What does this skill do, and when should you use it?
This skill defines how to choose operating-system path types in the Codex repository. It focuses on path representations in app-server and exec-server protocols and on conversions between protocol boundaries and internal code. The guidance distinguishes legacy native-path strings, PathUri, AbsolutePathBuf, and PathBuf by use case. It also sets migration constraints for compatibility, security, diagnostics, and persistence.
When defining or explicitly migrating path-bearing types, it guides developers toward LegacyAppPathString, PathUri, AbsolutePathBuf, PathBuf, or String. It requires path conversion at the app-server protocol boundary, file:// URIs in exec-server APIs, and regular String deserialization for model-generated tool arguments followed by feature-specific path handling. It also specifies conversion-error behavior, URI formatting in diagnostics, and minimal migration changes.
- Maintaining app-server protocol types while preserving native path strings sent and received by existing clients.
- Adding or migrating exec-server API fields that use file:// URIs.
- Designing shared dependencies used by both servers without conflating their path semantics.
- Handling model-generated tool arguments that may contain raw relative or absolute paths for any operating system.
- Migrating path handling without changing model-visible text or introducing significant new failure modes.
How do you install this skill?
- This is migration guidance rather than a self-contained executable or verified automation tool; confirm that the referenced types exist and run project tests before adoption.
- The concrete review process for conversion failures, platform differences, and security-relevant paths is not specified; do not assume a migration is regression-free from the document alone.
- No Chinese documentation or mainland-China reachability evidence is provided, although the core function is local code guidance and does not visibly depend on an overseas online service.
The skill is located at .codex/skills/path-types/SKILL.md in the Codex repository; the README documents no separate skill installation process. To install Codex CLI, use curl -fsSL https://chatgpt.com/codex/install.sh | sh on macOS or Linux, or powershell -ExecutionPolicy ByPass -c "irm https://chatgpt.com/codex/install.ps1 | iex" on Windows. The README also lists npm install -g @openai/codex and brew install --cask codex.
tmp="$(mktemp -d)"
git clone --depth 1 https://github.com/openai/codex.git "$tmp"
mkdir -p ~/.claude/skills
cp -R "$tmp/.codex/skills/path-types" ~/.claude/skills/
rm -rf "$tmp"Generated from the source repository and skill path; it copies only this skill's folder. If the author's install steps above differ, follow those first. To scope it to one project, replace ~/.claude/skills with that project's .claude/skills.
How do you use this skill?
Once installed, send your agent any of these to trigger it:
- Choose the Rust type for this new exec-server path field according to the path-types guidance.
Trigger it when defining a new path-bearing type or explicitly requesting migration of an existing one in the Codex repository. Example: “Choose the Rust type for this new exec-server path field according to the path-types guidance.”
What are this skill's strengths and limitations?
- Clearly separates protocol-boundary types, internal path types, and model-generated tool arguments.
- Covers legacy-client compatibility, cross-platform URIs, error handling, and diagnostics during migration.
- Encourages focused changes and prevents premature storage of URIs in persistent data.
- It is tightly tailored to the Codex repository and its app-server and exec-server architecture.
- No scripts, test suite, or automated migration tool is provided.
- The source does not define the PathUri APIs or provide a complete migration example.
How does this skill compare with similar options?
Side by side with related skills; every score comes from the same FSRS standard.
| Skill | FS score | Stars | Last updated | License |
|---|---|---|---|---|
| Codex Path Types Guide this page ✓ OpenAI · Official | 47 · Use with care | ★ 129k | 11d ago | Apache-2.0 |
| LeanCTX — Local Context Intelligence Layer | 61 · Recommended | ★ 3.9k | 11d ago | Apache-2.0 |
| LeanCTX Local Context Control | 59 · Recommended | ★ 3.9k | 11d ago | Apache-2.0 |
| Callimachus Recall | 58 · Recommended | ★ 43 | 3mo ago | AGPL-3.0 |
| NeMo Relay Migration Assistant ✓ NVIDIA · Official | 57 · Use with care | ★ 3.6k | 11d ago | Apache-2.0 |
How did FollowSkills review this skill?
The skill provides only path-type selection and migration guidance, with no scripts, network access, credential handling, or destructive defaults. It asks for minimal edits and user input when compliance is difficult. However, it lacks explicit confirmation requirements, data-flow disclosure, rollback procedures, and sensitive-path handling boundaries, so full marks are not justified.
The rules are internally coherent and cover protocol boundaries, internal types, migration constraints, and failure strategies. The skill itself includes no tests, execution examples, or key-path diagnostic feedback. Under the static calibration, reliability is therefore capped at 10.
The name, description, and trigger are clear for defining new or explicitly migrating path-bearing types, and some non-fit situations are stated. However, there are no input/output examples, comprehensive non-fit boundaries, Chinese-language support, or evidence of mainland-China environment fit, so points are deducted.
The file has concise metadata, a clear title, and structured guidance; the repository supplies an Apache-2.0 license and official provenance. It lacks versioning, changelog, maintenance ownership, update path, installation notes, examples, and FAQs, leaving governance and maintenance assumptions unresolved.
The guidance is directly usable for Rust path-type selection and URI migration, and its core value is clear. However, there are no verified representative outputs, build results, or skill-specific test coverage, and real migrations still require manual judgment. Static calibration limits effectiveness to 7.
The skill is auditable primary source material, and the repository provides license and CI-related context. However, it contains no skill-specific tests, third-party reproduction, or corroborating evidence for its key paths, so the conclusion rests mainly on static inspection.
Open a dimension to read why it scored that way
Evidence confidence：Low — Mostly static review, author material or a limited demo; useful for discovery, not high-risk decisions.
See the full review method →