Orca Computer Use
stablyai/orca
Drives the GUI of a visible local app window through `orca computer`: accessibility tree, clicks, typing, menus, dialogs, and screenshots in native apps and…
ORCA frequency calculation. An agent skill from Hello-QM/catgo-LRG.
$ npx skills add Hello-QM/catgo-LRG --skill orca-freq -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install Hello-QM/catgo-LRG orca-freq --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/Hello-QM/catgo-LRG.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/orca-freq .claude/skills/orca-freq && 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 "orca-freq" agent skill from https://github.com/Hello-QM/catgo-LRG/tree/main/.claude/skills/orca-freq into .claude/skills/orca-freq/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "orca-freq", 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/Hello-QM/catgo-LRG/tree/main/.claude/skills/orca-freqType 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 Hello-QM/catgo-LRG --skill orca-freq -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install Hello-QM/catgo-LRG orca-freq --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Hello-QM/catgo-LRG.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/orca-freq .agents/skills/orca-freq && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "orca-freq" agent skill from https://github.com/Hello-QM/catgo-LRG/tree/main/.claude/skills/orca-freq into .agents/skills/orca-freq/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "orca-freq", 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 Hello-QM/catgo-LRG --skill orca-freq -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install Hello-QM/catgo-LRG orca-freq --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Hello-QM/catgo-LRG.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/orca-freq .cursor/skills/orca-freq && 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 "orca-freq" agent skill from https://github.com/Hello-QM/catgo-LRG/tree/main/.claude/skills/orca-freq into .cursor/skills/orca-freq/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "orca-freq", 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/Hello-QM/catgo-LRG.git --path .claude/skills/orca-freq--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 Hello-QM/catgo-LRG --skill orca-freq -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install Hello-QM/catgo-LRG orca-freq --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Hello-QM/catgo-LRG.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/orca-freq .gemini/skills/orca-freq && 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 "orca-freq" agent skill from https://github.com/Hello-QM/catgo-LRG/tree/main/.claude/skills/orca-freq into .gemini/skills/orca-freq/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "orca-freq", 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 Hello-QM/catgo-LRG orca-freqInstalls 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 Hello-QM/catgo-LRG --skill orca-freq -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/Hello-QM/catgo-LRG.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/orca-freq .github/skills/orca-freq && 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 "orca-freq" agent skill from https://github.com/Hello-QM/catgo-LRG/tree/main/.claude/skills/orca-freq into .github/skills/orca-freq/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "orca-freq", 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 Hello-QM/catgo-LRG --skill orca-freq -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install Hello-QM/catgo-LRG orca-freq --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Hello-QM/catgo-LRG.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/orca-freq .opencode/skills/orca-freq && 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 "orca-freq" agent skill from https://github.com/Hello-QM/catgo-LRG/tree/main/.claude/skills/orca-freq into .opencode/skills/orca-freq/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "orca-freq", 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.
orca-freqORCA frequency calculation. An agent skill from Hello-QM/catgo-LRG.
Orca Freq is an agent skill from Hello-QM/catgo-LRG. ORCA frequency calculation. Computes vibrational frequencies, IR intensities, zero-point energy, and thermochemistry at specified temperature/pressure.
Its SKILL.md is about 2.8k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
The repository describes itself as: AI-driven workbench for computational materials science — interactive 3D structure viewer, natural-language CatBot assistant, visual DAG workflow engine, HPC job submission… The licence is AGPL-3.0.
8 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit fd6291b. 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.
Shell commands in SKILL.md call:
curlpipFrom the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md. Its commands use curl and pip, which can reach the network depending on how they are called.
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.
Orca Freq loads about 2.8k tokens when it runs. Until then it costs about 40 tokens; SKILL.md has 833 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); files beside SKILL.md are not scanned.
The full file from Hello-QM/catgo-LRG at commit fd6291b, republished under its AGPL-3.0 licence (© Hello-QM). 833 words, ~2,781 tokens.
.claude/skills/orca-freq/SKILL.md (or your agent's skills folder).Use this skill when the user wants to:
The input structure MUST be optimized at the same level of theory used for the frequency calculation. Running frequencies on an unoptimized structure will produce meaningless imaginary frequencies.
