Agent skill

Report Issue

by codemie-ai in codemie-ai/codemie-code

This skill should be used when the user wants to report a bug, file an issue, or suggest a feature for the CodeMie Code CLI tool (codemie-ai/codemie-code repository on GitHub).

Apache-2.0Auto-check: notesTesting & QA

Install Report Issue

skills CLI
$ npx skills add codemie-ai/codemie-code --skill report-issue -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install codemie-ai/codemie-code report-issue --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/codemie-ai/codemie-code.git skills-src && mkdir -p .claude/skills && cp -r skills-src/src/agents/plugins/claude/plugin/skills/report-issue .claude/skills/report-issue && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
report-issue
GitHub stars
294
Token cost
~2.3k tokens
SKILL.md length
627 words
Files
1
Skills in repo
9
Repo updated
First seen
Licence
Apache-2.0

At a glance

This skill should be used when the user wants to report a bug, file an issue, or suggest a feature for the CodeMie Code CLI tool (codemie-ai/codemie-code repository on GitHub).

  • Works in 8 steps: Pre-flight and Diagnostic Collection → Understand the Issue → Classify the Issue → …
  • Wants to report a bug
  • SKILL.md covers Step 1: Pre-flight and…, Step 2: Understand the Issue, Step 3: Classify the Issue and Step 4: Compose the Issue Body, plus 4 more sections
  • Calls gh, node and npm; reaches gist.github.com

What it does

Report Issue is an agent skill from codemie-ai/codemie-code. This skill should be used when the user wants to report a bug, file an issue, or suggest a feature for the CodeMie Code CLI tool (codemie-ai/codemie-code repository on GitHub). Trigger phrases include: "report a bug", "open an issue", "submit an issue", "file a bug report", "something is broken in CodeMie", "report to GitHub", "create a GitHub issue", "suggest a feature for CodeMie", "request an enhancement", "I have a feature idea", "codemie is not working", or any mention of filing a report for CodeMie. This…

Its SKILL.md is about 2.3k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Testing & QA, covering QA and bug reports. It works with GitHub and Node.js. The repository describes itself as: AI Run CodeMie CLI with analytics capabilities. The licence is Apache-2.0.

When your agent uses it

  • Wants to report a bug
  • Suggest a feature for the CodeMie Code CLI tool (codemie-ai/codemie-code repository on GitHub)
  • Phrases include: report a bug
  • Submit an issue

Example prompts

  • “report a bug”
  • “open an issue”
  • “submit an issue”
  • “/report-issue”

Requirements

  • Node.js
  • Pre-approved tools (allowed-tools): Bash, Read, Grep

Workflow steps

8 steps, taken from the step headings in SKILL.md.

  1. Pre-flight and Diagnostic Collection
  2. Understand the Issue
  3. Classify the Issue
  4. Compose the Issue Body
  5. Preview and Confirm
  6. Upload Log Files as Gist
  7. Create the GitHub Issue
  8. Confirm and Link

What it can do on your machine

Read from SKILL.md and the folder at commit 0218c8d. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Bash
    • Read
    • Grep

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • gh
    • node
    • npm
    • brew
    • apt
    • dnf
    • winget

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • gist.github.com

    Also links to:

    • cli.github.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Report Issue loads about 2.3k tokens when it runs. Until then it costs about 198 tokens; SKILL.md has 627 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~198
When it runs · the whole SKILL.md, loaded when a task matches
~2.3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NoteRuns commands with sudoSKILL.md:42
    > - **Linux (apt)**: `sudo apt install gh`
  • NoteRuns commands with sudoSKILL.md:43
    > - **Linux (dnf)**: `sudo dnf install gh`
  • NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
    allowed-tools: Bash, Read, Grep

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from codemie-ai/codemie-code at commit 0218c8d, republished under its Apache-2.0 licence (© codemie-ai). 627 words, ~2,253 tokens.

