Official agent skill

Dd File Issue

by DataDog in DataDog/pup

File GitHub issues to the right repository (pup CLI or plugin)

OfficialApache-2.0Auto-check passedBackend & APIs

Install Dd File Issue

skills CLI
$ npx skills add DataDog/pup --skill dd-file-issue -a claude-code

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

GitHub CLI
$ gh skill install DataDog/pup dd-file-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/DataDog/pup.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/dd-file-issue .claude/skills/dd-file-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
dd-file-issue
GitHub stars
1k
Token cost
~2.3k tokens
SKILL.md length
683 words
Files
1
Skills in repo
12
Repo updated
First seen
Licence
Apache-2.0

At a glance

File GitHub issues to the right repository (pup CLI or plugin)

  • Works in 3 steps: Determine Repository → Search for Existing Issues → Create Issue
  • Backend & APIs work in your project
  • SKILL.md covers Decision Logic: Which…, Workflow, Implementation and Best Practices, plus 4 more sections
  • Calls gh

What it does

Dd File Issue is an agent skill from DataDog/pup, published by the product's own GitHub organization. File GitHub issues to the right repository (pup CLI or plugin)

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 Backend & APIs. It works with Datadog and GitHub. The repository describes itself as: Give your AI agent a Pup — a CLI companion with 200+ commands across 33+ Datadog products. The licence is Apache-2.0.

When your agent uses it

  • Backend & APIs work in your project

Example prompts

  • “/dd-file-issue”

Requirements

  • Node.js

Workflow steps

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

  1. Determine Repository
  2. Search for Existing Issues
  3. Create Issue

What it can do on your machine

Read from SKILL.md and the folder at commit 6a3c662. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • gh

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

  • Network

    No URLs in SKILL.md. Its commands use gh, which can reach the network depending on how they are called.

    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

Dd File Issue loads about 2.3k tokens when it runs. Until then it costs about 19 tokens; SKILL.md has 683 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~19
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 passed

The automated check found no risky patterns in SKILL.md.

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 DataDog/pup at commit 6a3c662, republished under its Apache-2.0 licence (© DataDog). 683 words, ~2,293 tokens.

Download SKILL.mdSave it as .claude/skills/dd-file-issue/SKILL.md (or your agent's skills folder).
name
dd-file-issue
description
File GitHub issues to the right repository (pup CLI or plugin)
trigger
Use this skill when the user wants to: - Report a bug - Request a feature - File an issue - Submit a problem report - Report something not working - Suggest…
examples
This isn't working, file an issue, Can you create a bug report for this?, I want to request a new feature, Report this error to the team

DD File Issue Skill

This skill helps you file GitHub issues to the correct repository. All issues — whether related to the pup CLI, skills, agents, or documentation — are tracked in DataDog/pup.

Invocation: /dd-file-issue

Decision Logic: Which Repository?

File to DataDog/pup Repository

All issues are filed here, including:

  • API Functionality: API calls failing, incorrect responses, missing API endpoints
  • Authentication: OAuth2 issues, token refresh problems, API key handling
  • CLI Behavior: Command syntax, flags not working, output format issues
  • pup Installation: Binary installation, PATH issues, version problems
  • API Coverage: Missing Datadog API endpoints, incomplete command coverage
  • Performance: Slow API calls, timeout issues
  • Error Messages: Confusing pup error messages, API errors
  • Agent Behavior: Agent selection, agent prompts, agent responses
  • Documentation: README, CLAUDE.md, AGENTS.md, agent files inaccurate
  • Agent Prompts: Agent giving wrong guidance, unclear instructions
  • Skill Issues: Skills not working correctly
  • Agent Selection: Claude picking wrong agent for task
  • Examples/Guides: Missing or incorrect examples in agent files
  • User Experience: Confusing workflows, unclear instructions

Example Issues:

  • "pup logs search returns 404 error"
  • "OAuth token refresh not working"
  • "Need support for new Datadog API endpoint"
  • "pup --output=json returns invalid JSON"
  • "pup auth login fails on Linux"
  • "logs agent doesn't explain query syntax clearly"
  • "Agent tells me to use wrong pup command"
  • "Documentation says to use TypeScript but we use pup now"
  • "Need better examples for metrics queries"
  • "Agent selection guide is confusing"

