develop-no-test

Étoiles0

Forks0

Mis à jour2 juillet 2026 à 11:57

Like /develop, but skips test-writer invocation and post-impl verification (for repos without a test suite — see ADR-014 §12)

Installation

Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.

Exécuter dans Manus

Source

sugiyama34

sugiyama34/fast_suisho

Ouvrir le dépôt GitHub Voir les dépôts du créateur

Téléchargement

Exécuter dans Manus

Métiers associésSOC

Basé sur la classification professionnelle SOC

Développeurs de logicielsProfessions informatiques et mathématiques·SOC 15-1252

SKILL.md

readonly

name	develop-no-test
description	Like /develop, but skips test-writer invocation and post-impl verification (for repos without a test suite — see ADR-014 §12)
allowed-tools	Agent, Bash, Read, Edit, Write, Glob, Grep
argument-hint	<feature description>

Thin alias for /develop --no-test.

Invoke /develop --no-test $ARGUMENTS directly. The parent skill handles the no-test mode (see ADR-014 §12 and .claude/skills/develop/SKILL.md Phase 2.NT).

Plus depuis ce dépôt

même dépôt

create-pr

sugiyama34/fast_suisho

Commit remaining changes, push the branch, open a pull request, and run Codex review

2026-07-030

develop

sugiyama34/fast_suisho

Full development cycle — plan a feature, implement it, and open a PR

2026-07-030

resolve-review

sugiyama34/fast_suisho

Process unhandled PR review comments on the current branch's open PR — answer questions, modify code, or push back

2026-07-030

experiment

sugiyama34/fast_suisho

Run deep-learning experiments as disciplined hypothesis tests — frame the question, set up a self-contained per-experiment folder, launch training/eval runs (confirming before heavy GPU jobs), track metrics, analyze results against a baseline, and write a human-readable report with tables and plots. Use this whenever the user is doing experimental ML work: launching or preparing a training/finetuning/sampling/eval run, an ablation, or a hyperparameter sweep; saying things like "let's try X and see if it helps," "does this change improve FID/accuracy/loss," "compare these two runs/checkpoints," "track this experiment," "analyze the results," or "write up what we found." Trigger even when the user doesn't say the word "experiment" but is clearly testing whether a change moves a metric, or wants results organized, compared, or reported reproducibly.

2026-07-020

finish-task

sugiyama34/fast_suisho

Post-merge cleanup — update main, prune the remote, and print one paste-ready block of follow-up commands

2026-07-020

grill-me

sugiyama34/fast_suisho

Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".

2026-07-020

Exécutez n'importe quel Skill en un clic