Load mandatory SolidWorks conventions, design rules, task-relevant knowledge documents, standards data, and initial design-rule checks before any modeling or CAD code.

Apache-2.0Auto-check passed

Install Sw Pre Start

skills CLI
$ npx skills add hashgraph-online/awesome-codex-plugins --skill sw-pre-start -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install hashgraph-online/awesome-codex-plugins sw-pre-start --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/hashgraph-online/awesome-codex-plugins.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/Erfouni/solidworks-GPT-plugin/plugins/solidworks-gpt-plugin/skills/sw-pre-start .claude/skills/sw-pre-start && rm -rf skills-src

Use ~/.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/

Facts

Skill name
sw-pre-start
GitHub stars
1.3k
Token cost
~1.8k tokens
SKILL.md length
869 words
Files
2
Skills in repo
716
Repo updated
First seen
Licence
Apache-2.0

At a glance

Load mandatory SolidWorks conventions, design rules, task-relevant knowledge documents, standards data, and initial design-rule checks before any modeling or CAD code.

  • Works in 7 steps: non-negotiable engineering requirement… → conventions → active design rules → …
  • SKILL.md covers Phase 0: non-negotiable…, Phase 1: conventions, Phase 2: active design rules and Phase 3: task knowledge, plus 4 more sections
  • Reaches sw-plugin.ideep.org

What it does

Sw Pre Start is an agent skill from hashgraph-online/awesome-codex-plugins. Load mandatory SolidWorks conventions, design rules, task-relevant knowledge documents, standards data, and initial design-rule checks before any modeling or CAD code. Use at the beginning of every SolidWorks create, modify, repair, assembly, drawing, or API task, before touching SolidWorks; also use its final phase before save and export.

Its SKILL.md is about 1.8k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).

The repository describes itself as: A curated list of awesome OpenAI Codex / ChatGPT plugins, skills, and resources. The 1 Codex Marketplace. See live plugins at: https://hol.org/plugins/best-codex-plugins. The licence is Apache-2.0.

Example prompts

  • “/sw-pre-start”

Workflow steps

7 steps, taken from the step headings in SKILL.md.

  1. non-negotiable engineering requirement (ENG-001)
  2. conventions
  3. active design rules
  4. task knowledge
  5. initial rule check
  6. standards on demand
  7. final rule check

What it can do on your machine

Read from SKILL.md and the folder at commit 3e1456a. 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

    No scripts in the folder and no shell commands in SKILL.md (its code samples are json).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • sw-plugin.ideep.org

    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

Sw Pre Start loads about 1.8k tokens when it runs. Until then it costs about 89 tokens; SKILL.md has 869 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~89
When it runs · the whole SKILL.md, loaded when a task matches
~1.8k

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 hashgraph-online/awesome-codex-plugins at commit 3e1456a, republished under its Apache-2.0 licence (© hashgraph-online). 869 words, ~1,833 tokens.

Download SKILL.mdSave it as .claude/skills/sw-pre-start/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
sw-pre-start
description
Load mandatory SolidWorks conventions, design rules, task-relevant knowledge documents, standards data, and initial design-rule checks before any modeling or CAD code. Use at the beginning of every SolidWorks create, modify, repair, assembly, drawing, or API task, before touching SolidWorks; also use its final phase before save and export.

SolidWorks Pre-Start

Run all phases in order. Do not model, generate CAD code, or call a SolidWorks API until Phases 1 through 4 complete or a documented KB outage forces the offline fallback.

Phase 0: non-negotiable engineering requirement (ENG-001)

This phase has no network dependency and is exempt from the offline fallback. The KB carries the same rule as a convention, but a documented outage must never be the reason it stops applying.

Do not create schematic, decorative, conceptual, simplified, placeholder, or visually representative components.

Every component must be a real, functional, manufacturable, technically accurate part. No component - regardless of size or importance - may be created merely for visual representation.

