Agent skill · Backend & API

dev-buddy-once

Run a single task using a specific AI provider and model. Supports subscription, API, and CLI presets.

majiayu000github.com/majiayu000GitHub ↗
claude-codecan modify filesMIT
Install
npx skills add majiayu000/claude-skill-registry --skill dev-buddy-once --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 2
SKILL.md size: 8 KB
Bundled scripts: none
Allowed tools: ReadBashTaskTaskOutputAskUserQuestionGlobGrep
Path: skills/ai-llm/dev-buddy-once/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 534
Language: HTML

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

# One-Shot Task Runner Run a single arbitrary task using any configured AI provider — no pipeline, no reviews, no orchestration. **Usage:** `/dev-buddy-once use <provider> [model <model>] <task description>` **Examples:** ``` /dev-buddy-once use minimax M2.5 model to help me design a new UI /dev-buddy-once use codex o3 model to refactor the auth module /dev-buddy-once use anthropic-subscription sonnet model to explain the codebase /dev-buddy-once use minimax to analyze performance bottlenecks ``` --- ## Step 1: Parse Arguments Extract three pieces from the user's message: - **Provider name** — the preset name (e.g., "minimax", "codex", "anthropic-subscription") - **Model** — the model identifier (e.g., "M2.5", "o3", "sonnet") - **Task** — everything else (the actual work to do) The user's message follows the skill trigger. Common patterns: - `use <provider> <model> model to <task>` - `use <provider> model <model> to <task>` - `use <provider> to <task>` (model omitted — will default) --- ## Step 2: Resolve Preset List available presets: ```bash bun -e " import { readPresets } from '${CLAUDE_PLUGIN_ROOT}/scripts/preset-utils.ts'; const presets = readPresets(); console.log(JSON.string

What's inside
Steps it walks through
  1. Step 1: Parse Arguments
  2. Step 2: Resolve Preset
  3. Step 3: Route by Provider Type
  4. Subscription (type: "subscription")
  5. API (type: "api")
  6. CLI (type: "cli")
  7. Step 4: Report Results
  8. Success (exit code 0)
  9. Validation Error (exit code 1)
  10. Execution Error (exit code 2)
  11. Timeout (exit code 3)
  12. Error Handling
  13. Anti-Patterns
Ships with 1 file
  • metadata.json
Commands it runs
bun -e "
import { readPresets } from '${CLAUDE_PLUGIN_ROOT}/scripts/preset-utils.ts';
const presets = readPresets();
bun "${CLAUDE_PLUGIN_ROOT}/scripts/one-shot-runner.ts" \
More from claude-skill-registry
All skills →
About this skill
What does the dev-buddy-once skill do?

Run a single task using a specific AI provider and model. Supports subscription, API, and CLI presets.

How do I install it?

Run `npx skills add majiayu000/claude-skill-registry --skill dev-buddy-once --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going