Reconstruct a complete consent-ready FeedbackSubmission from the entire current SolidWorks task, including corrected build instructions, every final code artifact, reproducible errors and fixes…

Apache-2.0Auto-check passed

Install Sw Learner

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

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

GitHub CLI
$ gh skill install hashgraph-online/awesome-codex-plugins sw-learner --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-learner .claude/skills/sw-learner && 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-learner
GitHub stars
1.2k
Token cost
~1.3k tokens
SKILL.md length
651 words
Files
2
Skills in repo
736
Repo updated
First seen
Licence
Apache-2.0

At a glance

Reconstruct a complete consent-ready FeedbackSubmission from the entire current SolidWorks task, including corrected build instructions, every final code artifact, reproducible errors and fixes…

  • Works in 5 steps: Confirm relevance and session → Resolve the part → Collect eligible images → …
  • Non-SolidWorks conversations
  • SKILL.md covers 1. Confirm relevance and session, 2. Resolve the part, 3. Collect eligible images and 4. Build FeedbackSubmission, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Sw Learner is an agent skill from hashgraph-online/awesome-codex-plugins. Reconstruct a complete consent-ready FeedbackSubmission from the entire current SolidWorks task, including corrected build instructions, every final code artifact, reproducible errors and fixes, lessons, and eligible images. Use throughout SolidWorks work for tracking and invoke at the end through sw-session-reporter; do not use for non-SolidWorks conversations.

Its SKILL.md is about 1.3k 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.

When your agent uses it

  • Non-SolidWorks conversations

Example prompts

  • “/sw-learner”

Requirements

  • Python 3

Workflow steps

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

  1. Confirm relevance and session
  2. Resolve the part
  3. Collect eligible images
  4. Build FeedbackSubmission
  5. Validate and persist privately

What it can do on your machine

Read from SKILL.md and the folder at commit 16b4156. 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.

    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

Sw Learner loads about 1.3k tokens when it runs. Until then it costs about 94 tokens; SKILL.md has 651 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~94
When it runs · the whole SKILL.md, loaded when a task matches
~1.3k

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 16b4156, republished under its Apache-2.0 licence (© hashgraph-online). 651 words, ~1,306 tokens.

Download SKILL.mdSave it as .claude/skills/sw-learner/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
sw-learner
description
Reconstruct a complete consent-ready FeedbackSubmission from the entire current SolidWorks task, including corrected build instructions, every final code artifact, reproducible errors and fixes, lessons, and eligible images. Use throughout SolidWorks work for tracking and invoke at the end through sw-session-reporter; do not use for non-SolidWorks conversations.

SolidWorks Learner

Track the session from the first SolidWorks message. When invoked, reread the entire Codex task and rebuild the complete current payload, not a delta. Keep only corrected final versions.

Never show the raw payload, base64 images, or full submission JSON to the user.

1. Confirm relevance and session

If no SolidWorks modeling, API calls, CAD code, design decisions, or debugging occurred, return an internal skip result and stop.

Read .sw-learner-state.json in the CAD working directory and require a non-empty fixed sessionId. If it is missing, resolve the plugin root and run scripts/sw_session.py start once, then keep that UUID for the rest of the task.

2. Resolve the part

Use quoted curl and the configured SW_KB_HOST default to query:

text
GET /api/parts?q={encoded-part-identifier}&pageSize=20

Record the best exact or close partId; use null when none exists. Preserve the known partNumber.

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.

3. Collect eligible images

Find images referenced by generated code (SaveBMP, ExportBMP, SaveAs, or paths ending in .png, .jpg, .jpeg, .bmp, .tiff, .tif, .gif) and images actually shown in the task. Include only existing readable files under 10 MB. Deduplicate by filename and encode bytes as base64.

Use MIME types image/png, image/jpeg, image/bmp, image/tiff, or image/gif. Convert Windows paths to accessible host paths when working through WSL.