For every individual component, including a single screw:

  1. Research it against reliable technical sources: peer-reviewed papers, engineering references, manufacturer documentation, and the latest applicable standards.
  2. Design from validated research - engineering principles, formulas, calculations, material properties, manufacturing constraints, tolerances, and safety requirements.
  3. Justify every value. Dimensions, geometries, connections, interfaces, loads, clearances, fasteners, materials and mechanical properties must all be realistic and technically defensible.
  4. Never invent. No assumptions, invented specifications, arbitrary dimensions, fake mechanisms, or purely visual detail.
  5. Cite the standards, formulas, calculations and references used for each part.

Model every physical component separately. If an assembly contains 10,000 parts, all 10,000 are researched, engineered and modelled individually. No group of parts may be replaced by a simplified block, visual shell, placeholder, texture, or symbolic representation. This covers screws, nuts, washers, bearings, seals, cables, connectors, welds, joints, gears, springs, housings, electronic components and internal mechanisms alike.

The finished design must be fully functional, physically realistic, engineering-accurate, dimensionally consistent, manufacturable, properly assembled, based on validated calculations, compliant with the latest applicable standards, and free of decorative, fictional or representational parts.

When the information is not available

If sufficient technical information or reliable references are unavailable for a component, do not fabricate or guess. State plainly what is missing and what must be researched or specified before that component can be designed accurately.

Stopping to ask is the correct outcome. A plausible-looking part built from invented numbers is a failure, not a partial success - it looks finished and will therefore be trusted.

An offline KB makes this more likely to be the right answer, not less: losing the standards tables means less grounding for a dimension, never permission to invent one.

Set KB_HOST from SW_KB_HOST; default to https://sw-plugin.ideep.org. Use curl through the shell for every runtime request. Quote the complete URL. Do not use browser or web-fetch tools for this KB.

On Windows, run curl.exe instead of curl: in Windows PowerShell 5.1 curl is an alias for Invoke-WebRequest, which rejects curl options such as -sS. curl.exe is the real curl in every Windows shell.

Phase 1: conventions

Run:

text
curl -sS "{KB_HOST}/api/knowledge?kind=convention"

Load every returned body once per Codex task. Treat conventions as hard rules unless the user explicitly overrides one. Read Persian and English documents. Expect conventions for metric units, ISO 2768-mK defaults, material defaults, fully-defined parametric sketches, PRJ-<part>-NNN naming, work/ and exports/ paths, clean rebuilds, assigned material, rule checks, STEP, and drawing PDF deliverables.

If required geometry or safety input remains unknown, ask the user; a KB default does not authorize inventing geometry-driving values.

Show full SKILL.md (336 more words)Show less

Phase 2: active design rules

Run:

text
curl -sS "{KB_HOST}/api/design-rules"

Skip entries with deprecated: true. Internalize the rest by category. Enforce severity as follows:

  • critical: block until resolved;
  • high: fix before completion;
  • medium: fix unless the user explicitly overrides;
  • low: advisory, apply when possible.

Phase 3: task knowledge

Create a concise URL-encoded query for the requested component and likely SolidWorks features, then run:

text
curl -sS "{KB_HOST}/api/knowledge/search?q={query}"

Read the top five to eight results, or up to ten for a complex assembly, thread, or sheet-metal task. Prioritize playbook, then reference, strategy, and convention. Read the complete reference for every SolidWorks API method about to be used. Fetch a known document with GET /api/knowledge/{slug} when necessary.

Phase 4: initial rule check

Build a JSON object from known values. Omit unknown keys; never fabricate them. Typical fields are:

json
{
  "welded": false,
  "tolerance_class": "m",
  "process": "machined_aluminum",
  "wall_thickness_mm": 2.0,
  "nominal_dimension_mm": 50.0,
  "fastener": "M8",
  "hole_mm": 9.0,
  "material": "6061-T6"
}

POST it with curl:

text
curl -sS -X POST "{KB_HOST}/api/check-context" -H "Content-Type: application/json" --data-binary "@<context.json>"

React to each result:

  • pass: continue;
  • fail: stop CAD work and fix the input, explaining the rule and change;
  • warn: flag it and fix when possible;
  • advisory: apply it as a design constraint;
  • na: ignore it.

Do not proceed while summary.fail is greater than zero.

