junior
Helps agents write, review, and validate Junior extension files including skills, plugins, and manifests.
Identity proven by GitHub's verified organisation badge (getsentry)
- Agents
- Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode, claude.ai and API
- License
- Apache-2.0 (permissive)
- Pin
- 1745a29pinned Oct 9, 2026
- Context cost
- about 920 tokenswhen the skill loads
- GitHub stars
- 367on getsentry/junior
- Scripts
- None found
What it does
“Build, review, or update Junior extension skills and plugins. Use when users ask to create a Junior SKILL.md, app skill, plugin, plugin.yaml, packaged plugin, MCP-backed plugin, OAuth or credentialed plugin, or to validate Junior extension files. Do not use for ordinary Junior usage, provider workflows, generic code editing, or non-Junior agent-skill authoring.”
Generated summary from the skill's own text
Helps agents write, review, and validate Junior extension files including skills, plugins, and manifests. Uses reference guides for skill authoring, plugin configuration, packaging, credentials, and troubleshooting to ensure files meet Junior's structural and runtime requirements.
When to use it
- Creating or updating SKILL.md files for Junior extensions
- Writing or reviewing plugin.yaml manifests and configuration
- Packaging reusable plugins for npm or monorepo distribution
- Validating Junior extension files and diagnosing validation failures
When not to
- General Junior usage or provider workflows unrelated to extension authoring
- Generic code editing tasks outside Junior extension context
- Creating skills for non-Junior agent platforms
Install
These commands install from the publisher's repository and need no account.
skills CLI
npx skills add getsentry/junior --skill juniorInstalls from the repository's default branch, which may have changed since the commit we checked.
GitHub CLI 2.90 or later
gh skill install getsentry/junior junior@1745a298365f0f001db0b3eec6de8a8347e0f6d9Installs the commit we checked (1745a29).
Copy by hand
Download the folder at 1745a29 and put it in .claude/skills/junior for Claude Code and in .agents/skills/junior for Codex, Cursor, Gemini CLI, GitHub Copilot and OpenCode.
Claude Code plugin
/plugin install sentry@claude-plugins-officialThe publisher's plugin in Claude's official marketplace. It may hold more than this skill, and we have not pinned it.
Claude Code plugin
/plugin install sentry-cli@claude-plugins-officialThe publisher's plugin in Claude's official marketplace. It may hold more than this skill, and we have not pinned it.
Copy for your agent
A prompt for any coding agent. It installs this skill from GitHub at the pinned commit, copies the files as they are, and runs nothing unless you ask.
Prompt
Install the agent skill "junior" by Sentry. Source, pinned to commit 1745a298365f0f001db0b3eec6de8a8347e0f6d9: https://github.com/getsentry/junior/tree/1745a298365f0f001db0b3eec6de8a8347e0f6d9/skills/junior 1. Download that folder at exactly this commit. Do not use the default branch. 2. Copy every file unchanged, keeping the folder structure, into .claude/skills/junior/ for Claude Code and .agents/skills/junior/ for Codex, Cursor, Gemini CLI, GitHub Copilot and OpenCode. Create the folders if they do not exist. 3. Do not edit the files, and do not run any script in the folder unless I ask you to. 4. When you are done, list the files you copied and where you put them. Listing and checks: https://www.agentnative.dev/skills/sentry/junior
SKILL.md at the pin
--- name: junior description: Build, review, or update Junior extension skills and plugins. Use when users ask to create a Junior SKILL.md, app skill, plugin, plugin.yaml, packaged plugin, MCP-backed plugin, OAuth or credentialed plugin, or to validate Junior extension files. Do not use for ordinary Junior usage, provider workflows, generic code editing, or non-Junior agent-skill authoring. --- # Junior Create or repair Junior extension files. ## References | Need | Read | | ------------------------------------------------------------------------ | -------------------------------------------------------------------------------------------- | | Choose app skill, app plugin, packaged plugin, or repo-local location | [references/placement-and-discovery.md](references/placement-and-discovery.md) | | Write or review a `SKILL.md` file | [references/skill-authoring.md](references/skill-authoring.md) | | Write or review `plugin.yaml` | [references/plugin-manifest.md](references/plugin-manifest.md) | | Decide where credentials, MCP, packages, OAuth, config, and setup belong | [references/runtime-authority.md](references/runtime-authority.md) | | Package a reusable plugin for npm or this monorepo | [references/packaging.md](references/packaging.md) | | Validate files or diagnose check failures | [references/validation-and-troubleshooting.md](references/validation-and-troubleshooting.md) | | Need concrete templates, robust variants, or anti-pattern corrections | [references/examples.md](references/examples.md) | Maintenance: [SPEC.md](SPEC.md). Provenance: [SOURCES.md](SOURCES.md). ## Workflow 1. Classify: - App-local skill: behavior only, no provider-specific runtime authority. - App-local plugin: provider or workflow bundle for one app. - Packaged plugin: reusable plugin shipped as an npm package. - Monorepo package: new or changed package under `packages/`. 2. Inspect: - Inspect nearby `SKILL.md` files, `plugin.yaml` manifests, app docs, and package metadata. - In this repo, treat `packages/junior-plugin-api/README.md`, `packages/junior/src/chat/plugins/README.md`, exported types, and validators as authoritative. - Preserve: placement, manifest authority, credential secrecy, validation, discovery. 3. Choose shape: - Skill only when no provider runtime setup is needed. - Plugin when config, credentials, OAuth, MCP, packages, postinstall, or reuse is needed. - References only for optional depth. 4. Author: - Put skill behavior in `SKILL.md`. - Put runtime authority in `plugin.yaml`. - Put reusable package metadata in `package.json`. - Keep secrets out of all committed files. 5. Validate: - Run the narrowest structural check first. - Fix every validation error before claiming the extension is complete. - For runtime dependencies, verify snapshot creation or one real workflow when available. ## Hard rules - Skill frontmatter owns activation only; plugin manifests own provider authority. - Do not use `requires-capabilities` or `uses-config` in skills. - Do not hardcode harness dispatcher mechanics in skill prose. - Do not print, persist, or ask users to paste secrets into skill files. - Do not create top-level `skills/` or `plugins/` in a Junior app unless local tooling explicitly requires that legacy layout. - Do not invent manifest fields. If the parser does not support a field, omit it or change the runtime first. ## Reporting 1. Files created or changed. 2. Placement and discovery path. 3. Validation commands and result. 4. Remaining runtime verification: OAuth, MCP, credentials, snapshots, Slack.