4. Build FeedbackSubmission

Follow ../../schemas/feedback-submission.schema.json. Always include:

  • issues: a two-to-five sentence narrative of what was built, the approach, mistakes fixed, validation, and final state;
  • sessionId: the fixed ID for this Codex task;
  • partId: the matched UUID or null when useful.

Add arrays only when they contain at least one item. Omit empty arrays entirely.

Classification hints

You know what you were asked to build. The reviewer sees only the resulting code and renders, and has to work backwards from them. Pass that knowledge forward so they confirm rather than deduce:

  • suggestedCategory: an exact category name from GET {SW_KB_HOST}/api/categories. Fetch the list; never invent a name. Use "Uncategorised" when nothing fits — reviewers create categories, agents do not.
  • suggestedPartName: short descriptive name including the defining dimension, e.g. "Cardan yoke, 30mm bore".
  • suggestedPartNumber: the part number when the user gave one or the catalog lookup in step 3 matched. Omit it rather than invent one — a fabricated part number is worse than none.

All three are optional; omit any you cannot infer, and never send an empty string. They are advisory: nothing is published on their strength, and partId is still set only by an explicit reviewer action, so a wrong guess costs nothing.

Show full SKILL.md (214 more words)Show less
Instructions

Include exact ordered build steps with the SolidWorks version, material, final feature order, real parameter values, API calls, validation, and exports. Skip generic steps that add no reusable knowledge.

Macros

Include every code artifact written in the task: Python, VBA, or SWAPI. Store the full verbatim final working source, never a summary or truncated excerpt. Required macro fields are name, language, and code. Add description, swFeaturesUsed, parameters, template flag, version, and part ID when known.

Known errors

Include only concrete failures with the exact return value or error, affected SolidWorks method, and a resolution that actually worked. Exclude typos, immediately-fixed syntax mistakes, vague symptoms, and non-SolidWorks issues.

Use severity critical for total failure, high for plausible but wrong output, medium for a caught and repaired failure, and low for minor inconvenience.

Lessons

Include non-obvious lessons demonstrated in this task, from successes and failures. Every lesson needs category, title, whatHappened, rootCause, prevention, and severity. Make prevention a concrete rule, never merely be careful.

5. Validate and persist privately

Write the payload to .sw-feedback-payload.json in the CAD working directory only when persistence is needed across the consent turn. Ensure it is ignored by version control. Validate it with:

text
python <plugin-root>/scripts/validate_feedback.py .sw-feedback-payload.json
python <plugin-root>/scripts/sw_session.py mark-payload --part-id <uuid-or-null> --part-number <value>

Increment payloadVersion on every rebuild. Replace earlier payload content; do not accumulate stale or broken code versions.

© 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-learner of hashgraph-online/awesome-codex-plugins.

  • SKILL.md
  • agents/openai.yaml

Open the folder on GitHubat commit 16b4156

Compare with similar skills

Sw Learner 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 Learner compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Sw Learner this skillhashgraph-online/awesome-codex-plugins1.2k—~1.3kAutomated safety check: PassApache-2.0
Cookie Consentthedaviddias/Front-End-Checklist74k—~637Automated safety check: PassMIT
Consent Modethedaviddias/Front-End-Checklist74k—~425Automated safety check: PassMIT
Written Consentanthropics/claude-for-legal9.6k2 repos~5.1kAutomated safety check: PassApache-2.0
Detecting Suspicious OAuth Application Consentmukul975/Anthropic-Cybersecurity-Skills34k—~605Automated safety check: PassApache-2.0
Consent Registryaaron-he-zhu/aaron-marketing-skills2.9k2 repos~2kAutomated safety check: PassApache-2.0

Similar skills

  • Cookie Consent

    thedaviddias/Front-End-Checklist

    A skill your agent uses when reviewing a website for GDPR/CCPA compliance, specifically whether cookie consent is obtained before non-essential cookies are set.

    74k GitHub stars~637 tokensUpdated yesterday
    Legal & ComplianceAuto-check passed
  • Consent Mode

    thedaviddias/Front-End-Checklist

    A skill your agent uses when auditing slow page loads, heavy assets, or rendering delays related to Implement Google Consent Mode v2.

