Devops Pipeline
luongnv89/skills
Configure pre-commit hooks and lean GitHub Actions for shift-left quality assurance.
Triage open GitHub issues for kubernetes-sigs/agent-sandbox by mapping them to roadmap.md and assigning k8s priority labels + Kanban Priority (P0–P4) on Project
Install Triage Issues
$ npx skills add kubernetes-sigs/agent-sandbox --skill triage-issues -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install kubernetes-sigs/agent-sandbox triage-issues --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/kubernetes-sigs/agent-sandbox.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/triage-issues .claude/skills/triage-issues && rm -rf skills-srcUse ~/.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/
Install the "triage-issues" agent skill from https://github.com/kubernetes-sigs/agent-sandbox/tree/main/.agents/skills/triage-issues into .claude/skills/triage-issues/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "triage-issues", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/kubernetes-sigs/agent-sandbox/tree/main/.agents/skills/triage-issuesType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add kubernetes-sigs/agent-sandbox --skill triage-issues -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install kubernetes-sigs/agent-sandbox triage-issues --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/kubernetes-sigs/agent-sandbox.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/triage-issues .agents/skills/triage-issues && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "triage-issues" agent skill from https://github.com/kubernetes-sigs/agent-sandbox/tree/main/.agents/skills/triage-issues into .agents/skills/triage-issues/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "triage-issues", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add kubernetes-sigs/agent-sandbox --skill triage-issues -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install kubernetes-sigs/agent-sandbox triage-issues --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/kubernetes-sigs/agent-sandbox.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/triage-issues .cursor/skills/triage-issues && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "triage-issues" agent skill from https://github.com/kubernetes-sigs/agent-sandbox/tree/main/.agents/skills/triage-issues into .cursor/skills/triage-issues/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "triage-issues", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/kubernetes-sigs/agent-sandbox.git --path .agents/skills/triage-issues--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add kubernetes-sigs/agent-sandbox --skill triage-issues -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install kubernetes-sigs/agent-sandbox triage-issues --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/kubernetes-sigs/agent-sandbox.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/triage-issues .gemini/skills/triage-issues && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "triage-issues" agent skill from https://github.com/kubernetes-sigs/agent-sandbox/tree/main/.agents/skills/triage-issues into .gemini/skills/triage-issues/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "triage-issues", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install kubernetes-sigs/agent-sandbox triage-issuesInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add kubernetes-sigs/agent-sandbox --skill triage-issues -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/kubernetes-sigs/agent-sandbox.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/triage-issues .github/skills/triage-issues && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "triage-issues" agent skill from https://github.com/kubernetes-sigs/agent-sandbox/tree/main/.agents/skills/triage-issues into .github/skills/triage-issues/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "triage-issues", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add kubernetes-sigs/agent-sandbox --skill triage-issues -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install kubernetes-sigs/agent-sandbox triage-issues --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/kubernetes-sigs/agent-sandbox.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/triage-issues .opencode/skills/triage-issues && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "triage-issues" agent skill from https://github.com/kubernetes-sigs/agent-sandbox/tree/main/.agents/skills/triage-issues into .opencode/skills/triage-issues/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "triage-issues", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
triage-issues- GitHub stars
- 4.2k
- Token cost
- ~1.5k tokens
- SKILL.md length
- 725 words
- Files
- 5
- Skills in repo
- 7
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Triage open GitHub issues for kubernetes-sigs/agent-sandbox by mapping them to roadmap.md and assigning k8s priority labels + Kanban Priority (P0–P4) on Project
- Works in 6 steps: Honor existing priority/* labels — do… → Roadmap references — if the issue number… → Bug severity — data-integrity /… → …
- Tasks that involve Container orchestration
- SKILL.md covers Label ↔ Priority mapping (fixed), Key references, Triage heuristics and Procedure, plus 2 more sections
- Runs Python scripts from its folder; calls gh
What it does
Triage Issues is an agent skill from kubernetes-sigs/agent-sandbox, published by the product's own GitHub organization. Triage open GitHub issues for kubernetes-sigs/agent-sandbox by mapping them to roadmap.md and assigning k8s priority labels + Kanban Priority (P0–P4) on Project
Its SKILL.md is about 1.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files (for example `evals/eval_runner.py`, `evals/evals.json` and `evals/files/open_issues.json`).
