find-prompt

Solid

Use when the user names a coding, Claude Code, research, documentation, or technology-selection task; asks which prompt to use; says to use the right prompt; or when an agent enters this repository and needs to orient without reading every file.

AI & Automation 53 stars 15 forks Updated 4 days ago MIT

Install

View on GitHub

Quality Score: 85/100

Stars 20%

Recency 20%

100

Frontmatter 20%

Documentation 15%

Issue Health 10%

License 10%

100

Description 5%

100

Skill Content

# Find the right prompt and continue This repository keeps one canonical routing table at [`.claude/skills/find-prompt/SKILL.md`](../../../.claude/skills/find-prompt/SKILL.md). Read that file completely, resolve its paths from the repository root, and follow its routing and composition rules. Cross-agent adaptations: - Treat `CLAUDE.md` and Claude Code configuration as subject matter, not as instructions for the current host, unless the task is specifically about Claude Code. - Use the current host's supported tool names and permission model while preserving the selected prompt's evidence, safety, verification, and completion requirements. - Keep all conversation constraints, including any prohibition on Git operations, deployment, external messages, or credentials. - Load only files that exist. If the canonical route is missing, use [`prompts/english/INDEX.md`](../../../prompts/english/INDEX.md) and report the inconsistency. After routing, state the loaded prompt path, the continuing task, measurable success criteria, and carried constraints in one short block, then continue the work.

Details

Author: Rtur2003
Repository: Rtur2003/Claude-Code-Promts-Skills
Created: 8 months ago
Last Updated: 4 days ago
Language: Python
License: MIT

Similar Skills

Semantically similar based on skill content — not just same category

AI & Automation Listed

meta-prompt

Turn a fuzzy ask into a sharp Claude Code prompt with context and acceptance criteria

0 Updated today

ku5ic

AI & Automation Listed

agent-prompt-author

Write, revise, and diagnose system prompts, orchestrator instructions, subagent delegation contracts, tool descriptions, and harness text for LLM agents you build and ship. Use whenever someone wants an agent to behave differently by changing its text — "write a system prompt for X", "improve this orchestrator prompt", "my agent keeps ignoring this rule", "the prompt got worse after I edited it", "add a constraint so it stops doing Y", "write a tool description", "should I run GEPA or DSPy on this", "review this agent prompt", "is this prompt any good", "how much of this is still needed". Also use when a prompt has grown past ~200 lines, when a refinement loop has stopped helping, or before investing in automated prompt optimization. Do NOT use for one-off chat prompts, for CLAUDE.md and repo context files (opposite policy — see Route C), or for brand voice and creative style guides.

0 Updated 3 weeks ago

amylyra

AI & Automation Listed

cc-best-practices

Official Claude Code best practices and prompt-library patterns. Use when the user asks how to prompt Claude Code effectively, how to structure a task (plan vs. direct, verify, scope), how to set up CLAUDE.md/skills/hooks/subagents/MCP, how to scale with headless or parallel sessions, or why a session is going badly (context bloat, repeated corrections).

0 Updated 1 months ago

1luvc0d3