Download SKILL.mdSave it as .claude/skills/report-issue/SKILL.md (or your agent's skills folder).
name
report-issue
description
This skill should be used when the user wants to report a bug, file an issue, or suggest a feature for the CodeMie Code CLI tool (codemie-ai/codemie-code repository on GitHub). Trigger phrases include: "report a bug", "open an issue", "submit an issue", "file a bug report", "something is broken in CodeMie", "report to GitHub", "create a GitHub issue", "suggest a feature for CodeMie", "request an enhancement", "I have a feature idea", "codemie is not working", or any mention of filing a report for CodeMie. This skill automatically collects diagnostic context (OS, Node.js, CLI version, installed agents, active profile, codemie doctor output, recent debug logs) and creates a structured GitHub issue via `gh issue create` with a user-confirmed preview step before submission.
allowed-tools
Bash, Read, Grep

Report Issue to CodeMie Code

Help the user file a well-structured bug report or feature request to codemie-ai/codemie-code on GitHub.

The goal is to create a rich issue that gives maintainers everything they need to triage and reproduce the problem — without requiring the user to manually gather technical details.


Step 1: Pre-flight and Diagnostic Collection

1a. Check gh CLI first — do this before anything else
bash
if ! command -v gh &>/dev/null; then
  echo "GH_NOT_INSTALLED"
else
  gh auth status 2>&1 || echo "GH_NOT_AUTHENTICATED"
fi

If GH_NOT_INSTALLED: Stop immediately and tell the user:

"gh (GitHub CLI) is not installed. It is required to create issues from the terminal.

Install it with one of:

  • macOS: brew install gh
  • Linux (apt): sudo apt install gh
  • Linux (dnf): sudo dnf install gh
  • Windows: winget install --id GitHub.cli
  • Or download from: https://cli.github.com

After installing, run gh auth login to connect your GitHub account, then try this skill again."

If GH_NOT_AUTHENTICATED: Stop and tell the user:

"gh is installed but not authenticated. Run gh auth login to connect to your GitHub account, then try again."

Do not proceed past this point until gh is installed and authenticated.

1b. Gather diagnostic context

Run the following and capture results. Don't display raw output yet.

bash
# OS + platform
uname -srm 2>/dev/null || echo "unknown"

# Node.js version
node --version 2>/dev/null || echo "not found"

# npm version
npm --version 2>/dev/null || echo "not found"

# CodeMie CLI version
codemie --version 2>/dev/null || echo "not found"

# Installed agents and versions
codemie list --installed 2>/dev/null || echo "unavailable"

# Full doctor output (profile, provider, dependency health, agent versions)
codemie doctor 2>/dev/null || echo "unavailable"

# Shell + terminal environment
echo "Shell: $SHELL"
echo "Terminal: ${TERM_PROGRAM:-unknown}"

# Extract ERROR and WARN lines from the two most recent log files.
# Log format: [TIMESTAMP] [LEVEL] [agent] [session-id] [profile] [component] message
# Files: ~/.codemie/logs/debug-YYYY-MM-DD.log (one per day, can be several MB)
LOG_DIR="$HOME/.codemie/logs"
RECENT_LOGS=$(ls -t "$LOG_DIR"/debug-*.log 2>/dev/null | head -2)
if [ -n "$RECENT_LOGS" ]; then
  echo "=== ERROR and WARN entries from recent logs ==="
  # Print filename headers and filter by level; limit to last 100 matches to keep size reasonable
  for f in $RECENT_LOGS; do
    echo "--- $f ---"
    grep -E '\[(ERROR|WARN)\]' "$f" | tail -50
  done
  echo "=== Full log files ==="
  for f in $RECENT_LOGS; do
    echo "$f"
  done
else
  echo "No debug logs found"
fi

Log file paths (captured above) will be used in Step 6 to upload as Gist.