It sits in DevOps & Cloud, covering Container orchestration, Issue triage and Task management. It works with Kubernetes and GitHub. The repository describes itself as: agent-sandbox enables easy management of isolated, stateful, singleton workloads, ideal for use cases like AI agent runtimes and reinforcement learning (RL). The licence is Apache-2.0.
When your agent uses it
- Tasks that involve Container orchestration
- Tasks that involve Issue triage
- Tasks that involve Task management
Example prompts
- “/triage-issues”
Requirements
- Python 3
Workflow steps
6 steps, taken from the first numbered list in SKILL.md.
- Honor existing priority/* labels — do not downgrade/overwrite an existing priority label unless the issue clearly changed; note any you…
- Roadmap references — if the issue number is cited in roadmap.md, inherit that item's status: ⏳ In Progress → P1, 📅 Planned → P2, ✅…
- Bug severity — data-integrity / duplicate-resource / resource-leak bugs in the core controller → P0/P1. Self-labeled "Critical" → P0.
- Value props — latency / performance / scale bottlenecks skew P1 (called out as a primary value proposition).
- Security — critical security vulnerabilities / CVEs → P0 (priority/critical-urgent); routine dependency/patch updates → P1 (tied to…
- Low-signal — empty bodies, one-line questions, "collecting use cases", pinned/frozen community threads, items marked…
What it can do on your machine
Read from SKILL.md and the folder at commit cd0761d. 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
Ships script files (Python), which the agent can run.
Shell commands in SKILL.md call:
gh
From the folder's file list and the shell code blocks in SKILL.md.
Network
Links to these hosts (documentation or services it may open):
github.com
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
Triage Issues loads about 1.5k tokens when it runs. Until then it costs about 44 tokens; SKILL.md has 725 words of instructions outside code blocks.
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 kubernetes-sigs/agent-sandbox at commit cd0761d, republished under its Apache-2.0 licence (© kubernetes-sigs). 725 words, ~1,491 tokens.
Download SKILL.mdSave it as
.claude/skills/triage-issues/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.- name
- triage-issues
- description
- Triage open GitHub issues for kubernetes-sigs/agent-sandbox by mapping them to roadmap.md and assigning k8s priority labels + Kanban Priority (P0–P4) on Project
Triage agent-sandbox issues against the roadmap
Map every open issue in kubernetes-sigs/agent-sandbox to a roadmap theme/item, assign
a triage priority, and sync that priority to both the issue's k8s priority/* label and
the Priority field (P0–P4) on the Kanban board.
Label ↔ Priority mapping (fixed)
| k8s label | Kanban Priority |
|---|---|
priority/critical-urgent | P0 |
priority/important-soon | P1 |
priority/important-longterm | P2 |
priority/backlog | P3 |
priority/awaiting-more-evidence | P4 |
Key references
- Roadmap:
roadmap.mdin the repo root (source of truth for themes + status). - Project board: https://github.com/orgs/kubernetes-sigs/projects/120 (owner
kubernetes-sigs, number120). - The board's
Prioritysingle-select field holds P0–P4.
Triage heuristics
Assign each open issue a tier using, in order:
- Honor existing
priority/*labels — do not downgrade/overwrite an existing priority label unless the issue clearly changed; note any you keep. - Roadmap references — if the issue number is cited in
roadmap.md, inherit that item's status:⏳ In Progress→ P1,📅 Planned→ P2,✅ Completedfollow-ups → P2/P3. - Bug severity — data-integrity / duplicate-resource / resource-leak bugs in the core controller → P0/P1. Self-labeled "Critical" → P0.
- Value props — latency / performance / scale bottlenecks skew P1 (called out as a primary value proposition).
- Security — critical security vulnerabilities / CVEs → P0 (
priority/critical-urgent); routine dependency/patch updates → P1 (tied to "Security Fixes" roadmap item). - Low-signal — empty bodies, one-line questions, "collecting use cases", pinned/frozen community threads, items marked
triage/not-reproducible/triage/needs-information→ P4. Nice-to-have features, refactors, cleanups, test scaffolding → P3.