Workflow

  1. Gather Information

    • What went wrong?
    • What were you trying to do?
    • What error message did you see (if any)?
    • What agent/command were you using?
  2. Determine Repository

    • All issues go to DataDog/pup
  3. Check for Existing Issues

    • Search the target repository for similar issues
    • If found, suggest commenting on existing issue instead
  4. Collect Issue Details

    • Title: Clear, concise summary (e.g., "logs agent: incorrect time format example")
    • Body: Detailed description with:
      • What happened
      • Expected behavior
      • Steps to reproduce
      • Environment details (OS, pup version, plugin version)
      • Relevant logs/errors
  5. Select Issue Type

    • Bug report
    • Feature request
    • Documentation improvement
    • Question
  6. Create Issue

    • Use gh issue create to file the issue
    • Add appropriate labels
    • Provide issue URL to user

Implementation

1. Determine Repository

All issues are filed against DataDog/pup. Ask clarifying questions to gather detail:

markdown
To file this issue correctly, I need to understand:

1. What were you trying to do?
2. What went wrong?
3. Was this a problem with:
   - A pup command not working?
   - An agent giving bad guidance?
   - Documentation being wrong/unclear?
2. Search for Existing Issues
bash
gh issue list \
  --repo DataDog/pup \
  --search "your search terms" \
  --limit 10
3. Create Issue
bash
gh issue create \
  --repo DataDog/pup \
  --title "Clear, concise title" \
  --body "Detailed description" \
  --label "bug" # or "enhancement", "documentation"
Issue Body Template

Use this template for comprehensive issue reports:

markdown
## Description
[Clear description of the issue]

## Expected Behavior
[What should happen]

## Actual Behavior
[What actually happened]

## Steps to Reproduce
1. [First step]
2. [Second step]
3. [...]

## Environment
- OS: [e.g., macOS 14.1, Ubuntu 22.04]
- Pup version: [run `pup --version`]
- Plugin version: [from plugin.json]
- Claude Code version: [if relevant]

## Error Messages / Logs

[Paste any error messages or relevant logs]


## Additional Context
[Any other relevant information]

## Suggested Fix (Optional)
[If you have ideas for how to fix this]

Best Practices

Good Issue Titles

✅ Good:

  • "logs agent: incorrect time format documentation"
  • "pup metrics query: --from flag ignores relative time"
  • "Agent selection guide: missing decision tree for security agents"

❌ Bad:

  • "It doesn't work"
  • "Bug"
  • "Help"
Show full SKILL.md (263 more words)Show less
When to Bundle Issues
  • Don't bundle unrelated issues - file separately
  • Do bundle if multiple issues stem from same root cause
  • Do bundle if documenting several examples of same problem
Labels to Use

For pup repository:

  • bug - Something isn't working
  • enhancement - New feature or request
  • documentation - Improvements or additions to documentation
  • agent - Related to specific agent behavior
  • skill - Related to skills
  • question - Further information is requested

Examples

Example 1: Filing a pup Bug

User: "The pup logs search command times out after 30 seconds"

Analysis: This is a pup CLI issue (command behavior)

Steps:

  1. Search existing issues: gh issue list --repo DataDog/pup --search "timeout"
  2. If not found, create issue:
bash
gh issue create \
  --repo DataDog/pup \
  --title "pup logs search: command times out after 30 seconds" \
  --body "## Description
The \`pup logs search\` command times out after 30 seconds when searching large time ranges.

## Expected Behavior
Should either complete the query or allow configurable timeout.

## Actual Behavior
Command fails with timeout error after 30 seconds.

## Steps to Reproduce
1. Run: \`pup logs search --query='*' --from='7d' --to='now'\`
2. Wait 30 seconds
3. See timeout error

## Environment
- OS: macOS 14.1
- Pup version: 1.2.3
- DD_SITE: datadoghq.com

## Error Message
\`\`\`
Error: request timeout after 30000ms
\`\`\`
" \
  --label "bug"
Example 2: Filing a Documentation Issue

User: "The logs agent documentation shows TypeScript examples instead of pup commands"

Analysis: This is a documentation issue

Steps:

  1. Search existing issues: gh issue list --repo DataDog/pup --search "TypeScript"
  2. Create issue:
bash
gh issue create \
  --repo DataDog/pup \
  --title "logs agent: outdated TypeScript examples in documentation" \
  --body "## Description
The logs agent documentation still shows TypeScript/Node.js examples instead of pup CLI commands.

