본문으로 건너뛰기
cccskills
무료GitHub에 공개

use-echo

Search prior Marin work across Echo wiki notes, files, pull requests, and issues. Reuse evidence during an investigation, update existing knowledge, and maintain incident records with links to the original sources.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

원문원문 설명 보기

Search Marin prior work and maintain Echo knowledge or incident records. Reuse retrieved evidence throughout the same investigation.

연동 도구Discord

실행 점수 미검증

설치 방법 보기

이럴 때 유용합니다

  • Finding previous investigations and fixes
  • Reusing evidence across follow-up questions
  • Updating reusable operational knowledge
  • Maintaining a record for an ongoing incident

포함된 파일(2)

  • SKILL.md5.6 KB
  • references/incidents.md3.5 KB

SKILL.md(원문)

설치하기 전에 에이전트에게 전달되는 지시 내용을 확인할 수 있습니다.

Use Echo

Use this entry point for prior-work search and knowledge publication. For live incidents, read incident records, which defines when to publish, how to format the record, and how to update it. Ordinary search does not require publishing a note.

Search Echo before rediscovering prior work. Cite canonical Echo, GitHub, or Discord URLs for the evidence you use.

Treat one incident, debugging session, or research question as one logical investigation across continuation turns. Search once when that investigation starts, then reuse relevant results already fetched in the conversation. Do not search again merely because the user asks a follow-up question or requests the next operational step. Search again only when the incident, question, repository scope, or freshness requirement changes, when a selected workflow requires a current duplicate check, or when the user explicitly asks.

Search

Use a natural-language federated search:

uv run infra/marina/apps/echo/cli.py search "how do I diagnose a stalled TPU collective" --limit 10

Search covers wiki, file, pr, and issue by default. Repeat --domain to select a subset.

File search infers the configured Marin-community repository from the current Git checkout, including ordinary contributor forks. Pass --repository <owner/repo> to choose one configured repository or --repository all to search all six. The CLI prints the resolved file scope once. Searches that omit the file domain work outside a Git checkout.

Discord is excluded by default because messages may be noisy or untrusted. Add --domain discord only when discussion history is relevant, and open the canonical URL when surrounding thread context matters.

Fetch a result's full detail with the value in the SOURCE ID column:

uv run infra/marina/apps/echo/cli.py get <source-id>

The GRADE KEY column is for feedback. get also accepts file grading keys with numeric suffixes, such as file:20849.

Grade evaluated results with the exact query and printed keys:

uv run infra/marina/apps/echo/cli.py feedback --query "stalled TPU collective" \
  --grade wiki:730=0 --grade file:731=10 \
  <<< "The file result answered the task; wiki results were off-topic."

Use 0 for irrelevant and 10 for directly useful. Grade only evaluated results and always explain overall quality on stdin, including for an empty result set.

Use grep for exact strings in GitHub or Discord activity, narrowing with --source or --kind when needed:

uv run infra/marina/apps/echo/cli.py grep "FAILED_PRECONDITION" --source github

Use rg for exact identifiers in the current checkout. Echo's file index follows the periodically refreshed GitHub head, so it does not contain branch-only or uncommitted files. Use wiki search --tag <tag> when tags, rather than federated relevance, define the desired synthesis. Authentication reuses the shared Marin login via iris login; see Echo setup and access.

Run this search sequence before adding or editing a wiki note.

Choose the durable home

Every live infrastructure incident, as defined in incident records, gets a standalone Echo record linked from its associated PR or issue. Also use the narrowest reusable home when the incident or other work changes durable guidance:

  • Update OPS.md for a recurring operational procedure, diagnostic workflow, or guardrail in one subsystem.
  • Update docs/ for reusable product or user guidance that belongs with the repository.
  • Edit an existing Echo wiki note for a cross-cutting pattern or synthesis that has no single repository home.
  • Add a wiki note only when the searches find no near-duplicate.

