Brief
alirezarezvani/claude-skills
/cs:brief <topic — Generate a one-page strategy brief from an office-hours intake.
Turn measured design briefs or existing parts into editable FreeCAD projects with checked dimensions, bores, clearances, interference and fastener access; deliver separate STEP/STL parts, reference…
$ npx skills add autonomous-ai/openharness --skill freecad -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install autonomous-ai/openharness freecad --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/autonomous-ai/openharness.git skills-src && mkdir -p .claude/skills && cp -r skills-src/store/agents/freecad/skills/freecad .claude/skills/freecad && 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 "freecad" agent skill from https://github.com/autonomous-ai/openharness/tree/main/store/agents/freecad/skills/freecad into .claude/skills/freecad/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "freecad", 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/autonomous-ai/openharness/tree/main/store/agents/freecad/skills/freecadType 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 autonomous-ai/openharness --skill freecad -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install autonomous-ai/openharness freecad --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/autonomous-ai/openharness.git skills-src && mkdir -p .agents/skills && cp -r skills-src/store/agents/freecad/skills/freecad .agents/skills/freecad && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "freecad" agent skill from https://github.com/autonomous-ai/openharness/tree/main/store/agents/freecad/skills/freecad into .agents/skills/freecad/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "freecad", 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 autonomous-ai/openharness --skill freecad -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install autonomous-ai/openharness freecad --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/autonomous-ai/openharness.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/store/agents/freecad/skills/freecad .cursor/skills/freecad && 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 "freecad" agent skill from https://github.com/autonomous-ai/openharness/tree/main/store/agents/freecad/skills/freecad into .cursor/skills/freecad/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "freecad", 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/autonomous-ai/openharness.git --path store/agents/freecad/skills/freecad--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 autonomous-ai/openharness --skill freecad -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install autonomous-ai/openharness freecad --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/autonomous-ai/openharness.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/store/agents/freecad/skills/freecad .gemini/skills/freecad && 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 "freecad" agent skill from https://github.com/autonomous-ai/openharness/tree/main/store/agents/freecad/skills/freecad into .gemini/skills/freecad/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "freecad", 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 autonomous-ai/openharness freecadInstalls 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 autonomous-ai/openharness --skill freecad -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/autonomous-ai/openharness.git skills-src && mkdir -p .github/skills && cp -r skills-src/store/agents/freecad/skills/freecad .github/skills/freecad && 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 "freecad" agent skill from https://github.com/autonomous-ai/openharness/tree/main/store/agents/freecad/skills/freecad into .github/skills/freecad/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "freecad", 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 autonomous-ai/openharness --skill freecad -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install autonomous-ai/openharness freecad --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/autonomous-ai/openharness.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/store/agents/freecad/skills/freecad .opencode/skills/freecad && 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 "freecad" agent skill from https://github.com/autonomous-ai/openharness/tree/main/store/agents/freecad/skills/freecad into .opencode/skills/freecad/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "freecad", 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.
freecadTurn measured design briefs or existing parts into editable FreeCAD projects with checked dimensions, bores, clearances, interference and fastener access; deliver separate STEP/STL parts, reference…
Freecad is an agent skill from autonomous-ai/openharness. Turn measured design briefs or existing parts into editable FreeCAD projects with checked dimensions, bores, clearances, interference and fastener access; deliver separate STEP/STL parts, reference drawings and a portable project handoff.
Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 11 other files, including scripts and reference files (for example `references/design-contract.md`, `scripts/build-part.sh` and `scripts/design.py`).
The repository describes itself as: The ultimate harness for coding agents and beyond. All your agents. All your machines. One command center. Start with code, then follow your curiosity and build across… The licence is MIT.
Read from SKILL.md and the folder at commit cc4983e. It shows what the files ask for, not the result of running them.
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.
Ships 8 files in scripts/ (Python, JavaScript and Shell), which the agent can run.
Shell commands in SKILL.md call:
nodeshFrom the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Freecad loads about 1.4k tokens when it runs, and up to ~2.9k if it reads all its reference files. Until then it costs about 62 tokens; SKILL.md has 725 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.
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); the scripts in this folder are not scanned.
The full file from autonomous-ai/openharness at commit cc4983e, republished under its MIT licence (© autonomous-ai). 725 words, ~1,420 tokens.
