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

Catgo Campaign Loop

by Hello-QM in Hello-QM/catgo-LRG

Run and resume the CatGo md-orchestration poll loop — delegate each poll to a subagent (keep main context lean), verify convergence by force, auto-advance each converged species per-species…

AGPL-3.0Auto-check passedAgent Workflows

Install Catgo Campaign Loop

skills CLI
$ npx skills add Hello-QM/catgo-LRG --skill catgo-campaign-loop -a claude-code

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

GitHub CLI
$ gh skill install Hello-QM/catgo-LRG catgo-campaign-loop --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/server/catgo/workflow/skills/catgo-campaign-loop .claude/skills/catgo-campaign-loop && 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
catgo-campaign-loop
GitHub stars
205
Token cost
~985 tokens
SKILL.md length
488 words
Files
1
Skills in repo
75
Repo updated
First seen
Licence
AGPL-3.0

At a glance

Run and resume the CatGo md-orchestration poll loop — delegate each poll to a subagent (keep main context lean), verify convergence by force, auto-advance each converged species per-species…

  • Works in 7 steps: Read plan.md + active STATUS.md (keep… → python poll.py --project --ssh — updates… → For finished calcs: a scheduler DONE ≠… → …
  • Resuming a campaigns job-watch loop
  • SKILL.md covers RULE — delegate each poll to a…, Each wake, Resuming (fresh agent / after… and Unattended (fully-ended session)
  • Calls python

What it does

Catgo Campaign Loop is an agent skill from Hello-QM/catgo-LRG. Run and resume the CatGo md-orchestration poll loop — delegate each poll to a subagent (keep main context lean), verify convergence by force, auto-advance each converged species per-species (pipeline, not barrier), and resume a campaign from disk after context compaction / new session. Use when driving or resuming a campaign's job-watch loop. Pairs with catgo-campaign.

Its SKILL.md is about 990 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 Agent Workflows, covering Subagents and Context engineering. 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

  • Resuming a campaigns job-watch loop
  • Tasks that involve Subagents
  • Tasks that involve Context engineering

Example prompts

  • “/catgo-campaign-loop”

Requirements

  • Python 3

Workflow steps

7 steps, taken from the first numbered list in SKILL.md.

  1. Read plan.md + active STATUS.md (keep working context lean).
  2. python poll.py --project --ssh — updates STATUS: queued via squeue;
  3. For finished calcs: a scheduler DONE ≠ "the science succeeded" — open the remote
  4. **Auto-advance each newly-converged calc to its NEXT plan step — per species, PIPELINE,
  5. Stage/decision point → python aggregate.py --project --plot → summary → checkpoint.
  6. Group meeting → python make_report.py --project --occasion groupmeeting.
  7. Unhandleable problem → write it to STATUS/LESSONS and stop (surface to the user).

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

    Shell commands in SKILL.md call:

    • 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

Catgo Campaign Loop loads about 985 tokens when it runs. Until then it costs about 98 tokens; SKILL.md has 488 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~98
When it runs · the whole SKILL.md, loaded when a task matches
~985

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). 488 words, ~985 tokens.

Download SKILL.mdSave it as .claude/skills/catgo-campaign-loop/SKILL.md (or your agent's skills folder).
name
catgo-campaign-loop
description
Run and resume the CatGo md-orchestration poll loop — delegate each poll to a subagent (keep main context lean), verify convergence by force, auto-advance each converged species per-species (pipeline, not barrier), and resume a campaign from disk after context compaction / new session. Use when driving or resuming a campaign's job-watch loop. Pairs with catgo-campaign.

catgo-campaign-loop — drive & resume the poll loop

TL;DR: Human-triggered ~10-min loop. Delegate each poll to a subagent (compact summary back). Verify convergence by force. Auto-advance each converged species to its next step (per species, not a barrier). State is on disk → any agent resumes.