Step 2: Understand the Issue

Extraction-first: If the user already described the issue in their request (problem, error message, steps, etc.), extract that information directly without asking them to repeat it. Only ask follow-up questions for missing pieces.

If no description was provided yet, ask the user for:

  1. Issue type: Bug report, feature request, or question?
  2. Title: A short, specific summary (one line)
  3. Description: What happened, what they expected, and any reproduction steps

When prompting for description, share these tips:

  • Include the exact command that triggered the problem
  • Paste the exact error message verbatim (not paraphrased)
  • Note whether it happens every time or intermittently
  • For feature requests: describe the use case and the expected behavior

Step 3: Classify the Issue

Determine the issue type based on the user's description:

  • Bug report — unexpected error, crash, wrong output → label: bug
  • Feature request — missing capability, enhancement ask → label: enhancement
  • Question / unclear behavior — seeking clarification → label: question

Show full SKILL.md (269 more words)Show less

Step 4: Compose the Issue Body

Build the issue body using the appropriate template below.

Security — before embedding diagnostic output:

  • Scan for and redact full API keys, tokens, or passwords (show only first 4 chars + ***)
  • The masked format proxy-ha***dled already used by codemie doctor is safe to include as-is
  • Remove any personal access tokens or private credential URLs
Template: Bug Report
markdown
## Description

<user's description of the problem>

## Steps to Reproduce

1.
2.
3.

## Expected Behavior

<what the user expected to happen>

## Actual Behavior

<what actually happened — paste error messages verbatim>

## Environment

| Field       | Value                        |
|-------------|------------------------------|
| OS          | <uname output>               |
| Node.js     | <node --version>             |
| npm         | <npm --version>              |
| CodeMie CLI | <codemie --version>          |
| Shell       | <$SHELL>                     |
| Terminal    | <$TERM_PROGRAM>              |

## Installed Agents

<formatted list from `codemie list --installed` — agent name and version per line>

## CodeMie Doctor Output

<details>
<summary>Full doctor output</summary>

<pre>
<codemie doctor output — with credentials redacted>
</pre>

</details>

## Recent Errors

<details>
<summary>ERROR and WARN entries from recent logs</summary>

<pre>
<filtered ERROR/WARN lines from the two most recent debug-YYYY-MM-DD.log files, or "No errors found">
</pre>

</details>

## Full Debug Logs

<full log file(s) attached as GitHub Gist — see link below, or "No log files found">
Template: Feature Request
markdown
## Summary

<one-sentence description of the feature>

## Motivation

<the problem this feature would solve, or the use case that is currently missing>

## Proposed Behavior

<what the user wants to happen — be specific about inputs, outputs, and commands>

## Alternatives Considered

<other ways you have worked around this, if any>

## Environment

| Field       | Value                        |
|-------------|------------------------------|
| OS          | <uname output>               |
| Node.js     | <node --version>             |
| CodeMie CLI | <codemie --version>          |

## Installed Agents

<formatted list from `codemie list --installed`>

Step 5: Preview and Confirm

Show the user the proposed issue title and full body. Ask:

"Here's the issue I'll create on GitHub. Does this look right, or would you like to change anything before I submit?"

Wait for confirmation before creating the issue.


Step 6: Upload Log Files as Gist

If log files were found in Step 1b, upload the two most recent ones as a secret Gist so they can be referenced in the issue. This keeps the issue body readable while giving maintainers the full context.

bash
# Upload the two most recent log files as a single secret Gist
gh gist create \
  --desc "CodeMie debug logs for issue report ($(date +%Y-%m-%d))" \
  ~/.codemie/logs/debug-$(date +%Y-%m-%d).log \
  ~/.codemie/logs/debug-$(date -v-1d +%Y-%m-%d 2>/dev/null || date -d yesterday +%Y-%m-%d).log \
  2>/dev/null

Capture the Gist URL from the output (it looks like https://gist.github.com/...).

