A tool for creating, checking, and deploying Apache Flink streaming SQL jobs from plain-language descriptions. Flink processes live data streams, while SQL is a language for describing data operations.

Use it for live-data pipelines such as windowed totals, running totals, top lists, duplicate removal, filtering, time-based joins, and Kafka topic-to-topic processing.

It checks jobs on a real Flink cluster so errors in time windows, watermarks, joins, or calculations are found before deployment.

How clementlemon02/text2flink configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to clementlemon02/text2flink. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/clementlemon02/text2flink/main/.claude/skills/flink-jobs/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/clementlemon02/text2flink

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/clementlemon02/text2flink/flink-jobs/github.svg)](https://agentmods.dev/skills/clementlemon02/text2flink/flink-jobs)

Your own site

<a href="https://agentmods.dev/skills/clementlemon02/text2flink/flink-jobs"><img src="https://agentmods.dev/badge/skills/clementlemon02/text2flink/flink-jobs/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/clementlemon02/text2flink/flink-jobs"><img src="https://agentmods.dev/badge/skills/clementlemon02/text2flink/flink-jobs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 138 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,069 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00138	$0.01069
Opus 5.5	$0.00055	$0.00428
Sonnet 5.5	$0.00028	$0.00214
Haiku 4.5	$0.00014	$0.00107

Measured 2mo ago against content hash 6d6b1c70e7e1, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

flink-jobs scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/flink-jobs/SKILL.md · 73 lines

How it starts

The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Authoring verified Apache Flink jobs

Streaming SQL fails silently: a wrong watermark or window compiles, runs, and quietly produces wrong numbers. Never hand the user hand-written Flink SQL as if it were correct. Instead use the text2flink MCP tools, which run the job on a real Flink cluster and return its actual output (or the real Flink error). Present only what the tools have verified.

Prerequisite

The text2flink MCP server must be connected, exposing three tools: generate_flink_job, ground_kafka_topic, deploy_to_kafka. If they are not available, tell the user to register it: claude mcp add text2flink -- python3 -m text2flink.mcp_server (host needs Flink + JDK 17; Kafka for the topic tools). Do not fall back to writing unverified SQL by hand.

Workflow

Get the schema.
- If the user references a live Kafka topic and you don't know its schema, call ground_kafka_topic with {topic, event_time} first. Use the returned source and sample_data directly in the next step.
- Otherwise, establish each source table: a name, columns as [[name, flinkType], ...], the event_time column, and watermark_delay_seconds. Ask the user only for what you can't reasonably infer.
Provide sample rows. Verification needs data. Include a few representative rows per source in sample_data ({source_name: [ {col: value, ...}, ... ]}). If the user gave none, synthesize a small, sensible sample that would exercise the request (e.g. two keys, a few events across two windows). TIMESTAMP columns accept either integer seconds (offset from a base) or a "yyyy-MM-dd HH:mm:ss.SSS" string.
Generate and verify. Call generate_flink_job with {request, sources, sample_data}.
- On ok: true: show the user interpreted_as (confirm you read the request correctly), the sql, and sample_output as evidence it ran. For anything ambiguous, confirm the interpretation before moving on.
- On ok: false: read the failure. stage: "understand" → the request was ambiguous or used an unsupported construct; reword and retry. stage: "execution" → read flink_error, fix the schema or interpretation, and retry. stage: "schema"/"sample_data" → fix the inputs. Do not present a failing job as a solution.

Read the full file on GitHub · 73 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2mo ago First seen · 73 lines · 138 tokens per session scan A 6d6b1c70e7e1

Subscribe to this mod's changes

flink-jobs is a skill published in the GitHub repository clementlemon02/text2flink (0 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 138 tokens to every session and 1,069 once invoked, about $0.0006 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Backend and APIs Data and AI LLM agentic flink mcp streaming text-to-sql

flink-jobs next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
flink-jobsclementlemon02/text2flink	Skill	0	3mo ago	Apache-2.0	A	138	Claude Code
backend-data-streamingj4flmao/agent-skills	Skill	38	3d ago	MIT	A	145	Claude Code, Codex
agentproto-llm-endpointagentproto/ts	Skill	9	today	Apache-2.0	A	77	Claude Code, Codex
openrouterbobmatnyc/claude-mpm-skills	Skill	78	3mo ago	MIT	B	32	Claude Code
ASCII Artagentic-in/elephant-agent	Skill	584	2mo ago	none	B	47	Claude Code, Codex
senior-data-engineerUCSB-NLP-Chang/Skill-Usage	Skill	49	7mo ago	none	A	100	Claude Code, Codex
llm-integrationLuuOW/meridian-mcp	Skill	0	24d ago	MIT	A	29	Claude Code, Codex

text2flink: Skill for Claude Code