RULE — delegate each poll to a subagent

Do NOT run poll/verify inline. Dispatch ONE subagent (opus) to run steps 1-3 (poll, ssh-read OUTCAR, verify, write result.md/STATUS/LESSONS) and return a compact summary only (one line per calc; no raw OUTCAR/OSZICAR/ssh dumps) — over a long run the verbose output would fill the main context toward 1M. Gates stay in the main agent (input-file gate, checkpoints): the subagent reports, the main agent shows the user + acts. The subagent must not submit/cancel jobs or touch the :8000 backend.

Each wake

  1. Read plan.md + active STATUS.md (keep working context lean).
  2. python poll.py --project <dir> --ssh <alias> — updates STATUS: queued via squeue; once a job leaves the queue, sacct gives the terminal verdict (COMPLETED→DONE; FAILED/TIMEOUT/OUT_OF_MEMORY/CANCELLED→FAILED; exit_code recorded).
  3. For finished calcs: a scheduler DONE ≠ "the science succeeded" — open the remote outputs and verify real convergence by FORCES: max atom < |EDIFFG| (force, NOT dE; the "kinetic energy error for atom" EATOM line is benign). Write energy_eV + max_force_eVA into result.md; on real failure (DONE-but-unconverged, or FAILED) record cause + fix in LESSONS.md.
  4. Auto-advance each newly-converged calc to its NEXT plan step — per species, PIPELINE, not a barrier. A converged geo_opt immediately triggers that species' next step (e.g. freq in a Gibbs study) from its CONTCAR; don't wait for siblings, don't wait for a user reminder. Render next-step inputs → input-file gate → submit_calc.py. ⛔ INPUT-FILE GATE (hard rule): "auto-advance" means auto-PREP, NOT auto-submit. Sync the converged CONTCAR and the next-step INCAR to the LOCAL folder, tell the user the exact LOCAL paths of INCAR + CONTCAR, and WAIT — the user checks/edits the files on disk. Submit ONLY after the user confirms. Do NOT push to the CatGO viewer as a substitute, and NEVER auto-submit. (YOLO waives.)
  5. Stage/decision point → python aggregate.py --project <dir> --plot → summary → checkpoint.
  6. Group meeting → python make_report.py --project <dir> --occasion groupmeeting.
  7. Unhandleable problem → write it to STATUS/LESSONS and stop (surface to the user).
Show full SKILL.md (128 more words)Show less

Resuming (fresh agent / after compaction)

State lives ON DISK, not in context — a campaign survives compaction, a new session, or a different agent. To resume with zero conversation history:

  1. Invoke the catgo-campaign skill; identify the project dir.
  2. Read in order: README.md → plan.md (+ each calc/<stage>/plan.md) → cluster.md → every calc/**/STATUS.md → result.md files → LESSONS.md = done / running / next.
  3. Continue the loop (delegate each poll to a subagent). Keep the discipline: flush results/STATUS/LESSONS/plan to files as it happens — never hold campaign state only in context.

Unattended (fully-ended session)

ScheduleWakeup dies with the session. For a campaign that must advance without you, register a cron routine that wakes a fresh agent on a schedule to poll the project (it resumes from disk). Otherwise the user says "resume <project>" in a new session.

© 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 server/catgo/workflow/skills/catgo-campaign-loop of Hello-QM/catgo-LRG.

Open the folder on GitHubat commit fd6291b

Compare with similar skills

Catgo Campaign Loop 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.

Catgo Campaign Loop compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Catgo Campaign Loop this skillHello-QM/catgo-LRG205—~985Automated safety check: PassAGPL-3.0
Claude Statusbarleeguooooo/claude-code-usage-bar377—~2.5kAutomated safety check: PassMIT
Badstephenleo/bmad-autonomous-development107—~7.7kAutomated safety check: PassMIT
Analyze Trajectoryyologdev/yoyo-evolve1.9k—~3.6kAutomated safety check: PassMIT
Code Context Slicingtrailofbits/skills7.4k—~2.1kAutomated safety check: PassCC-BY-SA-4.0
MoAI Foundation Coremodu-ai/moai-adk1.2k—~5kAutomated safety check: PassApache-2.0

Similar skills

  • Claude Statusbar

    leeguooooo/claude-code-usage-bar

    Manage cs (claude-statusbar) — switch theme/style/density, override severity colors, preview combinations, run doctor, reset config, install, upgrade (cs upgrade — the only supported upgrade path)…

    377 GitHub stars~2.5k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed

  • Bad

    stephenleo/bmad-autonomous-development

    BMad Autonomous Development — orchestrates parallel story implementation pipelines.