Phase 5: standards on demand

Query only the table needed for the current decision:

  • GET /api/standards/materials[/<name>] for density, yield, and modulus;
  • GET /api/standards/fits for ISO 286 hole and shaft deviations;
  • GET /api/standards/clearance_holes[/<designation>] for ISO 273 holes;
  • GET /api/standards/tolerances_iso2768 for general tolerances;
  • GET /api/standards/fasteners[/<designation>] for fastener geometry;
  • GET /api/standards/sheet_metal_gauges for gauge thickness;
  • GET /api/standards/preferred_numbers for R-series dimensions.

Record units. The KB database convention is mm, MPa, and g/cm3.

Phase 6: final rule check

After geometry is complete and before final save or export, POST a more complete final context to /api/check-context. Resolve every fail; document all advisories in the session issues narrative.

Offline and error behavior

  • Unreachable server: record KB offline - proceeding without pre-start checks and continue using verified engineering context.
  • Search 404: continue with available knowledge.
  • Check-context 422: retry once with fewer fields, then continue and record the issue.
  • 5xx or timeout: skip the failed phase and record it.

The KB accelerates the task; it is not a gatekeeper.

© hashgraph-online, 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 1 other file in plugins/Erfouni/solidworks-GPT-plugin/plugins/solidworks-gpt-plugin/skills/sw-pre-start of hashgraph-online/awesome-codex-plugins.

  • SKILL.md
  • agents/openai.yaml

Open the folder on GitHubat commit 3e1456a

Compare with similar skills

Sw Pre Start 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.

Sw Pre Start compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Sw Pre Start this skillhashgraph-online/awesome-codex-plugins1.3k—~1.8kAutomated safety check: PassApache-2.0
Ecc Conventionsaffaan-m/ECC276k—~2.8kAutomated safety check: PassMIT
Conventional Commit Reviewaffaan-m/ECC276k—~1.2kAutomated safety check: PassMIT
Naming Conventionsthedaviddias/Front-End-Checklist74k—~481Automated safety check: PassMIT
Conventional CommitJanDeDobbeleer/oh-my-posh24k—~1.2kAutomated safety check: NotesMIT
Backend Conventionsgetsentry/sentry46k—~1.3kAutomated safety check: PassCustom licence

Similar skills

  • Ecc Conventions

    affaan-m/ECC

    Development conventions and patterns for ECC. An agent skill from affaan-m/ECC.

    276k GitHub stars~2.8k tokensUpdated yesterday
    DevelopmentAuto-check passed
  • Reviews staged changes and drafts a Conventional Commits-compliant commit message with the right type, scope, and length.

    276k GitHub stars~1.2k tokensUpdated yesterday
    DevelopmentAuto-check passed
  • Naming Conventions

    thedaviddias/Front-End-Checklist

    A skill your agent uses when reviewing stylesheets, component styles, and responsive behavior related to Use consistent CSS naming conventions.

    74k GitHub stars~481 tokensUpdated 4 days ago
    Frontend & DesignAuto-check passed
  • Conventional Commit

    JanDeDobbeleer/oh-my-posh

    Workflow for generating conventional commit messages following the Conventional Commits specification.

    24k GitHub stars~1.2k tokensUpdated today
    DevelopmentAuto-check: notes
  • Backend Conventions

    getsentry/sentry

    Official

    Sentry backend conventions for logging, tracing/spans, span/tag attribute naming, metrics tags, and the options system.

    46k GitHub stars~1.3k tokensUpdated yesterday
    Auto-check passed
  • Conventional Commit

    github/awesome-copilot

    Official

    Prompt and workflow for generating conventional commit messages using a structured XML format.

    40k GitHub starsUsed in 1 repo~662 tokens
    DevelopmentAuto-check passed

More from hashgraph-online/awesome-codex-plugins

All 716 skills in this repo
  • Anime Reaction Gif

    hashgraph-online/awesome-codex-plugins

    Create original anime-style reaction stickers as looping GIFs and MP4 previews, using generated character pose sheets and timed key poses.