Create one incident entry per incident and edit it while the same incident continues. Keep raw logs and diffs in their source systems. Edit a near-duplicate synthesis instead of adding another.

Write or revise a wiki note

Write the shortest entry that changes a future action:

  • Lead with an actionable value: a decision, command, diagnostic discriminator, guardrail, or recovery step.
  • Include only the facts needed to support or apply that action. Link to the canonical PR, issue, dashboard, log bundle, or report for chronology and raw evidence instead of copying it into Echo.
  • Put the action in the title, use_when, or opening paragraph.
  • Keep chronology without a reusable decision in an issue, logbook, or source artifact.

Write an Open Knowledge Format document:

---
type: wiki-note
title: Stalled TPU collectives can have several low-power causes
use_when: when a distributed TPU job stalls before the first optimizer update
tags:
  - ops
  - debugging
  - iris
---

State the reusable pattern, how to distinguish its causes, and the evidence URLs.

Use lowercase kebab-case tags. Keep the title concrete and make use_when describe the future search trigger. Make the body stand alone. Cite canonical URLs inline. Concision still requires enough context to apply the guidance safely; do not omit a precondition, destructive-action warning, or material caveat.

Create a note:

uv run infra/marina/apps/echo/cli.py wiki add --file note.md

Revise the closest existing note:

uv run infra/marina/apps/echo/cli.py wiki show <id> > note.md
# Edit note.md.
uv run infra/marina/apps/echo/cli.py wiki edit <id> --file note.md

Both write commands print the canonical Echo URL. Return and cite that URL after every add or edit.

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

Compare Zephyr changes using the same prepared dataset and matching execution settings. Analyze Finelog metrics for each processing stage to distinguish CPU efficiency, elapsed time, and peak memory changes, then report improvements, regressions, or tradeoffs.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

  • Compare Zephyr performance before and after a PR
  • Assess speed gains against additional CPU usage
  • Check peak memory and out-of-memory regressions
marin-community/marin4천2026년 10월 24일 업데이트

Register Hugging Face datasets for Marin by inspecting their structure without downloading the full dataset. Identify text fields, configurations, and data splits, then add a dataset module and validate the mapping with a sample.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

  • Registering a Hugging Face dataset for Marin
  • Inspecting text fields without a full dataset download
  • Checking configurations and data splits
marin-community/marin4천2026년 10월 24일 업데이트

add-grant

무료

Turn a specified GCP access request into a reviewable Pulumi change and pull request. Select the narrowest suitable role and encrypt personal email identities, covering resource permissions and Cloud Run viewer access through IAP, an access gateway.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

  • Prepare a request for GCS bucket read access
  • Add a viewer to a Cloud Run service protected by IAP
  • Prepare service account impersonation permissions
marin-community/marin4천2026년 10월 24일 업데이트

Add or update Pallas/Mosaic kernels, specialized computation routines for JAX. The skill covers reference implementations, output and gradient checks, public wrappers, fallback behavior, performance benchmarks, and hardware-specific tuning when requested.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

  • Adding a Pallas kernel for a JAX computation
  • Checking outputs and gradients against a reference
  • Maintaining backend selection and fallback behavior
marin-community/marin4천2026년 10월 24일 업데이트

Try model or training changes in a copied Grug or Grugformer experiment, document the differences, and bring successful changes back into the base template while removing superseded experiment code and checking behavior.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

  • Try changes to attention or masking
  • Experiment with optimizers or training loops
  • Bring successful changes into the base template
marin-community/marin4천2026년 10월 24일 업데이트

Organize Marin experiment reports into a maintained index, or archive explicitly named older experiments using lasting tags and issue references. Existing conclusions and canonical links are preserved so experiment records remain traceable.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

  • Organizing an index of experiment reports
  • Consolidating canonical report entries
  • Archiving named legacy experiments
marin-community/marin4천2026년 10월 24일 업데이트

marin-community의 스킬 모두 보기

이 스킬의 문제 신고