From getsentry/junior at 1745a29, shown as plain text under its license: Apache-2.0 (permissive). The license text is in LICENSE.
View SKILL.md on GitHub at 1745a29Files
- SKILL.md4.1 KB · c8bbbd6e5d3b
- SOURCES.md3.1 KB · 288224f5c879
- SPEC.md2.4 KB · b60fa64b164a
- references/
- examples.md3.8 KB · 60a74b4eeb85
- packaging.md3.3 KB · d3accff4f300
- placement-and-discovery.md4.0 KB · 4aaf37e51cc4
- plugin-manifest.md7.5 KB · 4f8ed6cc2343
- runtime-authority.md3.0 KB · 7bf27c486ba6
- skill-authoring.md3.5 KB · db6a5f9ca335
- validation-and-troubleshooting.md8.2 KB · 5cfcedbcc907
10 files, 43 KB in total. Each file has a sha256 in the pin's manifest; the first 12 characters are shown.
Skill folder on GitHub at 1745a29More from Sentry
claude-settings-audit
This skill analyzes a repository to detect its tech stack, build tools, and service integrations, then generates recommended Claude Code settings.json…
Claude Code · about 2.9K tokens · pinned 6 days ago
commit
This skill enables the agent to create conventional commit messages following Sentry's style guide.
Claude Code, Codex, Cursor +4 · about 430 tokens · pinned 6 days ago
django-access-review
This skill guides agents through investigating Django and Django REST Framework code for IDOR and access control vulnerabilities.
Claude Code, Codex, Cursor +4 · about 2.5K tokens · pinned 6 days ago
django-perf-review
This skill audits Django codebases for performance problems by validating issues through code tracing before reporting.
Claude Code, Codex, Cursor +4 · about 2.8K tokens · pinned 6 days ago
iterate-pr
This skill automates PR iteration by fetching CI check statuses and review feedback, then fixing actionable failures and high/medium priority comments until…
Contains scripts
Claude Code · about 1.2K tokens · pinned 6 days ago
pr-writer
This skill helps agents write clear, reviewer-focused PR titles and descriptions by inspecting the branch, diff, and existing PR state, then crafting concise…
Claude Code, Codex, Cursor +4 · about 1.3K tokens · pinned 6 days ago
Related in AI and agents
-21risk-automation
This skill automates 21risk operations by connecting to the 21risk toolkit through Composio's Rube MCP server.
by ComposioOfficial publisher
Claude Code, Codex, Cursor +3 · about 690 tokens · pinned 6 days ago
-2chat-automation
This skill automates 2chat tasks by integrating with Composio's 2chat toolkit through Rube MCP.
by ComposioOfficial publisher
Agents not labelled yet · about 680 tokens · pinned 6 days ago
ably-automation
This skill automates Ably messaging platform tasks by connecting to Composio's Ably toolkit through Rube MCP.
by ComposioOfficial publisher
Agents not labelled yet · about 680 tokens · pinned 6 days ago
abstract-automation
This skill enables agents to automate Abstract design platform operations through Composio's Abstract toolkit via Rube MCP.
by ComposioOfficial publisher
Claude Code, Codex, Cursor +3 · about 690 tokens · pinned 6 days ago
abuselpdb-automation
This skill automates Abuselpdb operations through Composio's toolkit via Rube MCP, enabling the agent to search for IP/domain abuse reports and manage threat…
by ComposioOfficial publisher
Agents not labelled yet · about 700 tokens · pinned 6 days ago
abyssale-automation
This skill enables agents to automate Abyssale tasks through Composio's toolkit via Rube MCP.
by ComposioOfficial publisher
Claude Code, Codex, Cursor +3 · about 690 tokens · pinned 6 days ago