  • If only one log file exists, pass just that file.
  • If no log files exist, skip this step and note "No log files available" in the issue body.
  • Replace the <full log file(s) attached as GitHub Gist — see link below> placeholder in the issue body with the actual Gist URL.

Note: Gists are secret (not listed publicly) but accessible to anyone with the link.


Step 7: Create the GitHub Issue

bash
gh issue create \
  --repo codemie-ai/codemie-code \
  --title "<issue title>" \
  --body "<issue body with gist URL inserted>" \
  --label "<bug|enhancement|question>"

After the issue is created, tell the user:

© codemie-ai, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in src/agents/plugins/claude/plugin/skills/report-issue of codemie-ai/codemie-code.

Open the folder on GitHubat commit 0218c8d

Compare with similar skills

Report Issue next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Report Issue compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Report Issue this skillcodemie-ai/codemie-code294—~2.3kAutomated safety check: NotesApache-2.0
DeerFlow Smoke Testbytedance/deer-flow83k—~2.5kAutomated safety check: NotesMIT
Weavebench Cua ReproduceAMAP-ML/LongHorizon-Harness1.7k—~1.6kAutomated safety check: PassMIT
Evidence-Driven Testingmichaelshimeles/skills1.3k1 repos~3.9kAutomated safety check: PassNone
Senior QAnicepkg/auto-company1923 repos~1.1kAutomated safety check: NotesNone
Create GitHub IssueNVIDIA/OpenShell15k—~1.7kAutomated safety check: PassApache-2.0

Similar skills

  • DeerFlow Smoke Test

    bytedance/deer-flow

    Walks through an end-to-end smoke test of a DeerFlow deployment: pull the latest code, deploy with Docker or locally, verify services, run health checks and write a report.

    83k GitHub stars~2.5k tokensUpdated today
    Testing & QAAuto-check: notes
  • Weavebench Cua Reproduce

    AMAP-ML/LongHorizon-Harness

    Reproduce CUA-Harness experiments on WeaveBench from a GitHub checkout.

    1.7k GitHub stars~1.6k tokensUpdated 1 mo ago
    Testing & QAAuto-check passed
  • Evidence-Driven Testing

    michaelshimeles/skills

    Records an annotated screen recording of the agent testing an app hands-on, then posts the video and a results summary to the PR and tracker issue.

    1.3k GitHub starsUsed in 1 repo~3.9k tokens
    Testing & QAAuto-check passed
  • Senior QA

    nicepkg/auto-company

    Comprehensive QA and testing skill for quality assurance, test automation, and testing strategies for ReactJS, NextJS, NodeJS applications.

    192 GitHub starsUsed in 3 repos~1.1k tokens
    Testing & QAAuto-check: notes
  • Create GitHub Issue

    NVIDIA/OpenShell

    Official

    Create GitHub issues using the gh CLI. An agent skill from NVIDIA/OpenShell.

    15k GitHub stars~1.7k tokensUpdated today
    Testing & QAAuto-check passed
  • Triage Issues

    ClickHouse/clickhouse-java

    Analyzes a single GitHub issue at a time. An agent skill from ClickHouse/clickhouse-java.

    1.6k GitHub stars~904 tokensUpdated today
    Testing & QAAuto-check passed

More from codemie-ai/codemie-code

All 9 skills in this repo
  • Codemie Analytics

    codemie-ai/codemie-code

    CodeMie Analytics expert — use this skill whenever the user asks about CodeMie usage data, AI adoption metrics, user leaderboards, CLI insights, spending, LiteLLM costs, token usage, or wants to…

    294 GitHub stars~7.5k tokensUpdated yesterday
    Auto-check passed
  • Codemie HTML Report

    codemie-ai/codemie-code

    Build static HTML pages, reports, dashboards, and mockups that match the CodeMie UI design system.