Use
catgo_workflow(graph-based), NOTcatgo_workflow_engine(task-based). The graph-based tool auto-captures the viewer structure oncreateand supports connecting opt→freq via explicit node edges. Task-basedadd_taskdoesn't attach the viewer structure → "No input structure provided". Param keys also differ: graph-based usesmethod/basis, task-based usesorca_method/orca_basis.
catgo_view(action: "get_state")curl -s http://localhost:8000/api/hpc/connectionsCopy the session_id for host: login.expanse.sdsc.edu.
catgo_workflow(action: "create", name: "Water frequencies B3LYP")This creates a structure_input node with the current viewer structure.
Note its node ID.
Standalone freq (when structure is already optimized at the same level):
Inject extra_blocks: "%output jsongbwfile True jsonpropfile True end" so
ORCA emits the JSON files OPI parses.
catgo_workflow(action: "batch", workflow_id: "<wf_id>", operations: [
{"op": "add_node", "node_type": "freq", "label": "freq1",
"params": {
"software": "orca",
"method": "B3LYP",
"basis": "def2-SVP",
"charge": 0,
"multiplicity": 1,
"extra_blocks": "%output jsongbwfile True jsonpropfile True end"
}},
{"op": "connect", "from_id": "<structure_input_id>", "to_id": "freq1",
"from_handle": "structure", "to_handle": "structure"}
])Opt → Freq chain (recommended — consistent PES guaranteed):
catgo_workflow(action: "batch", workflow_id: "<wf_id>", operations: [
{"op": "add_node", "node_type": "geo_opt", "label": "opt1",
"params": {
"software": "orca",
"method": "B3LYP",
"basis": "def2-TZVP",
"opt_convergence": "TightOpt",
"dispersion": "D3BJ",
"charge": 0,
"multiplicity": 1
}},
{"op": "add_node", "node_type": "freq", "label": "freq1",
"params": {
"software": "orca",
"method": "B3LYP",
"basis": "def2-TZVP",
"dispersion": "D3BJ",
"charge": 0,
"multiplicity": 1
}},
{"op": "connect", "from_id": "<structure_input_id>", "to_id": "opt1",
"from_handle": "structure", "to_handle": "structure"},
{"op": "connect", "from_id": "opt1", "to_id": "freq1",
"from_handle": "structure", "to_handle": "structure"}
])The freq node consumes opt1's optimized structure — no separate depends_on
needed; the edge defines the dependency.
ORCA reports thermochemistry at 298.15 K / 1 atm by default. For other
conditions, chain a gibbs_energy analysis node:
{"op": "add_node", "node_type": "gibbs_energy", "label": "gibbs1",
"params": {"temperature": 373.15, "phase": "gas"}},
{"op": "connect", "from_id": "freq1", "to_id": "gibbs1",
"from_handle": "frequencies", "to_handle": "frequencies"}run_config MUST include module_loads, orca_dir, account, partition,
walltime, and the local-scratch SLURM template. Read
server/templates/orca_generic.sh and pass its contents as default_template.
catgo_workflow(action: "run", workflow_id: "<wf_id>", run_config: {
"execution_mode": "hpc",
"default_session_id": "<expanse_session_id>",
"base_work_dir": "/expanse/lustre/projects/sdp126/jyang25/ORCA/catgo",
"default_job_params": {
"nodes": 1, "ntasks": 4, "cpus_per_task": 1,
"walltime": "00:30:00", "partition": "debug"
},
"cluster_configs": {
"<expanse_session_id>": {
"account": "sdp126",
"partition": "debug",
"module_loads": "module load cpu/0.17.3b\nmodule load gcc/10.2.0/npcyll4\nexport PATH=$HOME/openmpi-4.1.8/bin:$PATH\nexport LD_LIBRARY_PATH=$HOME/openmpi-4.1.8/lib:$LD_LIBRARY_PATH",
"orca_dir": "/home/jyang25/orca_6_1_1_RRP8",
"default_template": "<contents of server/templates/orca_generic.sh>",
"default_job_params": {
"nodes": 1, "ntasks": 4, "cpus_per_task": 1,
"walltime": "00:30:00", "partition": "debug"
}
}
}
})For freq jobs longer than 30 min, bump walltime and switch partition to
shared or compute. The local-scratch template stages I/O to
$TMPDIR/orca_$SLURM_JOB_ID — necessary on Expanse (Lustre kills ORCA's
many-small-file I/O during numerical Hessians).