    1.3k GitHub stars~922 tokensUpdated today
    Auto-check passed
  • Calibredb

    hashgraph-online/awesome-codex-plugins

    Manage and query Calibre libraries with the calibredb CLI (local paths or Calibre Content server URLs).

    1.3k GitHub stars~1k tokensUpdated today
    Auto-check passed
  • Rust API Test Harness

    hashgraph-online/awesome-codex-plugins

    A skill your agent uses when adding, changing, testing, or debugging Rust HTTP APIs and services, especially when Codex needs black-box integration tests, random-port app startup, real database test…

    1.3k GitHub stars~1.7k tokensUpdated today
    Auto-check passed
  • Art

    hashgraph-online/awesome-codex-plugins

    Make a studio's game look like something at build time — a cover from a real frame of the game (free), painted covers, backdrops, textures and character plates from image models through the…

    1.3k GitHub stars~2.4k tokensUpdated today
    Auto-check passed
  • Calle

    hashgraph-online/awesome-codex-plugins

    Use CALL-E from Codex through the calle CLI. An agent skill from hashgraph-online/awesome-codex-plugins.

    1.3k GitHub stars~2.9k tokensUpdated today
    Auto-check passed
  • Game Balance Economy

    hashgraph-online/awesome-codex-plugins

    Balance game difficulty, resources, rewards, probability, progression, economies, and dominant strategies.

    1.3k GitHub stars~618 tokensUpdated today
    Auto-check passed

Questions about Sw Pre Start

What does Sw Pre Start do?

Load mandatory SolidWorks conventions, design rules, task-relevant knowledge documents, standards data, and initial design-rule checks before any modeling or CAD code. Sw Pre Start is an agent skill from hashgraph-online/awesome-codex-plugins. Load mandatory SolidWorks conventions, design rules, task-relevant knowledge documents, standards data, and initial design-rule checks before any modeling or CAD code.

How do I install Sw Pre Start in Claude Code?

Run `npx skills add hashgraph-online/awesome-codex-plugins --skill sw-pre-start -a claude-code`. Or copy the skill folder (plugins/Erfouni/solidworks-GPT-plugin/plugins/solidworks-gpt-plugin/skills/sw-pre-start in hashgraph-online/awesome-codex-plugins) into .claude/skills/sw-pre-start in your project. Claude Code loads it when a task matches its description.

How do I install Sw Pre Start in Codex?

Run `npx skills add hashgraph-online/awesome-codex-plugins --skill sw-pre-start -a codex`. Or copy the skill folder (plugins/Erfouni/solidworks-GPT-plugin/plugins/solidworks-gpt-plugin/skills/sw-pre-start in hashgraph-online/awesome-codex-plugins) into .agents/skills/sw-pre-start in your project. Codex loads it when a task matches its description.

Can I use Sw Pre Start 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 hashgraph-online/awesome-codex-plugins --skill sw-pre-start -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/sw-pre-start, .gemini/skills/sw-pre-start, .github/skills/sw-pre-start and .opencode/skills/sw-pre-start in your project.

What does Sw Pre Start need to run?

SKILL.md names no scripts, command-line tools or credentials: Sw Pre Start is instructions for the agent only.

Does Sw Pre Start access the network?

SKILL.md names 1 domain. In commands or code: sw-plugin.ideep.org; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is Sw Pre Start 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 Sw Pre Start use?

Sw Pre Start 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 Sw Pre Start use?

About 1.8k tokens (SKILL.md is roughly 7.3k 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 Sw Pre Start?

Skills that share tags, products or a category with Sw Pre Start: Ecc Conventions (affaan-m/ECC, 276k stars), Conventional Commit Review (affaan-m/ECC, 276k stars), Naming Conventions (thedaviddias/Front-End-Checklist, 74k stars) and Conventional Commit (JanDeDobbeleer/oh-my-posh, 24k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Sw Pre Start?

hashgraph-online (a GitHub organization) maintains it in hashgraph-online/awesome-codex-plugins, which has 1,267 GitHub stars. The repository holds 716 skills in this directory. The repository was last updated on October 10, 2026.

Source: hashgraph-online/awesome-codex-plugins on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.