New: 97,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Create Issue

by rajbos in rajbos/ai-engineering-fluency

Create a well-scoped GitHub issue in this repo. An agent skill from rajbos/ai-engineering-fluency.

MITAuto-check passedDevelopment

Install Create Issue

skills CLI
$ npx skills add rajbos/ai-engineering-fluency --skill create-issue -a claude-code

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

GitHub CLI
$ gh skill install rajbos/ai-engineering-fluency create-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/rajbos/ai-engineering-fluency.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/create-issue .claude/skills/create-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
create-issue
GitHub stars
115
Token cost
~2k tokens
SKILL.md length
1,016 words
Files
1
Skills in repo
22
Repo updated
First seen
Licence
MIT

At a glance

Create a well-scoped GitHub issue in this repo. An agent skill from rajbos/ai-engineering-fluency.

  • Works in 6 steps: Understand what and where → Investigate the codebase → Define the implementation → …
  • The user asks to create
  • SKILL.md covers When to Use This Skill, Step 1 — Understand what and…, Step 2 — Investigate the… and Step 3 — Define the…, plus 4 more sections
  • Calls gh, npm and dotnet

What it does

Create Issue is an agent skill from rajbos/ai-engineering-fluency. Create a well-scoped GitHub issue in this repo. Gathers what to implement and where from the user (asking about gaps), maps the change to concrete places in the codebase, lists tests to update, and checks for cross-surface gaps (VS Code extension vs. shared src/ vs. CLI/npm package vs. other hosts) before filing. Use whenever the user asks to create, file, write up or log an issue, feature request, bug or tech-debt item for this repository.

Its SKILL.md is about 2k 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 Development, covering Technical debt. It works with GitHub, Visual Studio Code and npm. The repository describes itself as: Extension that shows information about the estimated token usage and more of AI in editors/CLI's. The licence is MIT.

When your agent uses it

  • The user asks to create
  • Feature request
  • Tech-debt item for this repository

Example prompts

  • “/create-issue”

Workflow steps

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

  1. Understand what and where
  2. Investigate the codebase
  3. Define the implementation
  4. Tests
  5. Check for cross-surface gaps
  6. Create the issue

What it can do on your machine

Read from SKILL.md and the folder at commit 6933e2a. 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
    • npm
    • dotnet

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

  • Network

    No URLs in SKILL.md. Its commands use gh and npm, 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

Create Issue loads about 2k tokens when it runs. Until then it costs about 114 tokens; SKILL.md has 1,016 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~114
When it runs · the whole SKILL.md, loaded when a task matches
~2k

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 rajbos/ai-engineering-fluency at commit 6933e2a, republished under its MIT licence (© rajbos). 1,016 words, ~2,013 tokens.

Download SKILL.mdSave it as .claude/skills/create-issue/SKILL.md (or your agent's skills folder).
name
create-issue
description
Create a well-scoped GitHub issue in this repo. Gathers what to implement and where from the user (asking about gaps), maps the change to concrete places in the codebase, lists tests to update, and checks for cross-surface gaps (VS Code extension vs. shared src/ vs. CLI/npm package vs. other hosts) before filing. Use whenever the user asks to create, file, write up or log an issue, feature request, bug or tech-debt item for this repository.

Create Issue Skill

This skill is guidance only (no scripts). It describes how issues in this repo must be prepared before they are filed, so that whoever picks the issue up (a person or a coding agent) can start without re-doing the research.

When to Use This Skill

Use it whenever you are asked to create, file or write up an issue for this repository — features, bugs, improvements, tech debt. Do not file an issue from a one-line request without going through the steps below.

Step 1 — Understand what and where

Get the following from the user. Take what they already said; do not re-ask for it.

  • What should be implemented, fixed or changed, and why (the problem or the value).
  • Where it shows up: which surface(s) — VS Code extension, CLI, Visual Studio, JetBrains, desktop app, sharing-server, copilot-app canvas, docs/scripts — and which view/tab/command if it is UI.
  • For bugs: steps to reproduce, expected vs. actual, versions/editor involved.