    294 GitHub stars~3.3k tokensUpdated yesterday
    Auto-check passed
  • Msgraph

    codemie-ai/codemie-code

    Work with Microsoft 365 services via the Graph API — emails, calendar events, SharePoint sites (read and write), Teams chats and channel messages, OneDrive files, OneNote notebooks, Planner task…

    294 GitHub stars~4.1k tokensUpdated yesterday
    Auto-check passed
  • Codemie Assistant Builder

    codemie-ai/codemie-code

    Build, test and autonomously improve CodeMie platform assistants.

    294 GitHub stars~3.3k tokensUpdated yesterday
    Auto-check passed
  • Codemie Release

    codemie-ai/codemie-code

    Release a new version of CodeMie CLI. An agent skill from codemie-ai/codemie-code.

    294 GitHub stars~1.8k tokensUpdated yesterday
    Auto-check passed
  • Codemie Jira Assistant

    codemie-ai/codemie-code

    Business Analyst Assistant - expert to work with Jira. An agent skill from codemie-ai/codemie-code.

    294 GitHub stars~489 tokensUpdated yesterday
    Auto-check passed

Works with

Categories

Questions about Report Issue

What does Report Issue do?

This skill should be used when the user wants to report a bug, file an issue, or suggest a feature for the CodeMie Code CLI tool (codemie-ai/codemie-code repository on GitHub). Report Issue is an agent skill from codemie-ai/codemie-code. This skill should be used when the user wants to report a bug, file an issue, or suggest a feature for the CodeMie Code CLI tool (codemie-ai/codemie-code repository on GitHub).

When should I use Report Issue?

Report Issue fits situations like: wants to report a bug; suggest a feature for the CodeMie Code CLI tool (codemie-ai/codemie-code repository on GitHub); phrases include: report a bug; submit an issue.

How do I install Report Issue in Claude Code?

Run `npx skills add codemie-ai/codemie-code --skill report-issue -a claude-code`. Or copy the skill folder (src/agents/plugins/claude/plugin/skills/report-issue in codemie-ai/codemie-code) into .claude/skills/report-issue in your project. Claude Code loads it when a task matches its description.

How do I install Report Issue in Codex?

Run `npx skills add codemie-ai/codemie-code --skill report-issue -a codex`. Or copy the skill folder (src/agents/plugins/claude/plugin/skills/report-issue in codemie-ai/codemie-code) into .agents/skills/report-issue in your project. Codex loads it when a task matches its description.

Can I use Report Issue in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add codemie-ai/codemie-code --skill report-issue -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/report-issue, .gemini/skills/report-issue, .github/skills/report-issue and .opencode/skills/report-issue in your project.

What does Report Issue need to run?

Going by SKILL.md and its folder, Report Issue needs the command-line tools its instructions call (gh, node, npm, brew, apt and dnf). Our summary lists: Node.js. Its frontmatter pre-approves these tools: Bash, Read, Grep.

Does Report Issue access the network?

SKILL.md names 2 domains. In commands or code: gist.github.com; the agent is likely to contact it when it follows the instructions. As links in the text: cli.github.com. This is read from the text; nothing was executed.

Is Report Issue safe to install?

Our automated static check of SKILL.md found notes only (runs commands with sudo; pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Report Issue use?

Report Issue is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Report Issue use?

About 2.3k tokens (SKILL.md is roughly 9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Report Issue?

Skills that share tags, products or a category with Report Issue: DeerFlow Smoke Test (bytedance/deer-flow, 83k stars), Weavebench Cua Reproduce (AMAP-ML/LongHorizon-Harness, 1.7k stars), Evidence-Driven Testing (michaelshimeles/skills, 1.3k stars) and Senior QA (nicepkg/auto-company, 192 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Report Issue?

codemie-ai (a GitHub user) maintains it in codemie-ai/codemie-code, which has 294 GitHub stars. The repository holds 9 skills in this directory. The repository was last updated on October 7, 2026.

Source: codemie-ai/codemie-code on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.