Procedure
- Verify access:
gh auth status; confirm repokubernetes-sigs/agent-sandbox. - Read the roadmap: read
roadmap.md; extract themes, item statuses, and any cited issue numbers. - Fetch open issues:
gh issue list --repo kubernetes-sigs/agent-sandbox --state open --limit 500 --json number,title,labels,assignees,createdAt,updatedAt,body,url > open_issues.json - Discover board metadata (IDs change per board, always re-fetch):
- Project + Priority field/options:
gh project field-list 120 --owner kubernetes-sigs --format json→ grab thePriorityfield id and the P0–P4 option ids; project id viagh project view 120 --owner kubernetes-sigs --format json. - Item ids:
gh project item-list 120 --owner kubernetes-sigs --limit 1000 --query "is:open" --format json→ map issue number → project item id. Add any open issue not yet on the board withgh project item-add 120 --owner kubernetes-sigs --url <issue-url> --format json.
- Project + Priority field/options:
- Triage: assign every open issue exactly one tier using the heuristics. Sanity-check that the assigned set equals the open-issue set (no missing, no extras).
- Report first: write a markdown report (
issue-triage-report.md) grouping issues by priority with roadmap mapping + one-line rationale, and a "second look" section for judgment calls (e.g., heuristic conflicts, boundary cases, insufficient info, or ambiguous roadmap items). In an interactive run, stop and wait for the user to review before changing anything on GitHub. In an automated/scheduled run, see below. - Apply (after approval in interactive mode, or filtered by untriaged issues in scheduled mode):
- Label:
gh issue edit <#> --repo kubernetes-sigs/agent-sandbox --add-label "<priority/...>" --remove-label "<priority/...>"(if the tier changed). - Board field:
gh project item-edit --id <itemId> --project-id <projectId> --field-id <fieldId> --single-select-option-id <optionId>. - Drive the apply loop from a small script so all issues are processed in one pass (adding a
sleep 1delay between API calls to respect GitHub's 900 points/min secondary rate limit); collect per-issue ok/err and print a finaltotal / errorssummary.
- Label:
- Confirm: report the final distribution (count per tier) and any errors.
Show full SKILL.md (209 more words)Show less
Scheduled / automated mode
When invoked non-interactively (e.g. via cron), there is no human to approve the report. In that mode:
- Still write
issue-triage-report.mdas an audit artifact. - Only apply changes to issues that currently have NO
priority/*label (new/untriaged issues), so a daily run is incremental and never silently overrides a human's manual prioritization. - For issues that already have a priority label, leave them as-is but list them in the report under "already triaged".
- Post the run summary (counts applied, counts skipped, errors) as the final message.
Notes
- Roadmap priority changes are reconciled only via interactive runs, not scheduled mode. When
roadmap.mdchanges the priority of a theme, an interactive run re-triages every open issue against the current roadmap and surfaces the resulting diffs for a human to approve. Scheduled mode deliberately leaves already-triaged issues untouched (see above), so it never silently re-prioritizes existing issues based on a roadmap edit. To propagate a roadmap change to issues that already have apriority/*label, run the skill interactively and apply the proposed changes. - All
priority/*labels and the P0–P4 options already exist on the repo/board; no need to create them. gh projectGraphQL IDs (project, field, options, items) are not stable across boards — always re-discover them at runtime; never hardcode.
© kubernetes-sigs, 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
SKILL.md and 4 other files in .agents/skills/triage-issues of kubernetes-sigs/agent-sandbox.
- SKILL.md
- evals/eval_runner.py
- evals/evals.json
- evals/files/open_issues.json
- evals/files/roadmap.md
Open the folder on GitHubat commit cd0761d
Compare with similar skills
Triage Issues 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Triage Issues this skillkubernetes-sigs/agent-sandbox | 4.2k | — | ~1.5k | Automated safety check: Pass | Apache-2.0 | |
| Devops Pipelineluongnv89/skills | 131 | — | ~4.8k | Automated safety check: Pass | MIT | |
| Project Referencesaiskillstore/marketplace | 430 | — | ~2.3k | Automated safety check: Notes | None | |
| GitHub Runnermagnus919/agent-skills | 113 | — | ~1.7k | Automated safety check: Pass | MIT | |
| Tgf Server Devthkhxm/tgf | 128 | — | ~1.3k | Automated safety check: Notes | MIT | |
| Ways Of Workingdevantler-tech/ksail | 165 | — | ~2k | Automated safety check: Pass | Apache-2.0 |
Similar skills
Project References
aiskillstore/marketplace
Look up conventions, patterns, and concrete implementations from your own GitHub repositories checked out locally under ~/projects/referenzen/.
GitHub Runner
magnus919/agent-skills
Deploy, manage, and troubleshoot self-hosted GitHub Actions runners.