If any of this is unclear, ambiguous or you detect a gap (e.g. the request names a view but not what data it should show, or it is unclear whether other surfaces should get it too), ask the user before continuing. Ask concise, specific questions; batch them in one message. Prefer a recommendation ("I assume X, correct?") over open-ended questions. If the user cannot answer, record the open question in the issue instead of guessing.

Step 2 — Investigate the codebase

Before writing anything, look at the code. Do not describe changes from memory.

  • Start from AGENTS.md (repo structure, sub-project instructions) and the matching .github/instructions/*.instructions.md.
  • If .graphify-agent/graph.json exists, query it for structural questions (callers, blast radius), e.g. GRAPHIFY_OUT=.graphify-agent graphify query "<question>" (or pass --graph .graphify-agent/graph.json). Do not use the committed graphify-out/ directory; if the graph is missing, search with grep/glob.
  • Check docs/ (especially docs/features/, docs/adr/, docs/FLUENCY-METRICS-SCHEMA.md, docs/TRACKABLE-DATA.md) for existing design decisions that apply.
  • Search existing open and recently closed issues/PRs (gh issue list --state all --search "<keywords>", gh pr list --state all --search "<keywords>") to avoid duplicates; link related ones instead of duplicating.

Step 3 — Define the implementation

In the issue, list the places in the codebase that need to change, and how. Be concrete: file paths (and function/class names where useful), and one or two sentences per place on what changes there. Respect the repo's architecture:

  • Session parsing, token estimation and cost attribution live in the shared src/ modules; the CLI and VS Code extension consume them. Logic must not be reimplemented per surface (see "CLI Must Reuse Shared Functions" in AGENTS.md).
  • Webview changes must be registered/validated per AGENTS.md (views.config.json, a state for new tabs, check:contract, check:interaction, visual:diff).
  • New user-facing strings need localization keys and l10n.test.ts coverage.
  • Changes to sharing-server must follow sharing-server/AGENTS.md (data separation contract).
  • Changes to agents or skills under .github/ need the mirrored change under .claude/ (and vice versa).

State the approach you recommend; if there are real alternatives with different trade-offs, name them briefly.

Step 4 — Tests

List the tests that must be added or updated: the existing test files that cover the touched code (find them, give paths) and new cases needed (edge cases, regressions, empty/missing data). Name the validation commands from the relevant instructions file (e.g. npm run test:node, npm run check:contract, npm run check:interaction, dotnet test, ./gradlew test). If a UI changes, note that before/after screenshots are expected.

Show full SKILL.md (464 more words)Show less

Step 5 — Check for cross-surface gaps

This is the step that is most often skipped. Actively look for gaps the change would surface, by following the data from where it is produced to every place it is consumed.

The canonical example: a field is added to a view in the VS Code extension, but the data behind it is not available in the shared src/ modules / the CLI / the npm package (@rajbos/ai-engineering-fluency), so the other extension surfaces (CLI, Visual Studio, JetBrains, desktop, sharing-server, copilot-app) cannot show it and end up with empty or partial views.

Check, and record the result of each in the issue (even "not affected"):

  • Data availability: is every new piece of data computed in shared code and exposed through the CLI/npm package output, or only inside vscode-extension/? Does it need adding to the JSON/export schema and its docs?
  • Other surfaces: does each host that renders this view (Visual Studio, JetBrains via sync-host-views, desktop, sharing-server dashboard, copilot-app canvas) receive the new data, or will it show empty sections? Is a follow-up issue needed for those hosts?
  • Editors/adapters: does it work for every supported session source (Copilot Chat, Copilot CLI, Claude Code, JetBrains, etc.), or only the one the user tested with? What does the view show when the data is absent?
  • Upload/sharing path: if data is uploaded or shared, does the sharing-server schema, API and privacy contract need to change?
  • Docs & catalog: CHANGELOG, docs/, the What's New catalog, package.nls*.json, README screenshots.
  • Compatibility: stored/cached data and older CLI/extension versions reading new data (or vice versa).

If a gap is out of scope for this issue, say so explicitly and propose a separate follow-up issue (create it only with the user's agreement).

Step 6 — Create the issue

Compose the issue and show the user the draft (title + body) before filing, unless they already told you to just create it. Then file it with gh issue create.