## Location
\`agents/logs.md\` lines 150-200

## Expected
Should show pup CLI command examples like:
\`\`\`bash
pup logs search --query='*' --from='1h'
\`\`\`

## Actual
Shows TypeScript code with imports and API clients

## Impact
Confusing for users who expect pup CLI commands

## Files Affected
- agents/logs.md
- Possibly other agent files (need audit)
" \
  --label "documentation" \
  --label "agent"
Example 3: Feature Request

User: "Can we add an agent for Datadog SLO reporting?"

Analysis: This is a pup enhancement (new agent)

bash
gh issue create \
  --repo DataDog/pup \
  --title "enhancement: add SLO reporting agent" \
  --body "## Feature Request

### Description
Add a new agent focused on SLO reporting and analysis, separate from the SLO management agent.

### Use Cases
- Generate SLO reports for stakeholders
- Analyze SLO trends over time
- Compare SLOs across services

### Proposed Agent Capabilities
- Query SLO history
- Generate formatted reports
- Calculate SLO burn rates
- Identify at-risk SLOs

### Related Agents
- Current \`slos.md\` focuses on SLO CRUD operations
- New agent would focus on analytics and reporting

### Priority
Medium - would improve SLO workflow
" \
  --label "enhancement" \
  --label "agent"

Error Handling

If issue creation fails:

  1. Check network connectivity
  2. Verify gh CLI is authenticated: gh auth status
  3. Check repository permissions
  4. Provide user with issue details to file manually

Success Response

After successfully filing an issue:

markdown
✅ Issue created successfully!

**Repository**: DataDog/pup
**Issue**: #123
**URL**: https://github.com/DataDog/pup/issues/123
**Title**: [issue title]

The team will review your issue and respond soon. You can:
- Track the issue at the URL above
- Add more details by commenting on the issue
- Subscribe to notifications for updates

Tips for Users

  1. Be specific - Include exact commands, error messages, agent names
  2. Provide context - What were you trying to accomplish?
  3. Include environment details - OS, versions, configuration
  4. One issue per report - Don't bundle unrelated problems
  5. Check existing issues first - Avoid duplicates
  6. Be patient - Maintainers will respond when available

© DataDog, 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 skills/dd-file-issue of DataDog/pup.

Open the folder on GitHubat commit 6a3c662

Compare with similar skills

Dd File 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.

Dd File Issue compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Dd File Issue this skillDataDog/pup1k—~2.3kAutomated safety check: PassApache-2.0
Datadog Data Source GeneratorDataDog/terraform-provider-datadog468—~2.7kAutomated safety check: PassMPL-2.0
Release Lambda LayerDataDog/datadog-lambda-js126—~1.8kAutomated safety check: PassApache-2.0
Clarify Java CommentsDataDog/dd-trace-java736—~2.3kAutomated safety check: NotesApache-2.0
Debug Issue With Datadoglangfuse/langfuse35k—~1.6kAutomated safety check: PassCustom licence
Review PRDataDog/dd-trace-dotnet573—~788Automated safety check: PassApache-2.0

Similar skills

  • Datadog Data Source Generator

    DataDog/terraform-provider-datadog

    Official

    Generates a Datadog Terraform provider data source from an OpenAPI operation with tfgen and opens a review-ready GitHub PR with a risk scan and testing guide.

    468 GitHub stars~2.7k tokensUpdated today
    DevOps & CloudAuto-check passed
  • Release Lambda Layer

    DataDog/datadog-lambda-js

    Official

    Walks through releasing a new datadog-lambda-js Lambda layer version — the automated Commercial release (version bump, tag, GitLab sign/publish jobs, npm publish, GitHub release) and the manual…

    126 GitHub stars~1.8k tokensUpdated today
    Testing & QAAuto-check passed
  • Clarify Java Comments

    DataDog/dd-trace-java

    Official

    Clarify or review Java Javadocs, Javadoc tags, and explanatory code comments for legibility, accuracy, and source alignment.

    736 GitHub stars~2.3k tokensUpdated today
    DevelopmentAuto-check: notes
  • Debug Issue With Datadog

    langfuse/langfuse

    Establish root cause by combining Datadog telemetry with the Langfuse repo.

