跳到正文
cccskills
免费在 GitHub 公开

file-issue

Turn a bug report, improvement request, or experiment into a structured GitHub issue. Check for duplicates, write reproduction steps or testable completion criteria, apply suitable labels, and verify the published title and body.

中文简介正在准备中。当前显示英语简介。

原文查看原文说明

File a GitHub issue only when explicitly requested or delegated by another selected workflow; do not create issues merely because a problem was found.

集成工具GitHub
查看安装方法

适用场景

  • File a bug with clear reproduction steps
  • Create an improvement task with testable completion criteria
  • Track an experiment's hypothesis, status, and conclusions
  • Check for existing issues before filing new work

包含的文件(1)

  • SKILL.md4.4 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

File a GitHub issue

Before drafting, read AGENTS.md and:

  • .agents/skills/writing-style/SKILL.md
  • .agents/skills/writing-style/issues.md
  • .agents/skills/writing-style/ai-writing-donts.md

Issue Kinds and Body Structure

Pick the smallest matching structure.

KindWhen to useLabels
bugA bug or regression was foundbug, agent-generated
taskAn improvement, refactor, or feature requestagent-generated + priority if known
experimentAn experiment needs trackingexperiment, agent-generated

Bug body

<what is broken and its impact -- concrete symptoms or error messages>

Reproduce:
1. <step>
2. <step>

Expected: <what should happen instead>

<optional: concise evidence or confirmed root cause>

Task body

<what needs to be done and why -- enough context for anyone on the team>

Done when:
<specific, testable completion criteria>

Experiment body

## TL;DR

<One-paragraph current summary. Leave blank only when the work is just being kicked off.>

## Description

<Context someone outside the thread can understand.>

## Hypothesis or Goal

<What are you trying to learn, fix, or achieve?>

## Status

<Current state; update as evidence lands.>

## Links

* Logbook:
* W&B Report:
* Important updates:

## Decision Log

## Conclusion

Workflow

1. Gather and classify

Extract the symptom or desired outcome, impact, location, reproduction, known cause, and severity. Ask when the issue or its kind is ambiguous.

2. Check duplicates

Search for existing issues first:

gh issue list --repo marin-community/marin --state open --search "<keyword>"

If a match exists, tell the user and offer to comment on it instead.

3. Draft

Title: At most 80 characters, optionally prefixed with a scope tag. State a factual symptom for a bug (e.g. [levanter] Gradient accumulation drops the last microbatch) and an imperative outcome for a task (e.g. [levanter] Handle partial accumulation steps). Do not add bug:, task:, or another type prefix.

Use the body structure above. Keep the facts needed to act; link code with file:line, trim errors to relevant frames, and omit filler, repeated titles, diff inventories, and unnecessary implementation narration. Bugs need numbered reproduction steps; tasks need testable completion criteria.

4. Inspect the payload

Apply the writing-style final compression pass to the exact title and body that will be sent to GitHub. For a bug or task, verify the title is at most 80 characters. Every remaining sentence must add a symptom, impact, reproduction step, observation, expected behavior, or completion criterion.

5. Apply the approval boundary

If the user explicitly asked to file an issue, skip the preview — file it and share the link. If the agent surfaced the issue (not explicitly requested), show the drafted title and body and wait for approval or edits.

6. File the issue

Write the body to a uniquely named temp file, then pass it with --body-file. Do not inline the body with shell substitution (--body "$(cat <<'EOF' ...)") — multiline text can be corrupted by pasted output or escaping mistakes. Do not reuse a fixed path like /tmp/issue-body.md; concurrent agent runs can overwrite each other's drafts on shared hosts.

body_file="$(mktemp "${TMPDIR:-/tmp}/issue-body.XXXXXX.md")"
trap 'rm -f "$body_file"' EXIT

cat > "$body_file" <<'EOF'
<body>
EOF

issue_url="$(gh issue create --repo marin-community/marin \
  --title "<title>" \
  --label "agent-generated" \
  --body-file "$body_file")"

Add kind-appropriate labels (bug, experiment). If a relevant label does not exist, skip it rather than creating new labels. For task issues, add a priority label (p1, p2, p3) if the user specifies one or severity is clear.

Before creating the issue, re-open the body file and verify it contains no unrelated shell output (pre-commit logs, pytest session headers, prompt transcripts). If it does, clean the draft before posting.

After creating the issue, fetch its published text with gh issue view "$issue_url" --json title,body and correct any text added or altered by the publishing tool.

7. Report

Print the issue URL.

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

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.

中文简介正在准备中。当前显示英语简介。

  • 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/marin39952026年10月21日 更新

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.

中文简介正在准备中。当前显示英语简介。

  • Registering a Hugging Face dataset for Marin
  • Inspecting text fields without a full dataset download
  • Checking configurations and data splits
marin-community/marin39952026年10月21日 更新

add-grant

免费

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.

中文简介正在准备中。当前显示英语简介。

  • 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/marin39952026年10月21日 更新

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.

中文简介正在准备中。当前显示英语简介。

  • Adding a Pallas kernel for a JAX computation
  • Checking outputs and gradients against a reference
  • Maintaining backend selection and fallback behavior
marin-community/marin39952026年10月21日 更新

Preserve old experiment scripts with a dated Git tag, a named snapshot of the code, and add comments linking related GitHub issues to the archived files and cleanup pull request.

中文简介正在准备中。当前显示英语简介。

  • Preserving a snapshot of old experiment scripts
  • Linking experiment issues to archived files
  • Updating archive notices after a tag changes
marin-community/marin39952026年10月21日 更新

Launch and continuously monitor a specified Zephyr pipeline on Iris when asked. It checks coordinator and worker health, tracks stage progress, identifies stalled or repeated failures, and requires explicit approval before stopping or restarting jobs.

中文简介正在准备中。当前显示英语简介。

  • Launch a specified Zephyr pipeline and check startup
  • Monitor stage progress and worker health over time
  • Investigate stalled stages or repeated worker failures
marin-community/marin39952026年10月21日 更新

查看 marin-community 的全部技能

报告此技能的问题