New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Adsorbate Placement

by Hello-QM in 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.

AGPL-3.0Auto-check passedResearch & Science

Install Adsorbate Placement

skills CLI
$ npx skills add Hello-QM/catgo-LRG --skill adsorbate-placement -a claude-code

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

GitHub CLI
$ gh skill install Hello-QM/catgo-LRG adsorbate-placement --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/Hello-QM/catgo-LRG.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/structure-adsorbate .claude/skills/adsorbate-placement && 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
adsorbate-placement
GitHub stars
205
Token cost
~3k tokens
SKILL.md length
674 words
Files
1
Skills in repo
75
Repo updated
First seen
Licence
AGPL-3.0

At a glance

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.

  • Works in 5 steps: Generate slab (or use existing) → Find adsorption sites → Build workflow with adsorbate placement → …
  • The user asks to place an adsorbate molecule on a surface
  • SKILL.md covers Overview, Task Type: adsorbate_place, Discussion Checkpoints and MCP Workflow: Place Adsorbate…, plus 6 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Adsorbate Placement is an agent skill from Hello-QM/catgo-LRG. Use when the user asks to place an adsorbate molecule on a surface, find adsorption sites, or set up a surface+adsorbate model for DFT.

Its SKILL.md is about 3k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Research & Science. 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.

When your agent uses it

  • The user asks to place an adsorbate molecule on a surface
  • Find adsorption sites
  • Set up a surface+adsorbate model for DFT

Example prompts

  • “/adsorbate-placement”

Requirements

  • Python 3

Workflow steps

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

  1. Generate slab (or use existing)
  2. Find adsorption sites
  3. Build workflow with adsorbate placement
  4. PENDING_REVIEW -- verify adsorbate position
  5. Submit for DFT optimization

What it can do on your machine

Read from SKILL.md and the folder at commit fd6291b. 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 and python).

    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

Adsorbate Placement loads about 3k tokens when it runs. Until then it costs about 39 tokens; SKILL.md has 674 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~39
When it runs · the whole SKILL.md, loaded when a task matches
~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 Hello-QM/catgo-LRG at commit fd6291b, republished under its AGPL-3.0 licence (© Hello-QM). 674 words, ~3,042 tokens.

Download SKILL.mdSave it as .claude/skills/adsorbate-placement/SKILL.md (or your agent's skills folder).
name
adsorbate-placement
description
Use when the user asks to place an adsorbate molecule on a surface, find adsorption sites, or set up a surface+adsorbate model for DFT.

Adsorbate Placement

Overview

The adsorbate_place task type places adsorbate molecules on surface slabs. It uses ferrox (Rust) find_adsorption_sites to locate surface sites, then the CatGo placement engine (utils/adsorbate_placement.py) for Rodrigues rotation, overlap detection, and multi-dentate support.

Task Type: adsorbate_place

  • Type: adsorbate_place (local task, no HPC needed)
  • Engine: ferrox site finder + CatGo placement engine
  • Outputs: structure (slab+adsorbate as JSON)
Parameters
ParameterTypeDefaultDescription
structureJSONrequiredSlab structure input
speciesstr"OH"Adsorbate species name
sitestr"ontop"Site type: "ontop", "bridge", "hollow", or "all"
heightfloat2.0Height above surface in Angstroms
site_indexint0Which site of the given type to use (0 = first)
Supported Adsorbate Species
SpeciesAtomsBinding AtomNotes
OHO, HOHydroxyl, O-H = 0.96 A
OOOAtomic oxygen
OOHO, O, HO1Hydroperoxo, key OER intermediate
HHHAtomic hydrogen
H2OO, H, HOWater molecule
COC, OCCarbon monoxide, C-O = 1.13 A
CO2C, O, OCCarbon dioxide, linear
N2N, NNDinitrogen, N-N = 1.10 A
NHN, HNImide
NH2N, H, HNAmino
NH3N, H, H, HNAmmonia
CHOC, H, OCFormyl
COOHC, O, O, HCCarboxyl
Site Types
Siteferrox TypeCoordinationDescription
ontopatop1-foldDirectly above one surface atom
bridgebridge2-foldBetween two surface atoms
hollowhollow33-foldAbove threefold hollow site
allatop (default)1-foldAuto-selects ontop

Discussion Checkpoints

🔴 Must discuss with user:

  • Adsorbate species — determines the chemistry being studied; wrong species = wrong intermediate in the reaction pathway
  • Adsorption site (ontop/bridge/hollow) — different sites have different binding energies; for screening, test all three and report the most stable

🟡 Recommend confirming:

  • Height above surface (default: 2.0 A) — too close triggers repulsion during geo_opt, too far causes adsorbate to fly away; use 1.5-1.8 A for atomic O, 2.0-2.5 A for molecular species
  • Site index (default: 0) — which specific site of the given type; call catgo_analyze(action="adsorption_sites") first to see available sites
  • Multi-dentate orientation — for OOH, COOH, and other multi-atom adsorbates, the binding orientation matters; verify with catgo_view after placement

🟢 Safe defaults:

  • Collision detection enabled (ferrox automatic)
  • Automatic site finding via ferrox find_adsorption_sites
  • Binding atom orientation follows species convention (O down for OH, C down for CO)

MCP Workflow: Place Adsorbate on Slab

Step 1: Generate slab (or use existing)
json
{"tool": "catgo_fetch", "arguments": {
  "action": "crystal", "formula": "Pt", "provider": "mp"
}}
json
{"tool": "catgo_structure", "arguments": {
  "action": "slab",
  "miller_index": [1, 1, 1],
  "min_slab_size": 12.0,
  "min_vacuum_size": 15.0
}}
json
{"tool": "catgo_structure", "arguments": {
  "action": "supercell",
  "scaling": [2, 2, 1]
}}
Step 2: Find adsorption sites
json
{"tool": "catgo_analyze", "arguments": {
  "action": "adsorption_sites"
}}

This returns all available sites (ontop, bridge, hollow) with coordinates.

Show full SKILL.md (272 more words)Show less
Step 3: Build workflow with adsorbate placement

Using the workflow engine with adsorbate_place node:

json
{"tool": "catgo_workflow", "arguments": {
  "action": "batch",
  "workflow_id": "wf_123",
  "operations": [
    {"op": "add_node", "node_type": "slab_gen", "label": "slab1",
     "params": {"miller": [1, 1, 1], "layers": 4, "vacuum": 15.0}},
    {"op": "add_node", "node_type": "adsorbate_place", "label": "ads1",
     "params": {"species": "OH", "site": "ontop", "height": 2.0, "site_index": 0}},
    {"op": "add_node", "node_type": "geo_opt", "label": "go1",
     "params": {"software": "vasp", "ENCUT": 520, "freeze_mode": "layers", "freeze_layers": 2}},
    {"op": "connect", "from_id": "<structure_input_id>", "to_id": "slab1"},
    {"op": "connect", "from_id": "slab1", "to_id": "ads1",
     "from_handle": "structure", "to_handle": "structure"},
    {"op": "connect", "from_id": "ads1", "to_id": "go1",
     "from_handle": "structure", "to_handle": "structure"}
  ]
}}
Step 4: PENDING_REVIEW -- verify adsorbate position

The user should inspect the structure before submitting geo_opt. Check:

  • Adsorbate is at the correct site (ontop/bridge/hollow)
  • Height above surface is reasonable (1.5-2.5 A for most species)
  • No atom overlaps or unrealistic bond lengths
  • Binding atom orientation is correct (e.g., C down for CO, O down for OH)
json
{"tool": "catgo_view", "arguments": {"action": "get_state"}}
Step 5: Submit for DFT optimization
json
{"tool": "catgo_workflow", "arguments": {
  "action": "run",
  "workflow_id": "wf_123",
  "run_config": {"cluster": "expanse", "partition": "shared", "walltime": "04:00:00"}
}}

Python API

python
from catgo.workflow import Workflow

wf = Workflow("OH on Pt(111)")

# Bulk input
inp = wf.add_task("structure_input", structure=pt_bulk_json)

# Cut slab
slab = wf.add_task("slab_gen",
    structure=inp.output.structure,
    miller=(1, 1, 1),
    layers=4,
    vacuum=15.0)

# Place adsorbate
ads = wf.add_task("adsorbate_place",
    structure=slab.output.structure,
    species="OH",
    site="ontop",
    height=2.0,
    site_index=0)

# PENDING_REVIEW: user should verify adsorbate position before geo_opt

# Geometry optimization
opt = wf.add_task("geo_opt",
    structure=ads.output.structure,
    software="vasp",
    ENCUT=520,
    freeze_mode="layers",
    freeze_layers=2)

wf.submit()