    35k GitHub stars~1.6k tokensUpdated today
    AI & LLM EngineeringAuto-check passed
  • Review PR

    DataDog/dd-trace-dotnet

    Official

    Perform a review on a GitHub PR, leaving comments on the PR. An agent skill from DataDog/dd-trace-dotnet.

    573 GitHub stars~788 tokensUpdated today
    DevelopmentAuto-check passed
  • Golang Samber Slog

    context-labs/whip

    Structured logging extensions for Golang using samber/slog- — multi-handler pipelines, sampling, attribute formatting, HTTP middleware (gin, echo, fiber, chi), backend routing (datadog, sentry…

    1.1k GitHub starsUsed in 2 repos~3k tokens
    DevOps & CloudAuto-check passed

More from DataDog/pup

All 12 skills in this repo
  • Dd Idp

    DataDog/pup

    Official

    Find, filter, count, and connect software, teams, engineering work and delivery, infrastructure, and operational or security records through Pup's read-only Datadog entity graph.

    1k GitHub stars~2k tokensUpdated today
    Auto-check passed
  • Dd Debugger

    DataDog/pup

    Official

    Live Debugger - inspect runtime argument/variable values in production by placing log probes on methods.

    1k GitHub stars~2.7k tokensUpdated today
    Auto-check passed
  • Dd Docs

    DataDog/pup

    Official

    Datadog docs lookup using docs.datadoghq.com/llms.txt and linked Markdown pages.

    1k GitHub starsUsed in 1 repo~558 tokens
    Auto-check passed
  • Pup

    DataDog/pup

    Official

    Datadog API CLI with 49 command groups, 300+ subcommands. An agent skill from DataDog/pup.

    1k GitHub stars~523 tokensUpdated today
    Auto-check passed
  • Official

    Load when investigating a specific flaky test. An agent skill from DataDog/pup.

    1k GitHub starsUsed in 1 repo~2.3k tokens
    Auto-check passed
  • Dd Apm

    DataDog/pup

    Official

    APM - traces, services, dependencies, performance analysis. An agent skill from DataDog/pup.

    1k GitHub stars~1.5k tokensUpdated today
    Auto-check passed

Works with

Categories

Questions about Dd File Issue

What does Dd File Issue do?

File GitHub issues to the right repository (pup CLI or plugin). Dd File Issue is an agent skill from DataDog/pup, published by the product's own GitHub organization.

When should I use Dd File Issue?

Dd File Issue fits situations like: backend & APIs work in your project.

How do I install Dd File Issue in Claude Code?

Run `npx skills add DataDog/pup --skill dd-file-issue -a claude-code`. Or copy the skill folder (skills/dd-file-issue in DataDog/pup) into .claude/skills/dd-file-issue in your project. Claude Code loads it when a task matches its description.

How do I install Dd File Issue in Codex?

Run `npx skills add DataDog/pup --skill dd-file-issue -a codex`. Or copy the skill folder (skills/dd-file-issue in DataDog/pup) into .agents/skills/dd-file-issue in your project. Codex loads it when a task matches its description.

Can I use Dd File 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 DataDog/pup --skill dd-file-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/dd-file-issue, .gemini/skills/dd-file-issue, .github/skills/dd-file-issue and .opencode/skills/dd-file-issue in your project.

What does Dd File Issue need to run?

Going by SKILL.md and its folder, Dd File Issue needs the command-line tools its instructions call (gh). Our summary lists: Node.js.

Does Dd File Issue access the network?

SKILL.md contains no URLs. Its commands use gh, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Dd File Issue safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Dd File Issue use?

Dd File 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 Dd File Issue use?

About 2.3k tokens (SKILL.md is roughly 9.2k 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 Dd File Issue?

Skills that share tags, products or a category with Dd File Issue: Datadog Data Source Generator (DataDog/terraform-provider-datadog, 468 stars), Release Lambda Layer (DataDog/datadog-lambda-js, 126 stars), Clarify Java Comments (DataDog/dd-trace-java, 736 stars) and Debug Issue With Datadog (langfuse/langfuse, 35k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Dd File Issue?

DataDog (a GitHub organization, an official publisher) maintains it in DataDog/pup, which has 1,026 GitHub stars. The repository holds 12 skills in this directory. The repository was last updated on October 7, 2026.

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