catgo_workflow(action: "status", workflow_id: "<wf_id>")Pull the outputs into a local directory, including the OPI JSON files:
mkdir -p ./local_run
for f in ORCA.out ORCA.hess ORCA.property.json ORCA.json; do
curl -s -X POST http://localhost:8000/api/hpc/files/read-content \
-H 'Content-Type: application/json' \
-d "{\"session_id\":\"<expanse_session_id>\",\"file_path\":\"<work_dir>/$f\"}" \
> ./local_run/$f
doneParsed result fields (when fetched via catgo_workflow get_result or the
results-enriched endpoint):
frequencies: list of vibrational frequencies in cm⁻¹intensities: IR intensities in km/molis_imaginary: boolean flags for each frequencyzpe: zero-point energy in eVthermochemistry: dict with H, S, G at standard conditionsReplaces the hand-grep'd thermochemistry block. Requires pip install orca-pi.
import sys
sys.path.insert(0, ".claude/skills") # for the _shared helper
from _shared.orca_opi import parse_local
out = parse_local("./local_run")
# IR table — replaces frequencies + intensities + is_imaginary trio
ir = out.get_ir() # dict[int, IrMode]
for mode_idx, mode in ir.items():
print(mode_idx, mode.wavenumber, mode.intensity, mode.dipole)
# Thermochemistry (units: hartree, hartree/K)
thermo = {
"zpe_eh": out.get_zpe(),
"inner_energy_eh": out.get_inner_energy(),
"enthalpy_eh": out.get_enthalpy(),
"entropy_eh_per_K": out.get_entropy(),
"free_energy_eh": out.get_free_energy(),
"G_minus_Eel_eh": out.get_free_energy_delta(),
}
# Imaginary check from the raw frequency list (negatives = imaginary)
freqs = out.results_properties.geometries[0].thermochemistry_energies[0].freq
n_imag = sum(1 for f in freqs if f < 0)
print(f"Imaginary modes: {n_imag}")Use the shared helper to plot a stick spectrum and surface the PNG inline.
from _shared.orca_opi import quick_plot_ir, show_png
png = quick_plot_ir(out) # writes ./local_run/ir_spectrum.png
show_png(png, "IR spectrum") # prints ``After running this, reply to the user with the markdown link the script printed so Claude Code renders the figure inline in chat.
catgo_workflow_engine.add_task doesn't auto-attach the viewer structure → "No input structure provided".partition=workq (Shaheen default) is invalid on Expanse → use debug or shared.account=sdp126 → "Invalid account or account/partition combination".module_loads + orca_dir → orca not on PATH; numerical Hessians silently produce nothing./api/hpc/connections and update default_session_id + cluster_configs key.submit.sh on retry alone — call run with the new run_config to get a fresh script.catgo_view to visualize the modeORCA prints a thermochemistry block with:
| Quantity | Symbol | Units |
|---|---|---|
| Zero-point energy | ZPE | eV (or kcal/mol) |
| Thermal energy | U | eV |
| Enthalpy | H = U + pV | eV |
| Entropy | S | eV/K |
| Gibbs free energy | G = H - TS | eV |
For catalysis, feed the DFT energy and frequencies into gibbs_energy:
phase: "adsorbed" -- harmonic approximation (no translational/rotational)phase: "gas" -- ideal gas (includes translation, rotation, vibration)DFT frequencies are systematically overestimated. Common scaling factors:
| Method | Scaling factor |
|---|---|
| B3LYP/def2-SVP | 0.9813 |
| B3LYP/def2-TZVP | 0.9654 |
| PBE/def2-SVP | 0.9948 |
| HF-3c | 0.86 |
These are applied automatically by the gibbs_energy task when available.
| Parameter | Default | Description |
|---|---|---|
method | B3LYP | DFT functional |
basis | def2-SVP | Basis set |
charge / multiplicity | 0 / 1 | Charge and 2S+1 |
dispersion | (none) | D4 | D3BJ | D3 | none. Use this field, NOT extra_keywords. |
grid | DefGrid2 | DefGrid1/2/3 |
wavefunction, uno, uco | — | Open-shell tweaks |
num_cores / max_core_mb | 4 / 4000 | %pal nprocs / %maxcore |
⚠️
extra_keywordsandextra_blocksare NOT read by the engine. ForcingNumFreq, addingCPCM(Water), etc. via those keys silently does nothing. These are current node-def gaps for freq.
NumFreq is currently a gap — analytical Hessians are used by default for whatever functional supports them© Hello-QM, AGPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Just SKILL.md in .claude/skills/orca-freq of Hello-QM/catgo-LRG.
