본문으로 건너뛰기
cccskills
무료GitHub에 공개

pipeline-check

Check that the scheduled data work behind the reports actually ran and produced something sensible: the daily reshaping scripts, the API pulls, the tables the reports read from. Use each morning before anyone opens a report, when a report looks wrong and nobody knows whether it is the data or the query, after a schema or API change, when a new audience or source is added to the pipeline, or when a scheduled job failed or finished suspiciously fast.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

실행 점수 미검증

설치 방법 보기

포함된 파일(1)

  • SKILL.md2.6 KB

SKILL.md(원문)

설치하기 전에 에이전트에게 전달되는 지시 내용을 확인할 수 있습니다.

Pipeline check

Goal

A broken or stale pipeline is found before anyone opens a report built on it, not after.

Procedure

  1. Check it ran at all, and when it finished. A job that did not run leaves yesterday's data in place, which reads as a quiet day rather than as a failure. This is the single most valuable check here.
  2. Check the output volume against normal. Row counts per audience and per table, against what that day of the week usually produces. A run that finished in a third of the usual time with a tenth of the rows succeeded technically and failed in every way that matters.
  3. Check the freshness of what it depends on. An upstream API that returned an empty response produces a clean run over nothing.
  4. Spot check the shape, not just the count. Nulls where there should be values, dates outside the expected window, an audience whose rows all landed on one site.
  5. Trace anything odd to the change that caused it. A schema change, a new audience, a source field renamed. memory/conventions/pipelines.md records what each job reads and writes.
  6. Say what is affected downstream: which reports and which audiences read the tables in question, so somebody knows who not to send a report to this morning.
  7. Draft the fix or the rerun and hold it, unless a rerun is safe, idempotent and recorded as such.

Boundaries

  • Never rerun a job that is not recorded as safe to rerun. A partial second run is worse than a missing one.
  • Never patch data by hand in a production table to make a report look right.
  • Never report a job as healthy on the basis that it exited without an error.
  • Never let a report go out on data you know is stale without saying so.
  • Keep personal and confidential data out of any log or message written while investigating.

What to record

Keep memory/conventions/pipelines.md current: what each scheduled job reads and writes, when it runs, what a normal output volume looks like, whether it is safe to rerun, and which reports depend on it. Add each failure and its cause, since the same upstream API times out again.

리뷰

아직 리뷰가 없습니다. 사용해 본 소감을 남겨 주세요.

댓글

로그인 없이 쓸 수 있습니다. 사용 후기, 질문, 작동하지 않은 환경 등을 편하게 남겨 주세요.

아직 댓글이 없습니다. 첫 댓글을 남겨 보세요.

보내면 바로 공개됩니다. 이메일 주소나 전화번호 같은 개인 정보는 쓰지 마세요. URL은 2개까지입니다.

0 / 1,000자

이 양식은 reCAPTCHA로 보호되며 Google 개인정보처리방침 및 서비스 약관이 적용됩니다.

같은 저장소의 스킬

Plan or review software architecture through a small expert panel. Use when the user explicitly asks for architecture planning, system design, technical strategy, an architecture assessment, a design review, or a system health review. Do not use for ordinary PR review, debugging, or implementation.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

nanocoai/nanoclaw-templates202026년 9월 16일 업데이트

Thorough, consistently formatted competitor and product research. Produces a structured "About" doc, a "Recent News" log, and a row in a tracking spreadsheet. Use whenever the user researches a company or competitor, builds or updates a competitor doc, compares products, or logs a competitor to the tracker.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

nanocoai/nanoclaw-templates202026년 9월 16일 업데이트

Household assistant for a whole family. Runs a morning brief, plans meals and builds grocery lists (hunting the best prices), looks ahead at the week's logistics, stays on top of the kids' school, watches prices on things the family wants, and helps book appointments and reservations. Use it for anything that keeps the family's day or week running. Trigger even on implicit asks - "what's on today", "what do the kids have this week", "what should we make for dinner", "add milk to the list", "when's the dentist", "did anything come from school", "remind me about the permission slip", "watch this jacket and tell me if it drops", "book us a table Friday".

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

nanocoai/nanoclaw-templates202026년 9월 16일 업데이트

Reporting workflow for a working journalist, using web research and Apify's X scraper (social signals). Onboards the journalist, monitors their beat and builds digests, evaluates story pitches, finds and vets sources, and prepares interviews. Use for any newsroom task, such as "what's new on my beat", "is this pitch any good", "who should I talk to about X", "prep me for this interview", or "turn these notes into a draft".

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

nanocoai/nanoclaw-templates202026년 9월 16일 업데이트

Write the SQL or MongoDB query that answers a question and keeps answering it: the right grain, no fan out, parameterised window, checked against something known. Use when a number is needed that no report carries, when an existing query returns something that looks wrong, when a query is slow or expensive, or when somebody asks for a one off pull.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

nanocoai/nanoclaw-templates202026년 9월 16일 업데이트

Stand up reporting for a new audience — an external client, a business unit, a region, an executive team — end to end: what they need to see, whether the data exists, access and scoping, their place in the pipeline, the standard report set, and validation against numbers they can check themselves. Use when a new audience is onboarded, when an existing one adds a site, a region or a business unit, when their reporting is rebuilt after a change on their side, or when they say the numbers do not match their own records.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

nanocoai/nanoclaw-templates202026년 9월 16일 업데이트

nanocoai의 스킬 모두 보기

이 스킬의 문제 신고