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.
curl -O https://raw.githubusercontent.com/clementlemon02/text2flink/main/.claude/skills/flink-jobs/SKILL.mdgit clone --depth 1 https://github.com/clementlemon02/text2flinkWrote 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.
[](https://agentmods.dev/skills/clementlemon02/text2flink/flink-jobs)<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.
<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>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 | $0.00069 | $0.00535 |
| Sonnet 5 | $0.00028 | $0.00214 |
| Haiku 4.5 | $0.00014 | $0.00107 |
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 10d 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.
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_topicwith{topic, event_time}first. Use the returnedsourceandsample_datadirectly in the next step. - Otherwise, establish each source table: a
name,columnsas[[name, flinkType], ...], theevent_timecolumn, andwatermark_delay_seconds. Ask the user only for what you can't reasonably infer.
- If the user references a live Kafka topic and you don't know its schema, call
-
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_jobwith{request, sources, sample_data}.- On
ok: true: show the userinterpreted_as(confirm you read the request correctly), thesql, andsample_outputas 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"→ readflink_error, fix the schema or interpretation, and retry.stage: "schema"/"sample_data"→ fix the inputs. Do not present a failing job as a solution.
- On
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.
- 10d ago First seen · 73 lines · 138 tokens per session scan A 6d6b1c70e7e1
flink-jobs is a skill published in the GitHub repository clementlemon02/text2flink (0 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 138 tokens to every session and 1,069 once invoked, about $0.0007 per session on Opus 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.
Other skills, from other repositories
agentproto-llm-endpoint
Use the local LLM endpoint proxy (localhost:18090) — or your own gated public deployment — to route Claude Code / Claude SDK through custom providers (OpenRouter, Moonshot, Groq, ZAI) via an Anthropic-compatible gateway. Covers adapter-specific behaviors, auth patterns, proxy codenames, and common failure modes.
openrouter
OpenRouter unified AI API - Access 200+ LLMs through single interface with intelligent routing, streaming, cost optimization, and model fallbacks.
llm-integration
Claude and OpenAI API patterns, prompt design, context management, streaming, tool use, cost control, multi-model routing.
ASCII Art
Generate ASCII art using pyfiglet (571 fonts), cowsay, boxes, toilet, image-to-ascii, remote APIs (asciified, ascii.co.uk), and LLM fallback. No API keys required.
senior-data-engineer
World-class data engineering skill for building scalable data pipelines, ETL/ELT systems, real-time streaming, and data infrastructure. Expertise in Python, SQL, Spark, Airflow, dbt, Kafka, Flink, Kinesis, and modern data stack. Includes data modeling, pipeline orchestration, data quality, streaming quality…
serving-llms-vllm
Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism.