statuslines

Jon Gallant's collection of skills for AI coding agents — works with GitHub Copilot, Claude, Codex, and any agent that supports the SKILL.md format. A general-purpose monorepo: each skill lives in its own folder under skills/ and can be installed individually or all at once.

Skills

Skill	What it does
create-canvas-app	Build GitHub Copilot App canvas extensions fast — a no-build Preact + htm kit with live SSE state, durable storage, Primer theming, official GitHub Lucide icons, deep links into the app, a generator, and an installable skill.
create-gh-pages-site	Scaffold a working GitHub Pages site from a vetted template (static, Astro, React + Vite, Eleventy, Jekyll, or a skills catalog) into your current repo by default — injects the correct base path for the target repo, wires the official GitHub Actions Pages deploy workflow, sets the repo's Website link, and shows how to enable Pages.
create-skill	Create and register a complete portable agent skill with focused instructions, deterministic tests, Vally evals, catalog metadata, and optional validated thumbnail art from a built-in or user-described provider.
create-skills-repo	Create or safely upgrade a cross-agent skills marketplace repository with every supported manifest, Vally, secure CI, Dependabot, a functional starter skill, and an optional GitHub Pages catalog.
repo-ready	Scaffold and maintain the standard community health files every GitHub repository needs (.gitignore, LICENSE, CONTRIBUTING, issue templates, CI workflows, dependabot, and more). Two modes: init (interview + scaffold) and update (scan for gaps).
naming-is-hard	Interactive naming assistant for projects, CLIs, and products. Profiles what you're building, generates diverse candidate names, learns your preferences as you react, and validates finalists against real availability (domains, GitHub, npm/PyPI/crates/RubyGems/NuGet, social handles) plus a trademark and existing-business screen. Every finalist lands a verdict: Deal Breaker, It's Complicated, or Perfect Match.
eli5	Explain the code, error, design, or idea already in context using plain language, a useful analogy, the proper grown-up terms, and an honest note about where the analogy stops working.
dns-doctor	Audit DNS delegation, records, DNSSEC, CAA, web routing, TLS, CDN behavior, mail authentication, takeover exposure, and zone hygiene, then apply exact provider changes only after explicit user approval.
deps-doctor	Audit, update, and secure dependencies across npm, pnpm, Yarn, pip, Poetry, uv, Go, Cargo, Bundler, Composer, NuGet, Maven, Gradle, Swift, pub, and Hex, plus Docker base images, GitHub Actions, Terraform, and dev container features. Ranks vulnerabilities by exploitation evidence, withholds releases too new to have been vetted, fixes breaking changes forward instead of rolling back, and never opens an empty dependency pull request.
git-tidy	Content-aware Git work triage across branches, worktrees, stashes, remote refs, tags, remotes, artifacts, ignored tracking, large blobs, and maintenance. Leads with plain decisions and concrete actions while exact proof stays available on demand; analysis is read-only and every action requires separate approval.

A skill is invoked straight from the Copilot composer — here create-canvas-app turns a one-line prompt into a working canvas:

Copilot CLI Statusline Extensions

This plugin also ships four composable terminal statuslines for GitHub Copilot CLI under extensions/ (exposed to Agent Plugins 1.0 hosts via com.github.copilot/extensions/):

Extension	What it shows
pr-statusline	Open session PRs on GitHub and follow checks, conflicts, approvals, and review threads. Background-agent PRs can appear in the agent summary; confirmed merged pills clear after your next message following detection.
issue-statusline	Separate clickable pill for each GitHub issue the active session is working on: priority or bug labels, linked open PR indicator, assignee handle, comment count, and a purple Closed badge that dismisses on your next prompt.
subagent-statusline	Overall session subagent counts (starting, exploring, in PR, merged, and failed). Settled counts dismiss on the next real user message after detection without hiding ongoing agents. Use /tasks to inspect individual agents.
worktree-statusline	Checkout-grouped rows with full paths, native [⎇ branch*+%] labels, upstream ↑/↓ divergence counts and missing base commits, followed by related PRs and issues. Hides Copilot's own checkout label and empty historical rows; supports detached HEADs and one overall subagent summary.

With Branch and Worktree enabled, each checkout row starts with a blue, non-linked path [⎇ branch*+%] pill, followed by its PRs and linked issues. * means unstaged changes, + staged changes, and % untracked files (not a percentage). For example, origin/feat/login↑1↓2 means one local-only commit and two upstream commits missing locally; origin/main↓3 means three missing base commits. Zero counts are hidden, and target? means a known comparison is unavailable. Counts use locally fetched refs, not a background network fetch. The base is the matched PR's target, otherwise the remote default branch; it is not a guess about where the branch was originally created. Copilot's own checkout label is hidden; one overall subagent summary appears below the checkout rows. See the worktree guide for association and visibility rules. Disabling worktree grouping restores horizontal composition.