Complete OER Workflow Example

The oxygen evolution reaction (OER) has four intermediates: *OH, *O, *OOH, and clean slab. Each needs geo_opt + freq + gibbs_energy.

python
from catgo.workflow import Workflow

wf = Workflow("OER on IrO2(110)")

# Shared bulk input
inp = wf.add_task("structure_input", structure=iro2_bulk_json)
slab = wf.add_task("slab_gen",
    structure=inp.output.structure,
    miller=(1, 1, 0), layers=4, vacuum=15.0)

# --- Clean slab branch ---
slab_opt = wf.add_task("geo_opt", structure=slab.output.structure,
    software="vasp", ENCUT=520, system_name="clean_slab",
    freeze_mode="layers", freeze_layers=2)
slab_freq = wf.add_task("freq", structure=slab_opt.output.structure,
    software="vasp", freeze_mode="layers", freeze_layers=2)
slab_gibbs = wf.add_task("gibbs_energy",
    energy=slab_opt.output.energy,
    frequencies=slab_freq.output.frequencies,
    phase="adsorbed")

# --- *OH branch ---
oh_ads = wf.add_task("adsorbate_place", structure=slab.output.structure,
    species="OH", site="ontop", height=2.0)
oh_opt = wf.add_task("geo_opt", structure=oh_ads.output.structure,
    software="vasp", ENCUT=520, system_name="OH_ads",
    freeze_mode="layers", freeze_layers=2)
oh_freq = wf.add_task("freq", structure=oh_opt.output.structure,
    software="vasp", freeze_mode="layers", freeze_layers=2)
oh_gibbs = wf.add_task("gibbs_energy",
    energy=oh_opt.output.energy,
    frequencies=oh_freq.output.frequencies,
    phase="adsorbed")

# --- *O branch ---
o_ads = wf.add_task("adsorbate_place", structure=slab.output.structure,
    species="O", site="ontop", height=1.8)
o_opt = wf.add_task("geo_opt", structure=o_ads.output.structure,
    software="vasp", ENCUT=520, system_name="O_ads",
    freeze_mode="layers", freeze_layers=2)
o_freq = wf.add_task("freq", structure=o_opt.output.structure,
    software="vasp", freeze_mode="layers", freeze_layers=2)
o_gibbs = wf.add_task("gibbs_energy",
    energy=o_opt.output.energy,
    frequencies=o_freq.output.frequencies,
    phase="adsorbed")

# --- *OOH branch ---
ooh_ads = wf.add_task("adsorbate_place", structure=slab.output.structure,
    species="OOH", site="ontop", height=2.0)
ooh_opt = wf.add_task("geo_opt", structure=ooh_ads.output.structure,
    software="vasp", ENCUT=520, system_name="OOH_ads",
    freeze_mode="layers", freeze_layers=2)
ooh_freq = wf.add_task("freq", structure=ooh_opt.output.structure,
    software="vasp", freeze_mode="layers", freeze_layers=2)
ooh_gibbs = wf.add_task("gibbs_energy",
    energy=ooh_opt.output.energy,
    frequencies=ooh_freq.output.frequencies,
    phase="adsorbed")

# --- Gas-phase references (H2O, H2) ---
h2o_inp = wf.add_task("structure_input", structure=h2o_gas_json)
h2o_opt = wf.add_task("geo_opt", structure=h2o_inp.output.structure,
    software="vasp", ENCUT=520, ISMEAR=0, KPOINTS=[1,1,1],
    system_name="H2O_gas")
h2o_freq = wf.add_task("freq", structure=h2o_opt.output.structure,
    software="vasp")
h2o_gibbs = wf.add_task("gibbs_energy",
    energy=h2o_opt.output.energy,
    frequencies=h2o_freq.output.frequencies,
    phase="gas")

h2_inp = wf.add_task("structure_input", structure=h2_gas_json)
h2_opt = wf.add_task("geo_opt", structure=h2_inp.output.structure,
    software="vasp", ENCUT=520, ISMEAR=0, KPOINTS=[1,1,1],
    system_name="H2_gas")
h2_freq = wf.add_task("freq", structure=h2_opt.output.structure,
    software="vasp")
h2_gibbs = wf.add_task("gibbs_energy",
    energy=h2_opt.output.energy,
    frequencies=h2_freq.output.frequencies,
    phase="gas")

