Execute qualquer Skill no Manus
com um clique

Execute qualquer Skill no Manus com um clique

oh-my-setting-ops

Estrelas2

Forks0

Atualizado10 de julho de 2026 às 16:12

Maintain an oh-my-setting install from chat. Use when the user asks to check install status, update oh-my-setting ("업데이트 해줘"), run doctor ("닥터 돌려줘", "설치 상태 확인"), clean legacy skill links, fix duplicate skill picker entries, regenerate local snapshots, or explain what the installed agent rules/scripts are doing. For the shared repo dashboard ("what's the current state", "oms state") use agent-harness instead.

Instalação

Instalar com Codex ou Claude Copie este prompt, cole no Codex, Claude ou outro assistente e deixe que ele revise a página da skill e instale para você.

Executar no Manus

Fonte

eightmm

eightmm/oh-my-setting

Abrir repositório GitHub Ver repositórios do creator

Download

Executar no Manus

Ocupações relacionadasSOC

Baseado na classificação ocupacional SOC

Administradores de redes e sistemas de computadorInformática e Matemática·SOC 15-1244

SKILL.md

readonly

name

oh-my-setting-ops

description

Goal: the user asks in chat; the agent runs local scripts. Do not tell the user to run scripts manually unless a command is impossible from the current agent.

Rules

Use local files and shell commands only. Do not use MCP servers, app connectors, or plugin connector tools.
Start with ~/.oh-my-setting/scripts/status.sh or repo-local scripts/status.sh when orienting; it reports install links, tools, active task state, and auto-update state.
For install health, run doctor.sh; for skill picker duplicates, run skill-doctor.sh.
For legacy oh-my-setting symlink cleanup, run cleanup.sh --dry-run first, summarize exactly what would be removed, then run cleanup.sh --apply when the user asked for cleanup/fix or already approved the current task.
cleanup.sh --apply only removes known oh-my-setting legacy symlinks and backup skill symlinks. Do not delete unrelated third-party plugins, caches, regular files, or directories unless the user explicitly approves that separate scope.
After cleanup or update, rerun doctor.sh and report remaining warnings.
Update/uninstall/plugin removal must run from the canonical receipt owner; foreign checkouts refuse before pulling or mutating global state. Use the canonical root printed by status.sh.
Treat Auto Update: stale as historical state only; update/check again from the canonical checkout before reporting current update health.
If the current session still shows stale skills, tell the user that the UI may cache skill lists until a new agent session starts.

Common Requests

Status:

~/.oh-my-setting/scripts/status.sh

Update and verify:

~/.oh-my-setting/scripts/update.sh

Install health:

~/.oh-my-setting/scripts/doctor.sh

Duplicate $skill entries or stale skills:

~/.oh-my-setting/scripts/cleanup.sh --dry-run
~/.oh-my-setting/scripts/cleanup.sh --apply
~/.oh-my-setting/scripts/skill-doctor.sh

Regenerate local snapshots:

~/.oh-my-setting/scripts/write-machine-snapshot.sh
~/.oh-my-setting/scripts/generate-slurm-skill.sh

Output

Use compact prose. Include commands run and whether doctor/skill-doctor passed. Do not add a fixed changed/verified/not-verified block for questions or design explanations.

Mais deste repositório

mesmo repositório

agent-harness

eightmm/oh-my-setting

Shared multi-agent harness state and coordination for Codex, Claude Code, and Antigravity. Use for repo resume/state, shared memory or active-task handoff, plan claims/recovery, fail-ledger checks, stale `.oms` cleanup, role/executor setup, local provider calls or write delegation, patch admission/landing, artifact provenance, and prior-session handoff.

