Add Uint Support
pytorch/pytorch
Add unsigned integer (uint) type support to PyTorch operators by updating ATDISPATCH macros.
Review or refresh repository specs against implementation and tests.
Install Spec Check
$ npx skills add gdsfactory/sax --skill spec-check -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install gdsfactory/sax spec-check --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/gdsfactory/sax.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/spec-check .claude/skills/spec-check && 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 "spec-check" agent skill from https://github.com/gdsfactory/sax/tree/main/.agents/skills/spec-check into .claude/skills/spec-check/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "spec-check", 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/gdsfactory/sax/tree/main/.agents/skills/spec-checkType 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 gdsfactory/sax --skill spec-check -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install gdsfactory/sax spec-check --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/gdsfactory/sax.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/spec-check .agents/skills/spec-check && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "spec-check" agent skill from https://github.com/gdsfactory/sax/tree/main/.agents/skills/spec-check into .agents/skills/spec-check/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "spec-check", 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 gdsfactory/sax --skill spec-check -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install gdsfactory/sax spec-check --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/gdsfactory/sax.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/spec-check .cursor/skills/spec-check && 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 "spec-check" agent skill from https://github.com/gdsfactory/sax/tree/main/.agents/skills/spec-check into .cursor/skills/spec-check/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "spec-check", 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/gdsfactory/sax.git --path .agents/skills/spec-check--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 gdsfactory/sax --skill spec-check -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install gdsfactory/sax spec-check --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/gdsfactory/sax.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/spec-check .gemini/skills/spec-check && 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 "spec-check" agent skill from https://github.com/gdsfactory/sax/tree/main/.agents/skills/spec-check into .gemini/skills/spec-check/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "spec-check", 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 gdsfactory/sax spec-checkInstalls 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 gdsfactory/sax --skill spec-check -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/gdsfactory/sax.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/spec-check .github/skills/spec-check && 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 "spec-check" agent skill from https://github.com/gdsfactory/sax/tree/main/.agents/skills/spec-check into .github/skills/spec-check/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "spec-check", 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 gdsfactory/sax --skill spec-check -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install gdsfactory/sax spec-check --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/gdsfactory/sax.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/spec-check .opencode/skills/spec-check && 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 "spec-check" agent skill from https://github.com/gdsfactory/sax/tree/main/.agents/skills/spec-check into .opencode/skills/spec-check/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "spec-check", 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
spec-check- GitHub stars
- 131
- Token cost
- ~650 tokens
- SKILL.md length
- 294 words
- Files
- 1
- Skills in repo
- 2
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Review or refresh repository specs against implementation and tests.
- Works in 6 steps: Bound the review. Use the requested… → Trace each important claim. Inspect its… → Classify disagreements. Report stale… → …
- Conformance audits
- Calls git
- Spec drift checks after changes
What it does
Spec Check is an agent skill from gdsfactory/sax. Review or refresh repository specs against implementation and tests. Use for conformance audits, spec drift checks after changes, documenting existing subsystems, or updating evidence. Read-only by default; edit specs when the user requests a refresh, without silently changing runtime behavior.
Its SKILL.md is about 650 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in AI & LLM Engineering, covering Deep learning. The repository describes itself as: S + Autograd + XLA :: S-parameter based frequency domain circuit simulations and optimizations using JAX. The licence is Apache-2.0.
When your agent uses it
- Conformance audits
- Spec drift checks after changes
- Documenting existing subsystems
- Updating evidence
Example prompts
- “/spec-check”
Workflow steps
6 steps, taken from the first numbered list in SKILL.md.
- Bound the review. Use the requested subsystem or diff. If scope is clear,
- Trace each important claim. Inspect its source symbol, tests, and any example
- Classify disagreements. Report stale spec, implementation mismatch, missing
- Verify proportionally. Run focused, non-destructive checks when practical.
- Review mode: return prioritized findings first, followed by coverage limits.
- Refresh mode (requested by user): update the existing spec's established
What it can do on your machine
Read from SKILL.md and the folder at commit 784e750. 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
Shell commands in SKILL.md call:
git
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.
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
Spec Check loads about 650 tokens when it runs. Until then it costs about 77 tokens; SKILL.md has 294 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); files beside SKILL.md are not scanned.
SKILL.md
The full file from gdsfactory/sax at commit 784e750, republished under its Apache-2.0 licence (© gdsfactory). 294 words, ~650 tokens.
Download SKILL.mdSave it as
.claude/skills/spec-check/SKILL.md (or your agent's skills folder).- name
- spec-check
- description
- Review or refresh repository specs against implementation and tests. Use for conformance audits, spec drift checks after changes, documenting existing subsystems, or updating evidence. Read-only by default; edit specs when the user requests a refresh, without silently changing runtime behavior.
Check and refresh specs
Read repository-root AGENTS.md, specs/README.md, and the relevant subsystem
specs. See the spec index and
verification guidance. Do not load every spec
for a local review.
- Bound the review. Use the requested subsystem or diff. If scope is clear, proceed without a questionnaire; if a whole-repo audit is requested, inventory public modules and prioritize observable contracts over private implementation.
- Trace each important claim. Inspect its source symbol, tests, and any example needed to resolve meaning. Test presence is not test execution, and a passing file does not verify every nearby claim. Check inputs, outputs, errors, units, shape/direction, compatibility, and applicable numerical assumptions.