# Free energy diagram
fed = wf.add_task("free_energy_diagram",
    gibbs_values={
        "clean": slab_gibbs.output.gibbs,
        "OH": oh_gibbs.output.gibbs,
        "O": o_gibbs.output.gibbs,
        "OOH": ooh_gibbs.output.gibbs,
        "H2O": h2o_gibbs.output.gibbs,
        "H2": h2_gibbs.output.gibbs,
    },
    step_order=["clean", "OH", "O", "OOH", "O2"])

wf.submit()

DAG Structure (Single Adsorbate)

bulk_crystal --> slab_gen --> adsorbate_place --> [PENDING_REVIEW] --> geo_opt

DAG Structure (OER)

                                /--> *OH  --> geo_opt --> freq --> gibbs --\
bulk --> slab_gen --> slab -----+--> *O   --> geo_opt --> freq --> gibbs ---+--> free_energy_diagram
                          \    \--> *OOH --> geo_opt --> freq --> gibbs --/
                           \--> clean_slab --> geo_opt --> freq --> gibbs -/

Comparing Multiple Sites

To compare adsorption at different sites (ontop, bridge, hollow), create separate branches from the same slab:

python
for site_type in ["ontop", "bridge", "hollow"]:
    ads = wf.add_task("adsorbate_place",
        structure=slab.output.structure,
        species="OH",
        site=site_type,
        height=2.0,
        site_index=0)
    opt = wf.add_task("geo_opt",
        structure=ads.output.structure,
        software="vasp", ENCUT=520,
        system_name=f"OH_{site_type}")

Common Pitfalls

  1. Always build the slab and supercell BEFORE placing adsorbates. Adding adsorbates to a 1x1 slab gives unphysically high coverage.
  2. The initial height matters: too close triggers repulsion, too far may cause the adsorbate to fly away during geo_opt. Use 1.5-2.5 A for most species.
  3. OOH tends to dissociate into O + OH during relaxation on some surfaces. Use tight EDIFFG and monitor the trajectory.
  4. For bridge and hollow sites, the adsorbate is placed between atoms automatically by the ferrox site finder. Do not manually calculate midpoints.
  5. After placement, always verify with catgo_view that no atoms overlap and the geometry looks reasonable before submitting to DFT.
  6. When using site_index, call catgo_analyze with action: "adsorption_sites" first to see available sites and their indices.
  7. The site="all" option defaults to ontop (atop) sites. For specific site types, always pass the explicit type name.

© 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

Files

Just SKILL.md in .claude/skills/structure-adsorbate of Hello-QM/catgo-LRG.

Open the folder on GitHubat commit fd6291b

Compare with similar skills

Adsorbate Placement 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.

Adsorbate Placement compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Adsorbate Placement this skillHello-QM/catgo-LRG205—~3kAutomated safety check: PassAGPL-3.0
Hypothesis Generationspacering-net/codeg3.9k14 repos~3.6kAutomated safety check: NotesMIT
GitHub Deep Researchbytedance/deer-flow84k4 repos~1.3kAutomated safety check: PassMIT
Nature Paper CardYuan1z0825/nature-skills47k2 repos~2.1kAutomated safety check: PassApache-2.0
Content Research Writerweapp-tailwindcss/weapp-tailwindcss1.9k25 repos~3.5kAutomated safety check: PassMIT
Peer Reviewspacering-net/codeg3.9k17 repos~5.9kAutomated safety check: NotesMIT

Similar skills

  • Hypothesis Generation

    spacering-net/codeg

    Structured hypothesis formulation from observations. An agent skill from spacering-net/codeg.

    3.9k GitHub starsUsed in 14 repos~3.6k tokens
    Research & ScienceAuto-check: notes

  • GitHub Deep Research

    bytedance/deer-flow

    Researches a GitHub repository over four rounds using the GitHub API and web search, then writes a structured markdown report with timeline, metrics and Mermaid diagrams.

    84k GitHub starsUsed in 4 repos~1.3k tokens
    Research & ScienceAuto-check passed

  • Nature Paper Card

    Yuan1z0825/nature-skills

    Builds a structured deep-reading card for one scientific paper, covering methods, how experiments support claims, limitations and research ideas, with a script to prepare the source.