2026-07-122

chem-bio-ml

eightmm/oh-my-setting

Discovery-focused chem-bio ML guardrails for small molecules, molecular 3D and physics, proteins and variants, biomolecular interactions, peptides and antibodies, reactions and synthesis, generative design, cellular omics and phenotypic profiling, and biomedical networks. Use before writing, reviewing, evaluating, or training on RDKit/SMILES/SELFIES, QSAR/ADMET, quantum or force data, MMseqs2/MSA/protein language models, PDB/AlphaFold/DMS, docking/DTI/PPI, peptide-MHC or antibody data, reaction/retrosynthesis/yield data, molecular or protein generation, RNA/oligonucleotide/CRISPR, single-cell perturbation/Cell Painting, or biomedical knowledge graphs. Enforce domain splits, leakage checks, label semantics, baselines, metrics, calibration, applicability domain, and provenance.

2026-07-122

ml-training

eightmm/oh-my-setting

PyTorch training correctness for optimizers and schedules, distributed/DDP, variable-size masked losses, checkpoint save/load, CUDA runtime settings, and equivariant model checks. Use when writing or reviewing training loops, optimizer/scheduler setup, multi-GPU code, loss reduction, or checkpoints.

2026-07-122

peer-review

eightmm/oh-my-setting

Multi-agent code review. Use when the user explicitly requests independent verification, cross-agent/council review, or a release go/no-go or requested ML pre-training gate needs several independent reviewers. High-risk changes alone do not require this skill.

2026-07-122

research-method

eightmm/oh-my-setting

Hypothesis-driven loop for ML and scientific experiments. Use to turn a question into a falsifiable hypothesis, design the smallest disconfirming run, pre-register prediction/baseline/metric, interpret results, coordinate experiment claims, reproduce or compare runs, or trace an output to its run.

2026-07-122

slurm-hpc

eightmm/oh-my-setting

Slurm/HPC workflow helper. Use when working on clusters, partitions, nodes, sbatch/srun jobs, GPU/CPU allocations, queues, logs, checkpoints, or any resource-heavy command — e.g. "submit the job", "check the queue", "잡 돌려줘", "큐 확인", "GPU 몇 장", "학습 돌려줘" on a cluster; also digesting a long job log (job-digest, "로그 요약") and reconciling finished Slurm jobs into shared state (run-reconcile, sacct). Reads local cluster reference when generated.

2026-07-122

name

oh-my-setting-ops

description

Goal: the user asks in chat; the agent runs local scripts. Do not tell the user to run scripts manually unless a command is impossible from the current agent.

Rules

Use local files and shell commands only. Do not use MCP servers, app connectors, or plugin connector tools.
Start with ~/.oh-my-setting/scripts/status.sh or repo-local scripts/status.sh when orienting; it reports install links, tools, active task state, and auto-update state.
For install health, run doctor.sh; for skill picker duplicates, run skill-doctor.sh.
For legacy oh-my-setting symlink cleanup, run cleanup.sh --dry-run first, summarize exactly what would be removed, then run cleanup.sh --apply when the user asked for cleanup/fix or already approved the current task.
cleanup.sh --apply only removes known oh-my-setting legacy symlinks and backup skill symlinks. Do not delete unrelated third-party plugins, caches, regular files, or directories unless the user explicitly approves that separate scope.
After cleanup or update, rerun doctor.sh and report remaining warnings.
Update/uninstall/plugin removal must run from the canonical receipt owner; foreign checkouts refuse before pulling or mutating global state. Use the canonical root printed by status.sh.
Treat Auto Update: stale as historical state only; update/check again from the canonical checkout before reporting current update health.
If the current session still shows stale skills, tell the user that the UI may cache skill lists until a new agent session starts.

Common Requests

Status:

~/.oh-my-setting/scripts/status.sh

Update and verify:

~/.oh-my-setting/scripts/update.sh

Install health:

~/.oh-my-setting/scripts/doctor.sh

Duplicate $skill entries or stale skills:

~/.oh-my-setting/scripts/cleanup.sh --dry-run
~/.oh-my-setting/scripts/cleanup.sh --apply
~/.oh-my-setting/scripts/skill-doctor.sh

Regenerate local snapshots:

~/.oh-my-setting/scripts/write-machine-snapshot.sh
~/.oh-my-setting/scripts/generate-slurm-skill.sh

Output

Use compact prose. Include commands run and whether doctor/skill-doctor passed. Do not add a fixed changed/verified/not-verified block for questions or design explanations.