Installing statuslines@jongio-skills (statuslines only) or jongio-skills@jongio-skills (all skills and statuslines) from the jongio/skills marketplace auto-registers the statuslines and opens an interactive checkbox picker on first session start (and adds /statusline-setup so you can toggle Pull Requests, GitHub Issues, Subagents, and Branch and Worktree anytime), or you can run the standalone setup script:

# Install just the statuslines (no skills) in Copilot CLI:
/plugin marketplace add jongio/skills
/plugin install statuslines@jongio-skills

# Windows (PowerShell one-liner)
irm https://raw.githubusercontent.com/jongio/skills/main/install-statusline.ps1 | iex

# macOS & Linux (Bash one-liner)
curl -fsSL https://raw.githubusercontent.com/jongio/skills/main/install-statusline.sh | bash

Install

Option 1: Copilot Plugin Marketplace (Recommended)

jongio/skills plugs directly into the GitHub Copilot plugin system (works in both the Copilot app and the Copilot CLI). The repo ships a root marketplace.json and plugin.json so you can install the complete collection (all skills and statuslines) or pick individual skills:

# 1. Register the marketplace once inside Copilot CLI:
/plugin marketplace add jongio/skills

# 2a. Install the entire collection (all skills + CLI statuslines):
/plugin install jongio-skills@jongio-skills

# 2b. Or install just the CLI statuslines (no skills):
/plugin install statuslines@jongio-skills

# 2c. Or install just one skill from the marketplace:
/plugin install create-canvas-app@jongio-skills

Or from your terminal shell:

copilot plugin marketplace add jongio/skills
copilot plugin marketplace browse jongio-skills
copilot plugin install jongio-skills@jongio-skills
# or just the CLI statuslines (no skills):
copilot plugin install statuslines@jongio-skills
# or a single skill:
copilot plugin install create-canvas-app@jongio-skills

In the Copilot app (no commands needed):

1. Open Settings and select Plugins.

   

2. Click Install ▾ → Add marketplace, enter jongio/skills, and click Add marketplace.

   

3. The marketplace's skills appear grouped under jongio-skills — click Install on the one you want (or jongio-skills for the complete collection).

   

4. The skill installs and is enabled, ready to use right away.

   

Option 2: Skills CLI (npx skills)

For hosts that use the standalone vercel-labs/skills CLI (skills.sh):

# List the skills available in this repo:
npx skills add jongio/skills --list

# Install one skill globally for GitHub Copilot:
npx skills add jongio/skills --skill create-canvas-app -g --agent github-copilot

# Install into the current project instead of globally (drop -g):
npx skills add jongio/skills --skill create-canvas-app

# Install every skill in the repo:
npx skills add jongio/skills --all

After any install, reload skills with /skills reload or start a new session. Each skill is then available as /<skill-name> (e.g. /create-canvas-app).

App and editor support

The repository keeps every skill under skills/ and wraps that canonical directory with the native manifests required by each supported host. No skill content is copied between formats.

Surface	Support	Install or discovery path
GitHub Copilot app	Marketplace and individual or complete plugin install	Open Customize, select Plugins, add jongio/skills, then install one skill or jongio-skills.
GitHub Copilot in Visual Studio Code	Agent Plugins 1.0 and marketplace install	Enable chat.plugins.enabled, run Chat: Install Plugin From Source, and enter https://github.com/jongio/skills.
GitHub Copilot CLI	Marketplace and direct plugin install	Run copilot plugin marketplace add jongio/skills or copilot plugin install jongio/skills.
Copilot coding agent and code review	Agent Skills in the target repository	Install selected skills into the target repository with npx skills add jongio/skills.
ChatGPT desktop and Codex CLI	Codex marketplace and skills-only plugin	Add jongio/skills as a marketplace. If using sparse paths, include .agents/plugins, .codex-plugin, and skills.
ChatGPT web and mobile	Public directory plugins only	A Git marketplace cannot enable these surfaces. Public availability requires review through the OpenAI plugin submission portal.
Codex IDE extension	Standalone Agent Skills only	The IDE extension does not support plugins. Install selected skills with npx skills add jongio/skills --agent codex.
Claude Code, including its Visual Studio Code and JetBrains integrations	Claude marketplace plugin	Run /plugin marketplace add jongio/skills, then /plugin install jongio-skills@jongio-skills.
Cursor	Agent Plugins 1.0 and Cursor marketplace	Install https://github.com/jongio/skills from Customize, or import the repository as a marketplace.
Gemini CLI and its editor companion	Gemini extension	Run gemini extensions install https://github.com/jongio/skills. Gemini Code Assist is a separate product and does not load Gemini CLI extensions.
Goose Desktop, Windsurf, Cline, Roo Code, and OpenCode	Native Agent Skills	Install selected skills with npx skills add jongio/skills; the installer places them in each host's supported skills directory.