    107 GitHub stars~7.7k tokensUpdated 5 mo ago
    Agent WorkflowsAuto-check passed

  • Analyze Trajectory

    yologdev/yoyo-evolve

    Diagnoses a recurring failure such as a stuck task, repeated CI error or frequent reverts by sending sub-agents through the logs and returning one root-cause diagnosis.

    1.9k GitHub stars~3.6k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed

  • Code Context Slicing

    trailofbits/skills

    Official

    Picks a small, graph-based slice of source with Trailmark and hands a focused code task to a smaller or local model without exposing the whole repository.

    7.4k GitHub stars~2.1k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed

  • MoAI Foundation Core

    modu-ai/moai-adk

    Reference for MoAI-ADK's core development principles: TRUST 5 quality gates, SPEC-first domain-driven workflow, agent delegation and token budgeting.

    1.2k GitHub stars~5k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed

  • Cc Dev Agent

    sangrokjung/claude-forge

    A skill your agent uses when starting Claude Code projects, writing CLAUDE.md/spec.md, dispatching subagents, or requesting Agent Teams parallel development.

    850 GitHub stars~771 tokensUpdated 1 mo ago
    Agent WorkflowsAuto-check passed

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 16 days ago
    Auto-check passed

  • Lammps Deepmd

    Hello-QM/catgo-LRG

    Run LAMMPS molecular dynamics with DeePMD-kit machine learning potentials.

    205 GitHub starsUsed in 1 repo~1k tokens
    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 16 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 16 days ago
    Auto-check passed

  • Adsorbate Placement

    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.

    205 GitHub stars~3k tokensUpdated 16 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 16 days ago
    Auto-check passed

Categories

Questions about Catgo Campaign Loop

What does Catgo Campaign Loop do?

Run and resume the CatGo md-orchestration poll loop — delegate each poll to a subagent (keep main context lean), verify convergence by force, auto-advance each converged species per-species…. Catgo Campaign Loop is an agent skill from Hello-QM/catgo-LRG. Run and resume the CatGo md-orchestration poll loop — delegate each poll to a subagent (keep main context lean), verify convergence by force, auto-advance each converged species per-species (pipeline, not barrier), and resume a campaign from disk after context compaction / new session.

When should I use Catgo Campaign Loop?

Catgo Campaign Loop fits situations like: resuming a campaigns job-watch loop; tasks that involve Subagents; tasks that involve Context engineering.

How do I install Catgo Campaign Loop in Claude Code?

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

How do I install Catgo Campaign Loop in Codex?

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

Can I use Catgo Campaign Loop 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 catgo-campaign-loop -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/catgo-campaign-loop, .gemini/skills/catgo-campaign-loop, .github/skills/catgo-campaign-loop and .opencode/skills/catgo-campaign-loop in your project.

What does Catgo Campaign Loop need to run?

Going by SKILL.md and its folder, Catgo Campaign Loop needs the command-line tools its instructions call (python). Our summary lists: Python 3.

Does Catgo Campaign Loop 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 Catgo Campaign Loop 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 Catgo Campaign Loop use?

Catgo Campaign Loop 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 Catgo Campaign Loop use?

About 985 tokens (SKILL.md is roughly 3.9k 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 Catgo Campaign Loop?

Skills that share tags, products or a category with Catgo Campaign Loop: Claude Statusbar (leeguooooo/claude-code-usage-bar, 377 stars), Bad (stephenleo/bmad-autonomous-development, 107 stars), Analyze Trajectory (yologdev/yoyo-evolve, 1.9k stars) and Code Context Slicing (trailofbits/skills, 7.4k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Catgo Campaign Loop?

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.