- Classify disagreements. Report stale spec, implementation mismatch, missing verification, or unresolved intent. Give a path/symbol, impact, and smallest useful next check. Do not automatically declare prose or code authoritative.
- Verify proportionally. Run focused, non-destructive checks when practical. Record command, environment assumptions, result, and limits. Distinguish static observations from runtime reproductions and untested hypotheses. See the verification guide before running environment setup or notebook commands.
- Review mode: return prioritized findings first, followed by coverage limits. Do not edit specs or runtime code merely because a mismatch was discovered.
- Refresh mode (requested by user): update the existing spec's established
behavior and evidence; put contradictions in
specs/open-questions.md. Label future behavior as proposed. Do not fix runtime code unless separately in scope. Check relative links, the index, andgit diff --checkbefore summarizing edits.
A useful refresh is concise: contract, evidence, verification limits, open questions. Avoid duplicating full signatures/API docs, asserting physical properties for models that intentionally violate them, or adding a bureaucracy of requirement IDs and status files. If evidence is unavailable, state what remains unknown and what would establish it; do not invent a guarantee.
© gdsfactory, 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
Just SKILL.md in .agents/skills/spec-check of gdsfactory/sax.
Open the folder on GitHubat commit 784e750
Compare with similar skills
Spec Check 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 |
|---|---|---|---|---|---|---|
| Spec Check this skillgdsfactory/sax | 131 | — | ~650 | Automated safety check: Pass | Apache-2.0 | |
| Add Uint Supportpytorch/pytorch | 104k | 2 repos | ~2.3k | Automated safety check: Pass | Custom licence | |
| Segment Anything Model GuideOrchestra-Research/AI-Research-SKILLs | 13k | 9 repos | ~3.3k | Automated safety check: Pass | MIT | |
| Add Oponnx/onnx | 22k | — | ~1.2k | Automated safety check: Pass | Apache-2.0 | |
| CLIP Image-Text MatchingOrchestra-Research/AI-Research-SKILLs | 13k | 8 repos | ~1.7k | Automated safety check: Pass | MIT | |
| Add Function Bodyonnx/onnx | 22k | — | ~1.1k | Automated safety check: Pass | Apache-2.0 |
Similar skills
Segment Anything Model Guide
Orchestra-Research/AI-Research-SKILLs
Guide to using Meta's Segment Anything Model for zero-shot image segmentation with point, box or mask prompts, or automatic mask generation.
Add Op
onnx/onnx
Add a new ONNX operator or update an existing operator to a new opset version.
CLIP Image-Text Matching
Orchestra-Research/AI-Research-SKILLs
Explains OpenAI's CLIP model for zero-shot image classification, image-text similarity, semantic image search and content moderation, with install steps and code patterns.
Add Function Body
onnx/onnx
Add a function body definition to an ONNX operator, defining how it decomposes into simpler ops.
Paddle Design Distributed
PaddlePaddle/Paddle
A skill your agent uses when working with Paddle's distributed training system: understanding parallelism strategies (DP, ZeRO, TP, PP, SP), semi-automatic parallel with ProcessMesh + shardtensor…
More from gdsfactory/sax
Spec Change
gdsfactory/sax
Make behavior changes using this repository's lightweight spec-driven flow.
Related
Categories
Questions about Spec Check
What does Spec Check do?
Review or refresh repository specs against implementation and tests. Spec Check is an agent skill from gdsfactory/sax. Review or refresh repository specs against implementation and tests.
When should I use Spec Check?
Spec Check fits situations like: conformance audits; spec drift checks after changes; documenting existing subsystems; updating evidence.
How do I install Spec Check in Claude Code?
Run `npx skills add gdsfactory/sax --skill spec-check -a claude-code`. Or copy the skill folder (.agents/skills/spec-check in gdsfactory/sax) into .claude/skills/spec-check in your project. Claude Code loads it when a task matches its description.
How do I install Spec Check in Codex?
Run `npx skills add gdsfactory/sax --skill spec-check -a codex`. Or copy the skill folder (.agents/skills/spec-check in gdsfactory/sax) into .agents/skills/spec-check in your project. Codex loads it when a task matches its description.
Can I use Spec Check 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 gdsfactory/sax --skill spec-check -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/spec-check, .gemini/skills/spec-check, .github/skills/spec-check and .opencode/skills/spec-check in your project.
What does Spec Check need to run?
Going by SKILL.md and its folder, Spec Check needs the command-line tools its instructions call (git).
Does Spec Check access the network?
SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Spec Check 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. Review the folder before installing.
What licence does Spec Check use?
Spec Check 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 Spec Check use?
About 650 tokens (SKILL.md is roughly 2.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Spec Check?
Skills that share tags, products or a category with Spec Check: Add Uint Support (pytorch/pytorch, 104k stars), Segment Anything Model Guide (Orchestra-Research/AI-Research-SKILLs, 13k stars), Add Op (onnx/onnx, 22k stars) and CLIP Image-Text Matching (Orchestra-Research/AI-Research-SKILLs, 13k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Spec Check?
gdsfactory (a GitHub organization) maintains it in gdsfactory/sax, which has 131 GitHub stars. The repository holds 2 skills in this directory. The repository was last updated on October 1, 2026.
Source: gdsfactory/sax on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.