    47k GitHub starsUsed in 2 repos~2.1k tokens
    Research & ScienceAuto-check passed

  • Content Research Writer

    weapp-tailwindcss/weapp-tailwindcss

    Assists in writing high-quality content by conducting research, adding citations, improving hooks, iterating on outlines, and providing real-time feedback on each section.

    1.9k GitHub starsUsed in 25 repos~3.5k tokens
    Research & ScienceAuto-check passed

  • Peer Review

    spacering-net/codeg

    Structured manuscript/grant review with checklist-based evaluation.

    3.9k GitHub starsUsed in 17 repos~5.9k tokens
    Research & ScienceAuto-check: notes

  • Last30days

    mvanhorn/last30days-skill

    Research what people actually say about any topic in the last 30 days.

    64k GitHub stars~7.9k tokensUpdated today
    Research & ScienceAuto-check: notes

More from Hello-QM/catgo-LRG

All 75 skills in this repo

  • Campaign Md Orchestration

    Hello-QM/catgo-LRG

    Drive a file-first, agent-in-the-loop computational campaign via a folder + markdown tree (no DB).

    205 GitHub stars~1.6k tokensUpdated 17 days ago
    Auto-check passed

  • Catgo Gibbs Pipeline

    Hello-QM/catgo-LRG

    Compute adsorption/reaction Gibbs free energies, free-energy diagrams, and electrochemical overpotentials (HER/ORR/OER/CO2RR/NRR) with VASP.

    205 GitHub stars~669 tokensUpdated 17 days ago
    Auto-check passed

  • Abinit

    Hello-QM/catgo-LRG

    Generate and manage ABINIT DFT calculations. An agent skill from Hello-QM/catgo-LRG.

    205 GitHub stars~963 tokensUpdated 17 days ago
    Auto-check passed

  • Adsorption Energy

    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.

    205 GitHub stars~1.4k tokensUpdated 17 days ago
    Auto-check passed

  • Analysis Router

    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…

    205 GitHub stars~869 tokensUpdated 17 days ago
    Auto-check passed

  • Atom Ops

    Hello-QM/catgo-LRG

    One-shot recipes for adding, deleting, moving, and replacing individual atoms in the active CatGo viewer structure.

    205 GitHub stars~1.2k tokensUpdated 17 days ago
    Auto-check passed

Categories

Questions about Adsorbate Placement

What does Adsorbate Placement do?

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. Adsorbate Placement is an agent skill from Hello-QM/catgo-LRG. Use when the user asks to place an adsorbate molecule on a surface, find adsorption sites, or set up a surface+adsorbate model for DFT.

When should I use Adsorbate Placement?

Adsorbate Placement fits situations like: the user asks to place an adsorbate molecule on a surface; find adsorption sites; set up a surface+adsorbate model for DFT.

How do I install Adsorbate Placement in Claude Code?

Run `npx skills add Hello-QM/catgo-LRG --skill adsorbate-placement -a claude-code`. Or copy the skill folder (.claude/skills/structure-adsorbate in Hello-QM/catgo-LRG) into .claude/skills/adsorbate-placement in your project. Claude Code loads it when a task matches its description.

How do I install Adsorbate Placement in Codex?

Run `npx skills add Hello-QM/catgo-LRG --skill adsorbate-placement -a codex`. Or copy the skill folder (.claude/skills/structure-adsorbate in Hello-QM/catgo-LRG) into .agents/skills/adsorbate-placement in your project. Codex loads it when a task matches its description.

Can I use Adsorbate Placement 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 Hello-QM/catgo-LRG --skill adsorbate-placement -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/adsorbate-placement, .gemini/skills/adsorbate-placement, .github/skills/adsorbate-placement and .opencode/skills/adsorbate-placement in your project.

What does Adsorbate Placement need to run?

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

Does Adsorbate Placement 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 Adsorbate Placement 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 Adsorbate Placement use?

Adsorbate Placement 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.

How many tokens does Adsorbate Placement use?

About 3k tokens (SKILL.md is roughly 12k 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 Adsorbate Placement?

Skills that share tags, products or a category with Adsorbate Placement: Hypothesis Generation (spacering-net/codeg, 3.9k stars), GitHub Deep Research (bytedance/deer-flow, 84k stars), Nature Paper Card (Yuan1z0825/nature-skills, 47k stars) and Content Research Writer (weapp-tailwindcss/weapp-tailwindcss, 1.9k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Adsorbate Placement?

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.