  • Template/title/labels: this repo has issue templates in .github/ISSUE_TEMPLATE/ (VS Code, CLI, Visual Studio). Use the one that matches the primary surface for the title prefix (e.g. [FEATURE][vscode] , [BUG][cli] ) and labels; for other surfaces, use a similar prefix and only labels that exist (gh label list). Do not invent labels.
  • Pass the body via --body-file (write it to a scratch file) to avoid shell quoting problems.

Suggested body structure:

markdown
## Summary
What and why, in 2–4 sentences.

## Current behaviour / problem
(bugs: repro steps, expected vs. actual)

## Proposed change
Where and how, per surface/file:
- `path/to/file.ts` — what changes
- ...

## Tests
- Update: `path/to/existing.test.ts` — what to add/adjust
- New: ...
- Validation: commands to run

## Cross-surface impact / gaps
- Data availability (shared `src/`, CLI, npm package): ...
- Other surfaces (VS Code, CLI, Visual Studio, JetBrains, desktop, sharing-server, copilot-app): ...
- Docs / changelog / What's New / localization: ...

## Open questions
Anything the user could not answer yet.

## Related
Links to related issues/PRs/docs.

Keep it factual and scoped; do not pad sections that do not apply (write "n/a" with a short reason instead). After filing, give the user the issue URL and a short list of any follow-up issues you recommend.

Rules

  • Never file before Steps 1–5 are done; never fabricate file paths, test names or labels — verify they exist.
  • Never include secrets, personal data or real session content in an issue.
  • Do not start implementing the issue unless the user asks.

© rajbos, MIT. 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 .claude/skills/create-issue of rajbos/ai-engineering-fluency.

Open the folder on GitHubat commit 6933e2a

Compare with similar skills

Create 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.

Create Issue compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Create Issue this skillrajbos/ai-engineering-fluency115—~2kAutomated safety check: PassMIT
Releasesignageos/vscode-sops122—~2.2kAutomated safety check: NotesMIT
Publish ExtensionFreakStudioCN/mpy-hardware-extension118—~1.3kAutomated safety check: PassCustom licence
Cutting A ReleaseTriliumNext/Trilium38k—~3.2kAutomated safety check: PassAGPL-3.0
Verdaccio Pull Request Workflowverdaccio/verdaccio18k—~1.9kAutomated safety check: PassMIT
Update .NET Supported OS Matrixdotnet/core22k—~4.1kAutomated safety check: PassMIT

Similar skills

  • Release

    signageos/vscode-sops

    Releases the vscode-sops extension end-to-end: determines the next version from the bump history, updates CHANGELOG.md and package.json/package-lock.json, builds via vscode:prepublish, publishes to…

    122 GitHub stars~2.2k tokensUpdated 6 mo ago
    DevelopmentAuto-check: notes

  • Publish Extension

    FreakStudioCN/mpy-hardware-extension

    发布 Blockless VS Code 扩展到 Visual Studio Marketplace（含发布前测试）/ ship the Blockless extension to the VS Code Marketplace.

    118 GitHub stars~1.3k tokensUpdated 9 days ago
    DevOps & CloudAuto-check passed

  • Cutting A Release

    TriliumNext/Trilium

    A skill your agent uses when cutting, preparing, or debugging a Trilium release — bumping the monorepo version, tagging, or diagnosing a failed "Release" workflow run.

    38k GitHub stars~3.2k tokensUpdated today
    DevelopmentAuto-check passed

  • Verdaccio Pull Request Workflow

    verdaccio/verdaccio

    Takes a change through a verdaccio pull request: branch, local checks, changeset, title and body, labels, CI and review rounds, and ports to other release lines.

    18k GitHub stars~1.9k tokensUpdated today
    DevelopmentAuto-check passed

  • Update .NET Supported OS Matrix

    dotnet/core

    Official

    Audits and updates the supported-os.json files for .NET releases, checking them against upstream lifecycle data and regenerating the markdown with the release-notes tool.

