Skip to content
Back to search

aster

SkillWorks with Claude CodeGitHub

Pointer to the canonical aster agent skill in skills/aster/. Use when an agent must define a parameterized antenna design space, run dry or real AEDT-backed design studies through a guarded solver, keep measured artifacts as evidence, apply explicit bandwidth/pattern acceptance rules, or re-score recorded runs without re-solving. The web GUI is not included; real runs require the ansys-aedt-mcp guard plus AEDT 2026 R1.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today

Check it deeper on your machine

It has changed since its scan on 21 Nov 2026.

As a Claude Code plugin, install it and then ask Claude Code:

/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/Hawse1337/aster with scanskillsafety

Or from a terminal, clone it and run it:

git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/Hawse1337/aster'

It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.

Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/hawse1337--aster/badge.svg)](/listings/hawse1337--aster)

HTML

<a href="/listings/hawse1337--aster"><img src="/api/listings/hawse1337--aster/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

SKILL.md · Manifest · 18 lines
  1. ---
  2. name: aster
  3. description: Pointer to the canonical aster agent skill in skills/aster/. Use when an agent must define a parameterized antenna design space, run dry or real AEDT-backed design studies through a guarded solver, keep measured artifacts as evidence, apply explicit bandwidth/pattern acceptance rules, or re-score recorded runs without re-solving. The web GUI is not included; real runs require the ansys-aedt-mcp guard plus AEDT 2026 R1.
  4. ---
  5. # aster skill
  6. The canonical skill (with `references/` and `scripts/`) lives in
  7. [`skills/aster/`](skills/aster/SKILL.md).
  8. Install it into an agent's skill directory:
  9. ```powershell
  10. aster skill install # → %USERPROFILE%\.dsh\skills\aster
  11. ```
  12. Or copy `skills/aster` there manually. Full documentation: [README.md](README.md) ·
  13. [user_doc/](user_doc/README.md) · [https://hawse1337.github.io/aster/](https://hawse1337.github.io/aster/)
README.md · README · 171 lines
  1. <p align="center">
  2. <img src="assets/banner.svg" alt="aster — an antenna design bench, evidence first" width="100%">
  3. </p>
  4. <p align="center">
  5. <a href="https://github.com/Hawse1337/aster/actions/workflows/ci.yml"><img alt="tests" src="https://github.com/Hawse1337/aster/actions/workflows/ci.yml/badge.svg"></a>
  6. <a href="https://github.com/Hawse1337/aster/releases/latest"><img alt="release" src="https://img.shields.io/github/v/release/Hawse1337/aster?color=e4572e"></a>
  7. <a href="https://hawse1337.github.io/aster/"><img alt="docs" src="https://img.shields.io/badge/docs-online-2a9d8f"></a>
  8. <a href="LICENSE"><img alt="license: MIT" src="https://img.shields.io/badge/license-MIT-2a9d8f"></a>
  9. <img alt="python 3.10+" src="https://img.shields.io/badge/python-3.10%2B-23262b">
  10. </p>
  11. # Keep the measurement. Change the target.
  12. > **aster** was previously published as **antopt**. The package import, CLI and
  13. > environment prefix are now `aster` / `ASTER_*`; the old repository URL redirects.
  14. `aster` is a design bench for antenna studies. You describe a parameter space and what "good"
  15. means, the library drives candidates through a guarded AEDT session, and every solve leaves its raw
  16. artifacts behind. When the requirement changes — a different band, a tighter ripple, a flatter
  17. elevation cut — you re-judge the history instead of burning another night of solver time.
  18. > **中文简介**:[README.zh-CN.md](README.zh-CN.md)
  19. > The web GUI / desktop application is under validation and is **not** part of this repository.
  20. ![The five-station loop](assets/loop.svg)
  21. ## Three forms, one bench
  22. | form | how you get it | use it when |
  23. |---|---|---|
  24. | **Python library + CLI** | wheel/sdist from [Releases](https://github.com/Hawse1337/aster/releases), then `aster doctor` | you script your own loop, run CI, or work in a notebook |
  25. | **Agent skill** | `aster skill install` (or copy `skills/aster/`) | an AI agent should run design studies with evidence rules |
  26. | **Docs + releases** | [hawse1337.github.io/aster](https://hawse1337.github.io/aster/) | you want the contract, the workflow and pinned artifacts |
  27. ## The bench
  28. Four verbs, one loop:
  29. - **Design** — `ParamSpec` / `ParamSpace` describe the knobs, `Objective` / `Constraint` describe the
  30. target. Nothing here knows about AEDT.
  31. - **Solve** — a candidate becomes a real run through the companion guard
  32. ([ansys-aedt-mcp](https://github.com/Hawse1337/ansys-aedt-mcp)). Sessions are addressed explicitly;
  33. budgets are spent, not assumed.
  34. - **Keep** — S11 Touchstone, far-field grids and native report images stay with the run record. A
  35. number without its artifact is a rumour.
  36. - **Judge** — acceptance rules are code (`band_acceptance`, `pattern_acceptance`, `acceptance`), so a
  37. verdict can be recomputed, compared and challenged.
  38. The archive is the point. A *campaign* is just a Python recipe over that loop; swap the evaluator
  39. (dry model or real solve) and the same recipe still runs.
  40. ## What it refuses to hide
  41. | risk | how aster handles it |
  42. |---|---|
