or rewriting the instruction anchor as part of an ordinary check. Changes to protected assets require explicit user approval and a focused review. Generate new hashes only after that review, then run all Skill tests and both checks.
Integrity limits
Local hashes make tampering visible during normal work; they cannot stop a committer who deliberately changes every local anchor. Trusted CI plus CODEOWNERS approval is required for merge-level enforcement.
© ShiinaLabs, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 7 other files (scripts, references) in .agents/skills/protect-knowledge-boundary of ShiinaLabs/wifi-lens.
- SKILL.md
- agents/openai.yaml
- references/boundary-policy.md
- scripts/check_public_knowledge.py
- scripts/verify_integrity.py
- tests/test_check_public_knowledge.py
- tests/test_commit_check_consent.py
- tests/test_verify_integrity.py
Open the folder on GitHubat commit 4783d30
Compare with similar skills
Protect Knowledge Boundary next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Protect Knowledge Boundary this skillShiinaLabs/wifi-lens | 118 | — | ~1.6k | Automated safety check: Pass | Apache-2.0 | |
| macOS View Refactorrobinebers/openusage | 4.3k | — | ~1.4k | Automated safety check: Pass | MIT | |
| View Refactorrobinebers/openusage | 4.3k | — | ~1.4k | Automated safety check: Pass | MIT | |
| Capture Usage4claude Screenshotsf-is-h/Usage4Claude | 400 | — | ~3k | Automated safety check: Pass | MIT | |
| macOS DevelopmentKartikLabhshetwar/better-shot | 2.4k | 2 repos | ~735 | Automated safety check: Pass | Custom licence | |
| Code ReviewRobertoMachorro/Moped | 115 | — | ~2.1k | Automated safety check: Pass | GPL-3.0 |
Similar skills
View Refactor
robinebers/openusage
Refactor macOS SwiftUI views and scenes with strong defaults for small dedicated subviews, stable sidebar and selection structure, explicit command and toolbar ownership, scene-aware state, and…
Capture Usage4claude Screenshots
f-is-h/Usage4Claude
Produce every Usage4Claude interface image used by the READMEs and docs.
macOS Development
KartikLabhshetwar/better-shot
Comprehensive macOS development guidance including Swift 6+, SwiftUI, SwiftData, architecture patterns, AppKit bridging, and macOS 26 Tahoe APIs.
Code Review
RobertoMachorro/Moped
Review guidance for Moped, a sandboxed macOS SwiftUI text editor with a homegrown TextKit 1 editor core in the local MopedEditor package.
Swiftui Debugging
st0012/cctop
A skill your agent uses when debugging SwiftUI issues in this macOS app — views not updating, layout problems, unnecessary re-renders, state ownership bugs, Preview crashes, or NSHostingView/NSPanel…
More from ShiinaLabs/wifi-lens
I18n Completer
ShiinaLabs/wifi-lens
A skill your agent uses when checking, completing, fixing, or adding translations in .xcstrings files, especially when localizations are missing or glossary terminology must be enforced.
Verify Build
ShiinaLabs/wifi-lens
A skill your agent uses when a change touches the WiFi Lens product itself (Swift app source, unit tests) before claiming that work is complete, before committing such a change, or when asked to…
Related
Categories
Questions about Protect Knowledge Boundary
What does Protect Knowledge Boundary do?
Invoke only when the user explicitly requests a WiFi Lens knowledge-boundary audit or the active task names that audit as a required deliverable. Protect Knowledge Boundary is an agent skill from ShiinaLabs/wifi-lens. Invoke only when the user explicitly requests a WiFi Lens knowledge-boundary audit or the active task names that audit as a required deliverable.
When should I use Protect Knowledge Boundary?
Protect Knowledge Boundary fits situations like: explicitly requests a WiFi Lens knowledge-boundary audit; the active task names that audit as a required deliverable.
How do I install Protect Knowledge Boundary in Claude Code?
Run `npx skills add ShiinaLabs/wifi-lens --skill protect-knowledge-boundary -a claude-code`. Or copy the skill folder (.agents/skills/protect-knowledge-boundary in ShiinaLabs/wifi-lens) into .claude/skills/protect-knowledge-boundary in your project. Claude Code loads it when a task matches its description.
How do I install Protect Knowledge Boundary in Codex?
Run `npx skills add ShiinaLabs/wifi-lens --skill protect-knowledge-boundary -a codex`. Or copy the skill folder (.agents/skills/protect-knowledge-boundary in ShiinaLabs/wifi-lens) into .agents/skills/protect-knowledge-boundary in your project. Codex loads it when a task matches its description.
Can I use Protect Knowledge Boundary in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add ShiinaLabs/wifi-lens --skill protect-knowledge-boundary -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/protect-knowledge-boundary, .gemini/skills/protect-knowledge-boundary, .github/skills/protect-knowledge-boundary and .opencode/skills/protect-knowledge-boundary in your project.
What does Protect Knowledge Boundary need to run?
Going by SKILL.md and its folder, Protect Knowledge Boundary needs Python for the scripts in its folder. Our summary lists: Python 3.
Does Protect Knowledge Boundary access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Protect Knowledge Boundary safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Protect Knowledge Boundary use?
Protect Knowledge Boundary is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Protect Knowledge Boundary use?
About 1.6k tokens (SKILL.md is roughly 6.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 801 tokens, read only when the agent opens those files.
What are the alternatives to Protect Knowledge Boundary?
Skills that share tags, products or a category with Protect Knowledge Boundary: macOS View Refactor (robinebers/openusage, 4.3k stars), View Refactor (robinebers/openusage, 4.3k stars), Capture Usage4claude Screenshots (f-is-h/Usage4Claude, 400 stars) and macOS Development (KartikLabhshetwar/better-shot, 2.4k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Protect Knowledge Boundary?
ShiinaLabs (a GitHub organization) maintains it in ShiinaLabs/wifi-lens, which has 118 GitHub stars. The repository holds 3 skills in this directory. The repository was last updated on October 7, 2026.
Source: ShiinaLabs/wifi-lens on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.