create-pr
- Repo stars 0
- Author updated Live
- Author repo skills-registry
- Domain
- Engineering
- Compatible agents
-
- Claude Code
- Cursor
- Cline
- Codex
- Windsurf
- Gemini CLI
- +20
- Trust score
- 88 / 100 · community maintained
- Author / version / license
- @tomevault-io · no license declared
- Token usage
- Lean
- Setup complexity
- Guided setup
- External API key
- Not required
- Operating systems
- Unspecified (assume cross-platform)
- Runtime requirements
- No special requirements
- Permissions
-
- Read-only
- Write / modify
- Shell exec
- Network behavior
- Local-only
- Install commands
- 26 variants
Profile is derived at build time from SKILL.md and install vectors. Subject to drift from author intent.
Heads up: 未限定 allowed-tools，默认拥有全部工具权限。
---
name: create-pr
description: Use after implementation is complete — stages, commits, pushes, and opens PRs for all affected s…
category: engineering
runtime: no special runtime
---
# create-pr output preview
## PART A: Task fit
- Use case: Use after implementation is complete — stages, commits, pushes, and opens PRs for all affected services. Triggers: "create PR", "open pull request", "push the code", "ready for review Use when this capability is needed..
- Inputs: target material, constraints, expected output, and acceptance criteria.
- Evidence boundary: follow “Phase 1 — Bootstrap / Phase 2 — Execute Workflow” and do not present inference as author intent.
## PART B: Execution result
- **01** The card summarizes the use case; runtime output centers on “Use after implementation is complete — stages, commits, pushes, and opens PRs for all affected services. Triggers: "create PR", "open pull request", "push the code", "ready for review Use when this capability is needed.”.
- **02** When the source has headings, the agent prioritizes “Phase 1 — Bootstrap / Phase 2 — Execute Workflow” so the result follows the author’s structure.
- **03** Typical output includes task judgment, concrete steps, required commands or file edits, validation, and follow-up options.
- **04** Risk context follows the fingerprint: read files, write/modify files, run shell commands; mostly runs locally; usually needs no extra API key.
## Running Rules
- read files, write/modify files, run shell commands; mostly runs locally; usually needs no extra API key.
- Validate with a small sample before expanding scope.
- Return the result, validation criteria, and next iteration options.The source mentions slash commands such as `/jlu-create-pr`, `/plugin`; use them first when your agent supports command triggers.
Name target files or source material, expected output, forbidden changes, and whether network or shell access is allowed. Permission fingerprint: read files, write/modify files, run shell commands.
Start with a small task and check whether the result follows “Phase 1 — Bootstrap / Phase 2 — Execute Workflow”. Inspect diffs, logs, previews, or tests before expanding scope.
Confirm the final output includes a concrete result, evidence, and next action. If it stays generic, tighten inputs, boundaries, and acceptance criteria.
---
name: create-pr
description: Use after implementation is complete — stages, commits, pushes, and opens PRs for all affected s…
category: engineering
source: tomevault-io/skills-registry
---
# create-pr
## When to use
- Use after implementation is complete — stages, commits, pushes, and opens PRs for all affected services. Triggers: "cr…
- Use it when the task has clear inputs, repeatable steps, and validation criteria.
## What to provide
- Target material, scope, expected result, and forbidden changes.
- Whether network, commands, file writes, or external services are allowed.
## Execution rules
- Organize steps around “Phase 1 — Bootstrap / Phase 2 — Execute Workflow” and keep inference separate from source facts.
- read files, write/modify files, run shell commands; mostly runs locally; usually needs no extra API key.
- Validate with a small sample before expanding the task.
## Output requirements
- Return the deliverable, key evidence, validation method, and next action.
- Mark missing information as unknown; do not invent commands, platforms, or dependencies.The author source anchors workflow facts; repository files anchor sources and commands; Fluxly only adds fit, limitations, and quality judgment.
skill "create-pr" {
input -> user goal + target files + boundaries + acceptance criteria
context -> Phase 1 — Bootstrap / Phase 2 — Execute Workflow
rules -> SKILL.md triggers / order / output contract
runtime -> no special runtime | read files, write/modify files, run shell commands | mostly runs locally
guardrails -> usually needs no extra API key + small-sample validation + diff/log review
output -> copyable result + checklist + next iteration
}You are the orchestrator for the /jlu-create-pr command.
Phase 1 — Bootstrap
Resolve plugin root. Try in order:
- Go up 2 levels from this skill's directory (plugin install at
<plugin-root>/skills/create-pr/SKILL.md). ~/.claude/jelou/(manual installation).
If neither resolves, stop with: "Plugin root not found. Ensure jelou-spec-plugin is installed."
Runtime contract (Claude Code). The workflow file uses OpenCode names:
- Workflow says
question→ invokeAskUserQuestion(deferred — preload below). - Workflow says
task→ invokeAgent(subagent dispatch). - Never narrate questions as plain text. Never skip a prescribed question.
Run these in parallel (single tool-call message — do NOT serialize):
Bash:<plugin-root>/bin/check-update.sh 2>/dev/null || echo SKIPPEDRead:<plugin-root>/jelou/workflows/create-pr.mdToolSearch:select:AskUserQuestion(max_results: 1) — mandatory before anyAskUserQuestioncall.
Update banner. If the bash output starts with UPDATE_AVAILABLE <local> <remote>, print one line and continue:
[jlu] v<remote> available (you have v<local>). Run: /plugin update jlu@jelou-spec-plugin
If the output is UP_TO_DATE or SKIPPED, continue silently. Update-check failures must never block the workflow.
ToolSearch fallback. If ToolSearch returns zero matches for AskUserQuestion, fall back to printing each question as plain text and warn the user that the skill cannot run correctly without AskUserQuestion in this Claude Code version.
Phase 2 — Execute Workflow
Follow the workflow file you just read. Do NOT spawn a sub-agent — execute the workflow yourself in this session.
The argument is {argument}. The plugin root is the path resolved above. The current working directory is {cwd}.
Source: cristian-pisco/jelou-spec-plugin — distributed by TomeVault.
Decide Fit First
Design Intent
How To Use It
Boundaries And Review