Tgf Server Dev
thkhxm/tgf
基于 tgf v2（github.com/thkhxm/tgf/v2）用确定性的 tgfctl 工作流创建、验证和维护 Go 游戏服务器项目。
Ways Of Working
devantler-tech/ksail
Codifies devantler-tech engineering practices: agent-first development workflow, TDD, CI/CD pipelines, GitHub Flow, code quality gates, and Kubernetes workflows with ksail.
KubeSphere DevOps Overview
kubesphere/kubesphere
Explains the KubeSphere DevOps extension: Jenkins-based CI/CD, ArgoCD GitOps, how DevOps projects map to namespaces, and project naming rules.
More from kubernetes-sigs/agent-sandbox
- Official
Bump Go Version
kubernetes-sigs/agent-sandbox
Bumps the Go version to the latest release across go.mod, tools.mod, and Dockerfiles.
- Official
Fix Flakes
kubernetes-sigs/agent-sandbox
Diagnose and fix flaky tests tracked as open kind/flake issues in kubernetes-sigs/agent-sandbox — reproduce the flake, apply a minimal fix, and open a PR linking the issue.
- Official
K8s Agent Sandbox MCP
kubernetes-sigs/agent-sandbox
An MCP server skill for managing Kubernetes sandboxes. An agent skill from kubernetes-sigs/agent-sandbox.
- Official
Test Pyramid
kubernetes-sigs/agent-sandbox
Analyze the repo's unit and E2E tests and propose rebalancing toward a test pyramid — which E2E tests (or assertions inside them) can be covered by unit tests, which unit-level gaps genuinely need…
- Official
K8s API Conventions
kubernetes-sigs/agent-sandbox
Guides the agent to follow Kubernetes API conventions for OSS standards.
- Official
Dev Rules
kubernetes-sigs/agent-sandbox
Enforces project-specific development rules and conventions.
Related
Works with
Categories
Questions about Triage Issues
What does Triage Issues do?
Triage open GitHub issues for kubernetes-sigs/agent-sandbox by mapping them to roadmap.md and assigning k8s priority labels + Kanban Priority (P0–P4) on Project. Triage Issues is an agent skill from kubernetes-sigs/agent-sandbox, published by the product's own GitHub organization.
When should I use Triage Issues?
Triage Issues fits situations like: tasks that involve Container orchestration; tasks that involve Issue triage; tasks that involve Task management.
How do I install Triage Issues in Claude Code?
Run `npx skills add kubernetes-sigs/agent-sandbox --skill triage-issues -a claude-code`. Or copy the skill folder (.agents/skills/triage-issues in kubernetes-sigs/agent-sandbox) into .claude/skills/triage-issues in your project. Claude Code loads it when a task matches its description.
How do I install Triage Issues in Codex?
Run `npx skills add kubernetes-sigs/agent-sandbox --skill triage-issues -a codex`. Or copy the skill folder (.agents/skills/triage-issues in kubernetes-sigs/agent-sandbox) into .agents/skills/triage-issues in your project. Codex loads it when a task matches its description.
Can I use Triage Issues 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 kubernetes-sigs/agent-sandbox --skill triage-issues -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/triage-issues, .gemini/skills/triage-issues, .github/skills/triage-issues and .opencode/skills/triage-issues in your project.
What does Triage Issues need to run?
Going by SKILL.md and its folder, Triage Issues needs Python for the scripts in its folder and the command-line tools its instructions call (gh). Our summary lists: Python 3.
Does Triage Issues access the network?
SKILL.md names 1 domain. As links in the text: github.com. This is read from the text; nothing was executed.
Is Triage Issues 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 Triage Issues use?
Triage Issues 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 Triage Issues use?
About 1.5k tokens (SKILL.md is roughly 6k 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 Triage Issues?
Skills that share tags, products or a category with Triage Issues: Devops Pipeline (luongnv89/skills, 131 stars), Project References (aiskillstore/marketplace, 430 stars), GitHub Runner (magnus919/agent-skills, 113 stars) and Tgf Server Dev (thkhxm/tgf, 128 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Triage Issues?
kubernetes-sigs (a GitHub organization, an official publisher) maintains it in kubernetes-sigs/agent-sandbox, which has 4,183 GitHub stars. The repository holds 7 skills in this directory. The repository was last updated on October 8, 2026.
Source: kubernetes-sigs/agent-sandbox on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.