  43. | "the result looks great" | every measured run keeps `result.s1p`, `farfield_views.json` and the native report PNGs |
  44. | "we changed the target, re-run everything" | records are re-scored; the solver is not called again unless you ask |
  45. | "the surrogate says it is good" | dry/surrogate results are labelled `PREDICTED`; validation state is explicit |
  46. | "the solve died, we lost the point" | failed runs are recorded as failed, with the reason, not dropped |
  47. | "which AEDT session was that?" | the guard requires one explicit PID or gRPC port per call |
  48. ## Try it in one minute
  49. ```powershell
  50. py -3.10 -m venv .venv
  51. .\.venv\Scripts\python.exe -m pip install -U pip
  52. .\.venv\Scripts\python.exe -m pip install -e ".[optimizer,surrogate,plot]"
  53. aster version
  54. aster doctor # what is missing before a real campaign
  55. aster dry-demo --samples 64
  56. ```
  57. `dry-demo` is a complete study on an analytic objective — Latin-hypercube design, Pareto archive,
  58. no AEDT required. The same shape in code:
  59. ```python
  60. from aster.core import Objective, ParamSpace, ParamSpec, latin_hypercube
  61. from aster.optimize import Evaluation, pareto_archive
  62. space = ParamSpace([
  63. ParamSpec("ring_radius", "mm", 20.0, 60.0, 40.0),
  64. ParamSpec("ring_height", "mm", 1.0, 10.0, 4.0),
  65. ])
  66. objectives = [Objective("gain", "peak_gain", "maximize"),
  67. Objective("bw", "s11_bandwidth", "maximize")]
  68. runs = [Evaluation("c%02d" % i, "ring", p,
  69. metrics={"peak_gain": predict_gain(p),
  70. "s11_bandwidth": predict_bw(p)}, feasible=True)
  71. for i, p in enumerate(latin_hypercube(space, 32, seed=1))]
  72. front = pareto_archive(runs, objectives)
  73. ```
  74. ## Runtime safety, by construction
  75. Real solves go through the companion guard
  76. [ansys-aedt-mcp](https://github.com/Hawse1337/ansys-aedt-mcp), not through a loose PyAEDT call in
  77. the same process:
  78. - the guard records the AEDT sessions **it** launched and refuses to attach to unmanaged ones
  79. (`guard_status` classifies every live `ansysedt.exe`);
  80. - `run_python_code` / `run_python_script` are refused by default at the guard's MCP and worker
  81. layers; a human operator can enable them for a supervised session;
  82. - run tokens bind analysis submissions to project/design/setup when
  83. `AEDT_GUARD_ENFORCE=1`;
  84. - launch/release events are audited and PyAEDT app objects are checked against the verified desktop.
  85. If the guard MCP tools are missing, **stop** — do not fall back to shell-level PyAEDT or
  86. `ansysedt.exe`. Fail-closed DSH/Codex configurations and the threat model are in the guard repo.
  87. See [user_doc/safety.md](user_doc/safety.md) for the boundary and residual risks.
  88. ## Real studies
  89. 1. Install the guard system and its virtual environment (PyAEDT 1.10.0, AEDT 2026 R1).
  90. 2. Point `ASTER_AEDT_EXE`, `ASTER_GUARD_REPO`, `ASTER_VENV_PYTHON`,
  91. `ASTER_REFERENCE_PROJECT`, `ASTER_CAMPAIGN_ROOT` at your machine.
  92. 3. Run the worker against a campaign directory; each candidate gets its own run folder and archive
  93. row.
  94. The contract, the run lifecycle and the artifact layout are in
  95. [user_doc/aedt_integration.md](user_doc/aedt_integration.md), with a walkthrough in
  96. [examples/aedt_campaign.md](examples/aedt_campaign.md).
  97. ## Drop it into an agent
  98. The skill lives in [`skills/aster/`](skills/aster/): `SKILL.md` plus `references/` (API map, AEDT
  99. contract, evidence rules) and a runnable `scripts/dry_demo.py`. Install it with one command:
  100. ```powershell
  101. aster skill install # → %USERPROFILE%\.dsh\skills\aster
  102. aster skill path # print the destination
  103. ```
  104. Or copy `skills/aster/` into your agent's skill directory by hand. The skill does **not** cover the
  105. GUI, which is not published.
  106. ## Repository map
  107. ```text
  108. assets/ banner + loop illustrations
  109. aster/ the library
  110. core.py parameter spaces, objectives, constraints
  111. optimize.py evaluations, dominance, Pareto archive
  112. campaign.py campaign recipes
  113. runtime/ measured-run manager + job store (no web server)
  114. worker.py command-line measured campaign worker
  115. aedt_host.py AEDT process helpers
  116. skills/aster/ bundled skill (mirrored from skills/aster at build time)
  117. cases/ benchmark/ interop/ optimizer/ parametric/ physics/ surrogate/ topology/
  118. skills/aster/ canonical agent skill (SKILL.md + references + scripts)
  119. tools/ sync_skill_bundle.py (mirror the skill into the package)
  120. user_doc/ installation, architecture, workflow, AEDT integration, skill, validation
  121. examples/ dry study + measured-campaign walkthrough
  122. tests/ offline suite (no AEDT needed)
  123. mkdocs.yml documentation site
  124. ```
  125. ## Status
  126. - Offline suite: **782 passed, 80 subtests**; CI runs it on Windows / CPython 3.12.
  127. - Measured runs are exercised on AEDT 2026 R1 through the guard; any solver number quoted from a
  128. study must be accompanied by its run artifacts.
  129. - Wheel and sdist: [v1.54.0 release](https://github.com/Hawse1337/aster/releases/tag/v1.54.0);
  130. documentation: [hawse1337.github.io/aster](https://hawse1337.github.io/aster/).
  131. ## License
  132. MIT — see [LICENSE](LICENSE). If you build a study on top of this bench, keep the artifacts; a bench
  133. without evidence is just furniture.

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.