agentleFS
open-thoughtsopen-thoughts/OpenThoughts-Agent/.agents/skills/file-issue/SKILL.md

file-issue

Skill309 starsChanged 4 months agoApache-2.0View on GitHub

File a GitHub issue for a bug or improvement found this session.

13 other projects use a version of this, 1 of them edited.

Adopted by

Most recently taken up by

Used with

Projects with it also use review-pr.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • DockerSkill

    review-pr

    Review one or more incoming Docker documentation pull requests as a maintainer. Independently validate technical claims, assess editorial fit and information architecture, choose a verdict, and draft exact inline or PR-wide feedback behind a confirmation gate. Use for requests such as "review PR 123", "is this PR correct?", "does this information belong here?", "validate this PR", or "help review backlog PRs". Do not use to maintain or fix a PR you own; use maintain-pr for that.

    Also in 4 projects that use this

The file

Show its rules and text

We split this skill into the rules it gives an agent

20 rules. 0 are common, 13 are distinctive, and 7 are very specific to this project.

  • 0

    Common

    Most of the 12 edited versions we read keep these.

  • 13

    Distinctive

    This author's own choices. Worth a look.

  • 7

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Create a GitHub issue in the current repository from bugs, regressions, or improvements identified in the current conversation.

    line 10
  2. Distinctive:

    If it's ambiguous what to file, ask the user before proceeding.

    line 100
  3. Distinctive:

    Search for existing issues first:

    line 108
  4. Distinctive:

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

    line 114
  5. Distinctive:

    Body: Use the section structure for the chosen kind (see above).

    line 124
  6. Distinctive:

    No filler ("I noticed...", "During our conversation...").

    line 128
  7. Distinctive:

    No markdown images or tables.

    line 129
  8. Distinctive:

    Keep every fact needed to understand and act on the issue.

    line 131
  9. Very specific:

    Do not repeat the title in a Description section.

    line 134
  10. Distinctive:

    Do not inventory files, functions, or proposed implementation steps that are not required to define the problem or completion criteria.

    line 135
  11. Distinctive:

    If the user explicitly asked to file an issue, skip the preview — file it and share the link.

    line 154
  12. Very specific:

    Write the body to a uniquely named temp file, then pass it with --body-file.

    line 160
  13. Very specific:

    Do not inline the body with shell substitution (--body "$(cat <<'EOF' ...)") — multiline text can be corrupted by pasted output or escaping …

    line 161
  14. Very specific:

    Add kind-appropriate labels (bug, experiment).

    line 180
  15. Distinctive:

    Before creating the issue, re-open the body file and verify it contains no unrelated shell output (pre-commit logs, pytest session headers, …

    line 184
  16. Very specific:

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

    line 188
  17. Distinctive:

    Never credit yourself in the issue.

    line 203
  18. Very specific:

    Always add the agent-generated label.

    line 204
  19. Distinctive:

    If the conversation does not contain a clear bug or actionable improvement, say so and ask the user what they want to file.

    line 207
  20. Distinctive:

    Use the smallest matching body structure.

    line 209

“Common” is measured: kept by at least 6 in 10 of the 12 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md
<!-- Vendored from marin-community/marin-style v0.3.0 — do not edit; re-run `marin-style sync`. -->

Skill: File GitHub Issue

Create a GitHub issue in the current repository from bugs, regressions, or improvements identified in the current conversation. gh defaults to the repo of the current checkout; pass --repo <owner>/<name> only to target a different one.

Background

Read first: AGENTS.md.

Before drafting, read:

  • .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 kind, then use the matching body structure below. There are no GitHub issue templates — these structures live here.

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:
* Report:
* Important updates:

## Decision Log

## Conclusion

Workflow

1. Gather Context from Conversation

Extract from the conversation:

  • What is broken or missing -- concrete symptoms, error messages, failing test output.
  • Where it happens -- file paths, line numbers, module names.
  • How to reproduce -- steps, commands, or minimal config that triggers it.
  • Root cause (if known).
  • Severity -- blocks work, causes data loss, or cosmetic?

If it's ambiguous what to file, ask the user before proceeding.

2. Classify the Issue

Pick the kind (bug, task, or experiment). If unsure, ask the user.

3. Duplicate Check

Search for existing issues first:

gh issue list --state open --search "<keyword>"

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

4. Draft the Issue

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

Body: Use the section structure for the chosen kind (see above).

Rules for the body:

  • No filler ("I noticed...", "During our conversation...").
  • No markdown images or tables.
  • Reference code with file:line links, not inline dumps.
  • Keep every fact needed to understand and act on the issue. Remove history, repetition, and implementation narration that does not define the problem or completion criteria; experiment issues may retain more tracking context.
  • Do not repeat the title in a Description section.
  • Do not inventory files, functions, or proposed implementation steps that are not required to define the problem or completion criteria.
  • Include error messages or stack traces in code blocks, trimmed to the relevant frames.
  • For task issues: include concrete Done when criteria.
  • For bug issues: include numbered reproduction steps.

5. Compress and 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.

This review is required even when the user explicitly asked to file the issue. It is an author self-check, not a request for approval.

6. Confirm or File Directly

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.

7. 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="$(gh issue create \
  --title "<title>" \
  --label "agent-generated" \
  --body-file "$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.

8. Report Back

Print the issue URL.

Writing Style

Terse: every sentence conveys new information; no preamble or editorializing; no restating code a link covers; annotate code links, don't narrate them.

Rules

  1. Never credit yourself in the issue.
  2. Always add the agent-generated label.
  3. Confirm with the user before filing only when the agent surfaced the issue (not when the user explicitly asked to file).
  4. If the conversation does not contain a clear bug or actionable improvement, say so and ask the user what they want to file.
  5. Use the smallest matching body structure. Omit optional context and headings that add no information.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.