Open the folder on GitHubat commit fd6291b
Orca Freq 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 |
|---|---|---|---|---|---|---|
| Orca Freq this skillHello-QM/catgo-LRG | 205 | — | ~2.8k | Automated safety check: Pass | AGPL-3.0 | |
| Orca Computer Usestablyai/orca | 88k | — | ~553 | Automated safety check: Pass | MIT | |
| Ito Computeaffaan-m/ECC | 276k | 1 repos | ~1.7k | Automated safety check: Pass | MIT | |
| Senior Computer Visiondavila7/claude-code-templates | 32k | 2 repos | ~1.4k | Automated safety check: Pass | MIT | |
| Orcaalsk1992/CloddsBot | 2.9k | — | ~119 | Automated safety check: Pass | MIT | |
| Senior Computer Visionalirezarezvani/claude-skills | 28k | 1 repos | ~3.2k | Automated safety check: Pass | MIT |
stablyai/orca
Drives the GUI of a visible local app window through `orca computer`: accessibility tree, clicks, typing, menus, dialogs, and screenshots in native apps and…
affaan-m/ECC
Query live GPU inventory, submit an authenticated Itô fixed-rate RFQ, inspect RFQ or procurement status, revoke device credentials, and run explicitly gated node qualification through the separately…
davila7/claude-code-templates
World-class computer vision skill for image/video processing, object detection, segmentation, and visual AI systems.
alsk1992/CloddsBot
Orca Whirlpools - concentrated liquidity on Solana. An agent skill from alsk1992/CloddsBot.
alirezarezvani/claude-skills
Computer vision engineering skill for object detection, image segmentation, and visual AI systems.
stablyai/orca
Show a chart, diagram, table, report or mockup inline in this Orca chat as an HTML page.
Hello-QM/catgo-LRG
Drive a file-first, agent-in-the-loop computational campaign via a folder + markdown tree (no DB).
Hello-QM/catgo-LRG
Compute adsorption/reaction Gibbs free energies, free-energy diagrams, and electrochemical overpotentials (HER/ORR/OER/CO2RR/NRR) with VASP.
Hello-QM/catgo-LRG
Generate and manage ABINIT DFT calculations. An agent skill from Hello-QM/catgo-LRG.
Hello-QM/catgo-LRG
A skill your agent uses when the user asks to place an adsorbate molecule on a surface, find adsorption sites, or set up a surface+adsorbate model for DFT.
Hello-QM/catgo-LRG
A skill your agent uses when the user asks for adsorption energy, binding energy, or wants to compare how strongly a molecule binds to a surface.
Hello-QM/catgo-LRG
A skill your agent uses when the user asks to analyze computational results: Gibbs free energy, OER/HER/CO2RR overpotentials, adsorption energy, convergence tests, DOS/d-band analysis, or Bader…
ORCA frequency calculation. An agent skill from Hello-QM/catgo-LRG. Orca Freq is an agent skill from Hello-QM/catgo-LRG. ORCA frequency calculation.
Run `npx skills add Hello-QM/catgo-LRG --skill orca-freq -a claude-code`. Or copy the skill folder (.claude/skills/orca-freq in Hello-QM/catgo-LRG) into .claude/skills/orca-freq in your project. Claude Code loads it when a task matches its description.
Run `npx skills add Hello-QM/catgo-LRG --skill orca-freq -a codex`. Or copy the skill folder (.claude/skills/orca-freq in Hello-QM/catgo-LRG) into .agents/skills/orca-freq 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 Hello-QM/catgo-LRG --skill orca-freq -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/orca-freq, .gemini/skills/orca-freq, .github/skills/orca-freq and .opencode/skills/orca-freq in your project.
Going by SKILL.md and its folder, Orca Freq needs the command-line tools its instructions call (curl and pip). Our summary lists: Python 3.
SKILL.md contains no URLs. Its commands use curl and pip, which can reach the network depending on how they are called. 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. Review the folder before installing.
Orca Freq is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 2.8k tokens (SKILL.md is roughly 11k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Orca Freq: Orca Computer Use (stablyai/orca, 88k stars), Ito Compute (affaan-m/ECC, 276k stars), Senior Computer Vision (davila7/claude-code-templates, 32k stars) and Orca (alsk1992/CloddsBot, 2.9k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Hello-QM (a GitHub user) maintains it in Hello-QM/catgo-LRG, which has 205 GitHub stars. The repository holds 75 skills in this directory. The repository was last updated on September 22, 2026.
Source: Hello-QM/catgo-LRG on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.