ralph-loop-template

Solid

Generate an iterable checklist PROMPT file for Ralph Loop from a plan file or the current conversation, and output the ready-to-run /ralph-loop command.

Data & Documents 17 stars 1 forks Updated 2 weeks ago MIT

Install

View on GitHub

Quality Score: 82/100

Stars 20%
42
Recency 20%
90
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
80
License 10%
100
Description 5%
100

Skill Content

# Ralph Loop Template ## Input ```text $ARGUMENTS ``` ## Instructions ### Step 1: Gather Plan **If an argument is provided**: Read the file to understand the plan content. **If no argument**: Search for a plan in the following order: 1. Search for plan files in the project root: `PLAN.md`, `plan.md`, `PLAN-*.md`, `plan-*.md`, `TODO.md`, `prd.md`, `PRD.md` - 1 found → Use it (inform the user which file was detected) - Multiple found → Present the list and ask for selection - 0 found → Proceed to next step 2. Use the plan discussed in the current conversation context. 3. If no plan exists in the conversation context, ask the user to describe the plan. ### Step 2: Identify Project Environment Collect project-specific information to embed in the PROMPT file. **Search for agent/project configuration files** in the following priority order: 1. `CLAUDE.md` (Claude Code) 2. `.cursorrules` (Cursor) 3. `.windsurfrules` (Windsurf) 4. `AGENTS.md`, `COPILOT.md`, `GEMINI.md` If a config file is found, extract: - Verification commands: Combine build, test, lint into a single chain (e.g., `npm run lint && npm run build && npm test`) - Key code style rules (items to insert into the PROMPT's absolute rules `{AGENT_RULES}`, max 3) **If no config file is found**: Infer from project structure: - `package.json` → npm/yarn commands - `Makefile` / `Justfile` → make/just commands - `Cargo.toml` → cargo commands - `pyproject.toml` / `setup.py` → python toolchain - If undetectable,...

Details

Author
2ykwang
Repository
2ykwang/agent-skills
Created
6 months ago
Last Updated
2 weeks ago
Language
Python
License
MIT

Integrates with

Similar Skills

Semantically similar based on skill content — not just same category