    22k GitHub stars~4.1k tokensUpdated yesterday
    DevelopmentAuto-check passed

  • Hunk Release Workflow

    modem-dev/hunk

    Maintainer workflow for preparing, publishing, verifying and curating Hunk releases, with confirmation gates before tags, publishes and public edits.

    9.5k GitHub stars~3.8k tokensUpdated today
    DevelopmentAuto-check passed

More from rajbos/ai-engineering-fluency

All 22 skills in this repo

  • Check Urls

    rajbos/ai-engineering-fluency

    Find all hardcoded URLs in TypeScript source files and verify they resolve (return HTTP 2xx/3xx).

    115 GitHub stars~662 tokensUpdated yesterday
    Auto-check passed

  • Deduplicate Code

    rajbos/ai-engineering-fluency

    Detect copy-pasted code blocks across the shared source (vscode-extension/src, the repo-root src/, cli/src) with the dependency-free check-code-duplication.js detector, then pick one duplicate group…

    115 GitHub stars~2.4k tokensUpdated yesterday
    Auto-check passed

  • Improve Tool Families

    rajbos/ai-engineering-fluency

    Analyze coverage of the vscode-extension's tool-family definitions (DEFAULTTOOLFAMILIES in vscode-extension/src/toolFamilies.ts) against the canonical tool-name list in src/toolNames.json and/or a…

    115 GitHub stars~1.3k tokensUpdated yesterday
    Auto-check passed

  • Load Cache Data

    rajbos/ai-engineering-fluency

    Load and display the last 10 cache entries as raw JSON output.

    115 GitHub stars~3.2k tokensUpdated yesterday
    Auto-check passed

  • PR Risk Review

    rajbos/ai-engineering-fluency

    Assess the risk of a changeset (a PR, a branch, or the working tree) and classify it as low, medium, or high with a written rationale.

    115 GitHub stars~2.6k tokensUpdated yesterday
    Auto-check passed

  • Session Log Data

    rajbos/ai-engineering-fluency

    Describes the data files available in the coding agent environment after copilot-setup-steps runs.

    115 GitHub stars~1.7k tokensUpdated yesterday
    Auto-check passed

Works with

Categories

Questions about Create Issue

What does Create Issue do?

Create a well-scoped GitHub issue in this repo. An agent skill from rajbos/ai-engineering-fluency. Create Issue is an agent skill from rajbos/ai-engineering-fluency. Create a well-scoped GitHub issue in this repo.

When should I use Create Issue?

Create Issue fits situations like: the user asks to create; feature request; tech-debt item for this repository.

How do I install Create Issue in Claude Code?

Run `npx skills add rajbos/ai-engineering-fluency --skill create-issue -a claude-code`. Or copy the skill folder (.claude/skills/create-issue in rajbos/ai-engineering-fluency) into .claude/skills/create-issue in your project. Claude Code loads it when a task matches its description.

How do I install Create Issue in Codex?

Run `npx skills add rajbos/ai-engineering-fluency --skill create-issue -a codex`. Or copy the skill folder (.claude/skills/create-issue in rajbos/ai-engineering-fluency) into .agents/skills/create-issue in your project. Codex loads it when a task matches its description.

Can I use Create 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 rajbos/ai-engineering-fluency --skill create-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/create-issue, .gemini/skills/create-issue, .github/skills/create-issue and .opencode/skills/create-issue in your project.

What does Create Issue need to run?

Going by SKILL.md and its folder, Create Issue needs the command-line tools its instructions call (gh, npm and dotnet).

Does Create Issue access the network?

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

Is Create 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 Create Issue use?

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

How many tokens does Create Issue use?

About 2k tokens (SKILL.md is roughly 8.1k 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 Create Issue?

Skills that share tags, products or a category with Create Issue: Release (signageos/vscode-sops, 122 stars), Publish Extension (FreakStudioCN/mpy-hardware-extension, 118 stars), Cutting A Release (TriliumNext/Trilium, 38k stars) and Verdaccio Pull Request Workflow (verdaccio/verdaccio, 18k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Create Issue?

rajbos (a GitHub user) maintains it in rajbos/ai-engineering-fluency, which has 115 GitHub stars. The repository holds 22 skills in this directory. The repository was last updated on October 6, 2026.

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