.claude/skills/freecad/SKILL.md (or your agent's skills folder). This skill also uses 9 other files; get the full folder from GitHub.Establish what the part must fit, how it attaches, which dimensions are measured, the units and the intended process/material. Explain a needed measurement in everyday terms. A sketch or photo can guide shape, but does not establish scale or hidden dimensions. Record assumptions separately from requirements. For load-bearing, electrical, medical or other consequential uses, identify the necessary professional/physical validation; do not certify suitability from a CAD preview.
Create design.json with the brief, named parts/reference envelopes and measurable checks. Read
the design contract when creating or changing this file. Cover
the requirements that matter to the user's job: outside dimensions alone do not establish fit.
Use reference shapes for boards, connectors, movement or fastener/tool access, and check those
references' dimensions/positions so an accidentally moved or undersized keep-out cannot pass.
Build the appropriate model, not automatically an enclosure. part.FCMacro is Python executed by
FreeCADCmd, not system Python. Use FreeCAD as App, Part, named inputs and reusable construction
functions. Import an existing STEP as a reference when useful; include only user-approved input
files in the explicit sourceFiles list. Never bundle an entire workspace or hidden credentials.
The macro reads inputs from HARNESS_WORKSPACE, creates the named document objects and saves
part.FCStd in the unique HARNESS_BUILD_DIR. Close the document after saving. The runner handles
exports, measurements, drawings and the portable bundle. The example's dimensions.json is an
editable starting point, not a restriction on new designs. Preserve a user's existing work.
sh "$FREECAD_SKILLS/freecad/scripts/build-part.sh"Requires Node 20+ and headless FreeCAD with Part, MeshPart and TechDraw (tested with 1.1.3).
The wrapper resolves FREECAD_BIN, the toolchain link,
freecadcmd/FreeCADCmd or the installed macOS app. Recent macOS packages put the CLI at
FreeCAD.app/Contents/Resources/bin/freecadcmd, not necessarily Contents/MacOS/FreeCADCmd.
The runner reopens the native document and validates its individual solids. Each manufactured part must be one solid; declare disconnected pieces separately. It checks the saved requirements and reimports individual STEP and STL exports. STEP volume, size and position must survive export; STL must be a closed mesh with matching dimensions. Assembly contacts are allowed, but unwanted overlap must be covered by interference/clearance checks. Reference objects are not exported.
Read .harness/geometry.json, inspect the actual assembly in the shared CAD Viewer and review
each projected drawing. Inspect access, orientation and assembly sequence as well as dimensions.
For revisions, retain unchanged requirements; update requirements only when the brief changes.
Rebuild, inspect the changed geometry and report what changed. Never treat a previous render as
evidence of a successful new build.
On failure, inspect .harness/build.log or .harness/failed-design.json. A failed measured candidate
is shown as candidate.step; the last successful part.step and handoff/ stay unchanged. Fix the
model or resolve the brief conflict, not the test threshold. .harness/history/ retains replaced
successful artifacts. Do not delete history or a build lock merely to hide an error. A stale lock
may be removed only after confirming its owning build is no longer running.
Legacy macros without design.json may still export part.step, but remain ready:false: geometry
validity alone is not a checked job. Add requirements before claiming a complete handoff.
After a successful build, explain the measured results and unresolved manufacturing assumptions.
Deliver handoff/project.zip plus the human-readable handoff/index.html, not just a screenshot.
To give the user a clickable local download page, run this in a managed long-lived process and
share the printed loopback URL (keep it running while the user needs it; Ctrl-C stops it):
node "$FREECAD_SKILLS/freecad/scripts/serve-handoff.mjs" "$HARNESS_WORKSPACE"The server serves only generated handoff artifacts, never directory listings or arbitrary inputs. The page is a receipt of the last successful build, not a live claim about later edits.
The ZIP contains the explicitly selected sources, native document, assembly, separate parts,
dimensioned reference SVGs, measurement receipt and standalone tools. With Node and FreeCAD
installed, extract it elsewhere and run node tools/build.mjs; no Harness installation is needed.
Verify this path for a materially new workflow before presenting it as independently reproducible.
STEP files keep assembly coordinates. Each part STL is translated to nonnegative coordinates, without choosing a print orientation. Quantity is a bill-of-parts count, not repeated geometry. The assembly STL is not a prepared print layout. The SVGs show overall projected dimensions; they are not fully toleranced production drawings. Review material, wall thickness, tool access, supports and physical fit separately. The macro is executable Python; run only trusted sources. Native files may contain generated Part features, not a fully constrained Sketcher history.
© autonomous-ai, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 9 other files (scripts, references) in store/agents/freecad/skills/freecad of autonomous-ai/openharness.
