What does this skill do, and when should you use it?
This skill converts error logs, voice dictation, raw notes, or screenshot descriptions into structured GitHub-flavored Markdown issues. Its template covers the summary, environment, reproduction steps, expected and actual behavior, error details, visual evidence, impact, and additional context. It also maps impact to severity and replaces potentially sensitive values with placeholders. It fits teams that need consistent issue reports, but the source does not indicate that it creates remote GitHub issues through an API.
Reads the user's bug notes, error messages, and screenshot context; extracts product, version, environment, reproduction steps, expected behavior, and actual behavior; formats error codes and messages; references attached images or GIFs; replaces sensitive fields with placeholders such as [PROJECT_NAME] and [USER_ID]; assigns severity based on outage, data loss, security impact, feature impairment, or minor inconvenience; generates a fixed Markdown issue and places it in /issues/ using a date-based filename.
- A developer pastes an unstructured error log and needs a GitHub-ready issue.
- A tester provides voice dictation or scattered notes and needs clear reproduction steps and impact.
- A support engineer includes screenshots or GIFs and needs the visual evidence referenced inline.
- A team wants outage, regression, feature, and UI reports to follow one Markdown format.
- A bug report contains project names or user IDs that should be replaced with safe placeholders.
How do you install this skill?
- Confirm authorization, target repository, and filename before creating an /issues/ file; preferably show the draft first.
- Do not fill factual gaps from memory; use placeholders or explicitly mark unknown values for unverified environment, version, product, or impact details.
- Add handling rules for empty input, conflicting facts, missing attachments, sensitive-data detection, and directory or file-write failures.
- No skill-specific acceptance criteria or test evidence is shown, so outputs should be treated as drafts requiring human review.
- Local filesystem
Run this in the project:
npx skills add microsoft/skills
Select github-issue-creator in the installation wizard. The skill is installed into the selected agent's directory, such as .github/skills/ for GitHub Copilot. You can also copy the .github/skills/github-issue-creator/ directory from the repository.
tmp="$(mktemp -d)"
git clone --depth 1 https://github.com/microsoft/skills.git "$tmp"
mkdir -p ~/.claude/skills
cp -R "$tmp/.github/skills/github-issue-creator" ~/.claude/skills/
rm -rf "$tmp"Generated from the source repository and skill path; it copies only this skill's folder. If the author's install steps above differ, follow those first. To scope it to one project, replace ~/.claude/skills with that project's .claude/skills.
How do you use this skill?
Once installed, send your agent any of these to trigger it:
- Turn these error logs and reproduction notes into a GitHub issue: …
Give the agent the raw failure information and ask it to format a GitHub issue, for example: “Turn these error logs and reproduction notes into a GitHub issue: …”. The generated issue should be saved as /issues/YYYY-MM-DD-short-description.md. The source does not document a specific file-creation command or a remote GitHub submission workflow.
What are this skill's strengths and limitations?
- A consistent template covers environment, reproduction, behavior differences, errors, and impact.
- Extracts structure from voice dictation, error logs, and screenshot descriptions.
- Provides severity rules and sensitive-data placeholder guidance.
- Supports inline references to screenshots and GIFs.
- The source does not show dedicated tests or test results for this skill.
- It specifies Markdown file creation but does not show direct remote GitHub Issue creation.
- The runtime needs write access to a local /issues/ directory.
- Filling missing context depends on conversation context or memory and may require review.
How does this skill compare with similar options?
Side by side with related skills; every score comes from the same FSRS standard.
| Skill | FS score | Stars | Last updated | License |
|---|---|---|---|---|
| GitHub Issue Creator this page ✓ Microsoft · Official | 43 · Not recommended | ★ 2.7k | 3mo ago | MIT |
| Codex Issue Digest ✓ OpenAI · Official | 57 · Use with care | ★ 129k | 11d ago | Apache-2.0 |
| RenderCV Issue Solver | 51 · Use with care | ★ 18k | 7mo ago | MIT |
| Playwright Issue Triage ✓ Microsoft · Official | 48 · Use with care | ★ 98k | 11d ago | Apache-2.0 |
| Codex Bug Triage Assistant ✓ OpenAI · Official | 40 · Not recommended | ★ 129k | 11d ago | Apache-2.0 |
How did FollowSkills review this skill?
The skill requires placeholders for potentially sensitive data and scopes output to Markdown files under the repository's /issues/ directory. However, it lacks user confirmation, permission boundaries, data-flow disclosure, rollback, or pre-creation review, and its instruction to fill gaps from memory can introduce unverified facts, so points are deducted.
Input types, template, and severity rules are broadly consistent, with no declared external dependency. Handling and diagnostic feedback are missing for empty input, conflicting facts, absent attachments, missing directories, and invalid filenames; static calibration therefore limits this score to 6.
The audience, input forms, and expected GitHub issue structure are reasonably clear. Non-fit scenarios, trigger boundaries, required fields, Chinese-language support, and detailed screenshot/GIF behavior are not defined, so points are deducted.
The skill has a name, description, structured sections, guidelines, and two examples; repository context also supplies an MIT license, official provenance, and active-development signal. The skill itself lacks versioning, changelog, maintenance ownership, installation notes, FAQs, and explicit limitations, while assuming the output path exists.
It offers direct value for turning notes and logs into readable issue drafts, and the examples show usable structures. However, outputs require factual review, the file-creation workflow is underspecified, and severity or environment details may be inferred incorrectly, so only limited static credit is warranted.
The skill includes a template and examples, but they are not independently reproducible test evidence. The supplied repository tests and CI cover a general Copilot harness rather than this skill's key paths, so verifiability remains low.
Open a dimension to read why it scored that way
Evidence confidence：Low — Mostly static review, author material or a limited demo; useful for discovery, not high-risk decisions.
See the full review method →