    74k GitHub stars~425 tokensUpdated yesterday
    Frontend & DesignAuto-check passed
  • Written Consent

    anthropics/claude-for-legal

    Official

    Draft a unanimous written consent of the board or a committee in house format, with precedent search from the consents repository.

    9.6k GitHub starsUsed in 2 repos~5.1k tokens
    Legal & ComplianceAuto-check passed
  • Detecting Suspicious OAuth Application Consent

    mukul975/Anthropic-Cybersecurity-Skills

    Detect risky OAuth application consent grants in Azure AD / Microsoft Entra ID using Microsoft Graph API, audit logs, and permission analysis to identify illicit consent grant attacks.

    34k GitHub stars~605 tokensUpdated 1 mo ago
    Backend & APIsAuto-check passed
  • Consent Registry

    aaron-he-zhu/aaron-marketing-skills

    A skill your agent uses when the user asks to "log this subscriber's opt-in", record unsubscribes/complaints, or query lawful basis; curates pseudonymous consent facts through the append-only…

    2.9k GitHub starsUsed in 2 repos~2k tokens
    Marketing & SEOAuto-check passed
  • Performing Timeline Reconstruction With Plaso

    mukul975/Anthropic-Cybersecurity-Skills

    Builds comprehensive forensic super-timelines using Plaso (log2timeline and psort) to correlate events across file system metadata, event logs, browser history, and registry artifacts into a unified…

    34k GitHub stars~3k tokensUpdated 1 mo ago
    SecurityAuto-check: notes

More from hashgraph-online/awesome-codex-plugins

All 736 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.

    1.2k GitHub stars~922 tokensUpdated yesterday
    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).

    1.2k GitHub stars~1k tokensUpdated yesterday
    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…

    1.2k GitHub stars~1.7k tokensUpdated yesterday
    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…

    1.2k GitHub stars~2.4k tokensUpdated yesterday
    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.

    1.2k GitHub stars~2.9k tokensUpdated yesterday
    Auto-check passed
  • Game Balance Economy

    hashgraph-online/awesome-codex-plugins

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

    1.2k GitHub stars~618 tokensUpdated yesterday
    Auto-check passed

Questions about Sw Learner

What does Sw Learner do?

Reconstruct a complete consent-ready FeedbackSubmission from the entire current SolidWorks task, including corrected build instructions, every final code artifact, reproducible errors and fixes…. Sw Learner is an agent skill from hashgraph-online/awesome-codex-plugins. Reconstruct a complete consent-ready FeedbackSubmission from the entire current SolidWorks task, including corrected build instructions, every final code artifact, reproducible errors and fixes, lessons, and eligible images.

When should I use Sw Learner?

Sw Learner fits situations like: non-SolidWorks conversations.

How do I install Sw Learner in Claude Code?

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

How do I install Sw Learner in Codex?

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

Can I use Sw Learner 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-learner -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-learner, .gemini/skills/sw-learner, .github/skills/sw-learner and .opencode/skills/sw-learner in your project.

What does Sw Learner need to run?

SKILL.md names no scripts, command-line tools or credentials: Sw Learner is instructions for the agent only. Our summary lists: Python 3.

Does Sw Learner 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 Sw Learner 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 Learner use?

Sw Learner 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 Learner use?

About 1.3k tokens (SKILL.md is roughly 5.2k 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 Learner?

Skills that share tags, products or a category with Sw Learner: Cookie Consent (thedaviddias/Front-End-Checklist, 74k stars), Consent Mode (thedaviddias/Front-End-Checklist, 74k stars), Written Consent (anthropics/claude-for-legal, 9.6k stars) and Detecting Suspicious OAuth Application Consent (mukul975/Anthropic-Cybersecurity-Skills, 34k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Sw Learner?

hashgraph-online (a GitHub organization) maintains it in hashgraph-online/awesome-codex-plugins, which has 1,232 GitHub stars. The repository holds 736 skills in this directory. The repository was last updated on October 6, 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.