From prompt-language
This skill should be used when the user asks to 'validate a flow', 'check my flow', 'lint this flow', 'is this flow correct', 'flow errors', 'flow warnings', or wants to analyze a prompt-language flow for issues before executing it.
npx claudepluginhub 45ck/prompt-language --plugin prompt-languageThis skill is limited to using the following tools:
Parse, lint, and score a prompt-language flow to find issues before execution.
Guides Next.js Cache Components and Partial Prerendering (PPR) with cacheComponents enabled. Implements 'use cache', cacheLife(), cacheTag(), revalidateTag(), static/dynamic optimization, and cache debugging.
Guides building MCP servers enabling LLMs to interact with external services via tools. Covers best practices, TypeScript/Node (MCP SDK), Python (FastMCP).
Generates original PNG/PDF visual art via design philosophy manifestos for posters, graphics, and static designs on user request.
Parse, lint, and score a prompt-language flow to find issues before execution.
Determine the flow source:
example.flow or any .flow file in the current directoryRun the validation script:
node <plugin-dir>/skills/flow-validate/validate.mjs [file-or-stdin]
Or pipe flow text to it:
echo '<flow text>' | node <plugin-dir>/skills/flow-validate/validate.mjs
Where <plugin-dir> is the directory containing this skill (find it via Glob for skills/flow-validate/validate.mjs).
Report the results to the user:
If there are warnings, suggest specific fixes for each one.
break or continue used outside a while/until/retry/foreachretry block has no run node -- retry re-loops on command_failed${varName} referenced but never defined by a let/var nodecommand_failed) but body has no run nodeGoal: line foundflow: blockWhen many warnings exist, report in this priority order:
Parse: pass/fail + countLint: pass/fail + countComplexity: score + short rationaleTop 3 fixes: concrete edits with expected impact.flow files exist and no argument is given, ask which file to validate.