agentleFS
ric03uecric03uec/clawrium/.claude/skills/itx-bug-new/SKILL.md

itx-bug-new

Skill67 starsChanged 2 months agoApache-2.0View on GitHub

Create a GitHub bug report from current context

The file

We split this skill into the rules it gives an agent

9 rules. About 0 are common, 6 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Create a GitHub issue for a bug based on the current conversation context.

    line 9
  2. Distinctive:

    Ask for Customer Outcome: Use the harness's user-question facility to ask:

    line 19
  3. Distinctive:

    Form Issue Title: Use the customer outcome as the issue title.

    line 27
  4. Distinctive:

    If the user provided a description argument, use it for context

    line 33
  5. Very specific:

    Create Issue: Use gh issue create with:

    line 52
  6. Distinctive:

    Always ask for customer outcome before creating the issue

    line 105
  7. Very specific:

    Always add needs-triage label for new bugs

    line 107
  8. Distinctive:

    If steps to reproduce are unclear, note that in the issue

    line 109
  9. Very specific:

    REQUIRED: After creating the issue, append prompt log to .itx/<N>/00_PLAN.md.

    line 114

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “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

Bug Report Creation

Create a GitHub issue for a bug based on the current conversation context.

Instructions

  1. Analyze Context: Review the current conversation for:
    • Error messages and stack traces
    • Unexpected behavior descriptions
    • Steps that led to the issue
    • Environment details (version, OS, etc.)
  2. Ask for Customer Outcome: Use the harness's user-question facility to ask:

    "What should the user be able to do when this bug is fixed?"

    Example outcomes:

    • "User can install dependencies without version mismatch errors"
    • "User can add resources with special characters in names"
    • "User can run status command without timeout"
  3. Form Issue Title: Use the customer outcome as the issue title.
    • Format: <outcome> (what the user can do after fix)
    • Example: "User can install dependencies without version mismatch errors"
    • The user can change this later if needed
  4. Gather Details:
    • If the user provided a description argument, use it for context
    • Identify steps to reproduce if available
    • Note environment details
  5. Load Project Name (for environment section):
    ITX_CONFIG="$(git rev-parse --show-toplevel)/.claude/itx-config.json"
    if [ -f "$ITX_CONFIG" ]; then
      PROJECT_NAME=$(jq -r '.project.name // ""' "$ITX_CONFIG")
      VERSION_LABEL=$(jq -r '.project.version_label // "Version"' "$ITX_CONFIG")
    fi
    
    # Fallback: use repository name if no config
    if [ -z "$PROJECT_NAME" ]; then
      REMOTE_URL=$(git config --get remote.origin.url)
      PROJECT_NAME=$(echo "$REMOTE_URL" | sed -E 's/.*[:/]([^/]+\/[^/]+)(\.git)?$/\1/' | cut -d'/' -f2)
    fi
  6. Create Issue: Use gh issue create with:
    gh issue create \
      --title "<customer outcome from step 3>" \
      --label "bug" \
      --label "needs-triage" \
      --body "<structured bug report>"
  7. Bug Report Body Format:

    ## Customer Outcome
    <The outcome statement - what user can do when fixed>
    
    ## Description
    <What is currently happening / the bug>
    
    ## Steps to Reproduce
    1. <step>
    2. <step>
    
    ## Expected Behavior
    <What should happen>
    
    ## Actual Behavior
    <What actually happens>
    
    ## Environment
    - <project name> version: <version>
    - Platform: <os/platform>
    - Other relevant details: <details>
    
    ---
    
    <details>
    <summary>Prompt Log</summary>
    
    **Stage**: bug-creation
    **Skill**: /itx-bug-new
    **Timestamp**: <ISO timestamp>
    **Model**: <model>
    
    ```prompt
    <original user prompt/context that led to this bug>
    </details> ```
  8. Return: The issue URL and number

Notes

  • Always ask for customer outcome before creating the issue
  • The outcome becomes the title - focus on what the user gains
  • Always add needs-triage label for new bugs
  • Include as much context as available from the conversation
  • If steps to reproduce are unclear, note that in the issue
  • Project name dynamically detected or loaded from config

Prompt Logging

REQUIRED: After creating the issue, append prompt log to .itx/<N>/00_PLAN.md.

See AGENTS.md for format specification.

mkdir -p .itx/<issue-number>
# Append prompt log to .itx/<issue-number>/00_PLAN.md

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.