The root plugin.json follows Agent Plugins 1.0, which is shared by GitHub Copilot in Visual Studio Code, Cursor, Codex, and other compatible hosts. Vendor-specific manifests exist only where a host requires a different discovery path:

plugin.json                         Agent Plugins 1.0 package
marketplace.json                    GitHub Copilot marketplace
.agents/plugins/marketplace.json    Codex and ChatGPT desktop marketplace
.codex-plugin/plugin.json           Codex plugin compatibility manifest
.claude-plugin/marketplace.json     Claude Code marketplace
.claude-plugin/plugin.json          Claude Code plugin
.cursor-plugin/marketplace.json     Cursor marketplace
gemini-extension.json               Gemini CLI extension
skills/                             Canonical Agent Skills

Dependency maintenance

Active development tooling uses Vally 0.18.0, pinned in the shared CI tools and each skill's manifest and lockfile. The active create-skill generator uses the same pin. The create-skills-repo bundled authoring snapshot and its shared Vally tooling also use 0.18.0 to preserve byte-for-byte authoring parity and generated-skill compatibility. Intentional evaluation fixtures and unrelated template dependencies retain their independent version snapshots.

Each independent npm root enforces min-release-age=7 in its .npmrc; Dependabot's npm entries use a seven-day cooldown. Use a supported npm release that implements this setting. The Vally 0.18.0 migration was explicitly approved as a one-time exception; no permanent release-age exclusions are configured.

Vally 0.18's preferred agent_environment key replaces the deprecated environment alias in active eval specs. Fixture staging, scoring thresholds, and CI's trial-level safety guards remain unchanged.

The site temporarily pins three compatible transitive security fixes through scoped overrides: astro's http-cache-semantics 4.3.0 (GHSA-ch52-4w7c-c8xp) and sharp 0.35.5 (GHSA-wq5f-xc86-pv6w), and unifont's undici 8.10.2 (GHSA-w293-vg96-wgc3 and the related undici advisories). Remove each override when a parent upgrade's resolved graph supplies a compatible patched version, then regenerate and audit the lockfile. These overrides do not authorize unrelated bot-owned updates.

Layout

marketplace.json              GitHub Copilot marketplace
plugin.json                   Agent Plugins 1.0 package manifest
.agents/plugins/              Codex and ChatGPT desktop marketplace
.codex-plugin/                Codex compatibility manifest
.claude-plugin/               Claude Code plugin and marketplace
.cursor-plugin/               Cursor marketplace
gemini-extension.json         Gemini CLI extension
test/                         Cross-harness distribution parity tests
skills/
  create-canvas-app/          One self-contained skill
    SKILL.md                  Authoring contract the agent reads
    README.md                 Human docs for the skill
    references/               Lookup detail SKILL.md links to, to stay under 500 lines
    evals/                    Vally eval spec plus its fixtures
    test/                     Deterministic tests, run in CI for every skill
    kit/  scripts/  docs/     Skill-specific assets
docs/                         Specs, test plans, thumbnail prompts
site/                         Astro catalog published to GitHub Pages
.github/workflows/            skill-lint (every push), skill-eval (agent evals)

Adding a skill

A skill is more than its folder: CI enforces that every skill is registered everywhere the catalog advertises it. The root distribution test covers every skill and host manifest. Skills with additional registration contracts enforce them in local tests. On pull requests, skill-lint.yml runs Vally lint, strict eval-spec lint, and deterministic tests for affected skills. Pushes to the default branch cover every skill. The workflow always builds the catalog site.

1. skills/<name>/ with SKILL.md (500-line ceiling; overflow goes to references/), README.md, package.json, test/, and evals/<name>/eval.yaml. Use /create-skill <name> to create and register this complete shape.
2. The skill table in this README.
3. marketplace.json and the keywords array in plugin.json.
4. site/src/content/skills/<name>.md, with thumb: pointing at images/thumb-<name>.png.
5. The all= matrix in .github/workflows/skill-eval.yml.
6. A tracked thumbnail at skills/<name>/thumbnail.png, generated from a prompt recorded in docs/thumbnail-prompts.md and listed in site/public/images/IMAGES.md. The site validates catalog mappings and generates ignored public copies before development and production builds.

Copy the newest skill rather than the oldest; it reflects the current conventions.

Investigating nightly eval failures

Skill Eval remains limited to trusted scheduled and manual runs; pull requests run model-free lint and deterministic tests. Model-backed runs use the owner's Copilot allowance and require an approved scope before dispatch.

For a bounded manual investigation, select explicit skill ids or paths separated by commas and a Vally filter_tag. The neutral ci=targeted tag selects the six current regression scenarios rather than their complete suites:

gh workflow run skill-eval.yml --repo jongio/skills --ref <reviewed-ref> \
  -f skill=create-skill,dns-doctor,create-gh-pages-site \
  -f filter_tag=ci=targeted -f verbose=true

Runs retain five trials per stimulus, two workers and zero retries. verbose defaults off and requires an explicitly filtered skill selection; opt in only for reviewed, non-sensitive fixtures because agent answers appear in the job log. No transcripts or environment-bearing artifacts are uploaded.

Every run prints normalized summary and failed-grader diagnostics, even when the eval command fails. The pass gate still rejects execution errors and any failed skill-invocation, diff-empty or tool-calls check; a high average prompt score does not waive those checks.

License

MIT — see LICENSE.