Open the folder on GitHubat commit cc4983e
Freecad 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 |
|---|---|---|---|---|---|---|
| Freecad this skillautonomous-ai/openharness | 1.2k | — | ~1.4k | Automated safety check: Pass | MIT | |
| Briefalirezarezvani/claude-skills | 28k | — | ~967 | Automated safety check: Pass | MIT | |
| Briefdavepoon/buildwithclaude | 3.6k | — | ~1.3k | Automated safety check: Notes | MIT | |
| Freecad Scriptsgithub/awesome-copilot | 40k | 1 repos | ~5.3k | Automated safety check: Pass | MIT | |
| Step Partsearthtojake/text-to-cad | 19k | 1 repos | ~1.5k | Automated safety check: Pass | MIT | |
| Measure Before You Fixgarrytan/gbrain | 31k | — | ~2.5k | Automated safety check: Pass | MIT |
alirezarezvani/claude-skills
/cs:brief <topic — Generate a one-page strategy brief from an office-hours intake.
davepoon/buildwithclaude
Session-start briefing from Origin. An agent skill from davepoon/buildwithclaude.
github/awesome-copilot
Expert skill for writing FreeCAD Python scripts, macros, and automation.
earthtojake/text-to-cad
Find, evaluate, and download common purchasable CAD parts from step.parts, including named off-the-shelf actuators, servos, motors, electronics boards, connectors, screws, bolts, nuts, washers…
garrytan/gbrain
Before fixing a slow/stale/timeout alert, measure the step yourself.
every-app/open-seo
Produce a scannable review brief for a branch or PR so the maintainer can approve without reading the whole diff.
autonomous-ai/openharness
Slices 3D mesh files into printer-profiled plain G-code through real slicer CLIs, with backend discovery, input inspection, dry runs and static validation.
autonomous-ai/openharness
Turns a home-automation request into standard, testable automations.yaml, run against Home Assistant Core's real triggers and verified with its own trace tool.
autonomous-ai/openharness
Turns a musical brief into LilyPond concert-pitch music, checked parts for each instrument and a playable practice pack.
autonomous-ai/openharness
Turns an STL and explicit printer and material requirements into compared OrcaSlicer plans, an editable 3MF project, checked G-code and a portable handoff.
autonomous-ai/openharness
Builds an editable DOCX report, a formula-driven XLSX workbook and a fresh LibreOffice PDF preview from one structured source file, then checks them together.
autonomous-ai/openharness
Dry-run, upload, and cautiously initiate local Bambu Lab print jobs from validated plain .gcode, using Bambu LAN FTPS/MQTT handoffs.
Turn measured design briefs or existing parts into editable FreeCAD projects with checked dimensions, bores, clearances, interference and fastener access; deliver separate STEP/STL parts, reference…. Freecad is an agent skill from autonomous-ai/openharness. Turn measured design briefs or existing parts into editable FreeCAD projects with checked dimensions, bores, clearances, interference and fastener access; deliver separate STEP/STL parts, reference drawings and a portable project handoff.
Run `npx skills add autonomous-ai/openharness --skill freecad -a claude-code`. Or copy the skill folder (store/agents/freecad/skills/freecad in autonomous-ai/openharness) into .claude/skills/freecad in your project. Claude Code loads it when a task matches its description.
Run `npx skills add autonomous-ai/openharness --skill freecad -a codex`. Or copy the skill folder (store/agents/freecad/skills/freecad in autonomous-ai/openharness) into .agents/skills/freecad in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add autonomous-ai/openharness --skill freecad -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/freecad, .gemini/skills/freecad, .github/skills/freecad and .opencode/skills/freecad in your project.
Going by SKILL.md and its folder, Freecad needs Python, JavaScript and a shell for the scripts in its folder and the command-line tools its instructions call (node and sh). Our summary lists: Python 3; Node.js; A Bash shell.
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.
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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
Freecad is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 1.4k tokens (SKILL.md is roughly 5.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.4k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Freecad: Brief (alirezarezvani/claude-skills, 28k stars), Brief (davepoon/buildwithclaude, 3.6k stars), Freecad Scripts (github/awesome-copilot, 40k stars) and Step Parts (earthtojake/text-to-cad, 19k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
autonomous-ai (a GitHub organization) maintains it in autonomous-ai/openharness, which has 1,210 GitHub stars. The repository holds 100 skills in this directory. The repository was last updated on October 10, 2026.
Source: autonomous-ai/openharness on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.