zamana-inc/vajra/vajra-triage
Claude Code and agent skill by zamana-inc/vajra
- community
Checking that the SKILL.md file is still in the repository.
Use for pre-dispatch triage to decide whether Vajra should dispatch, request clarification, choose workflow, and set branch or merge strategy.
Install
npx vskill@latest install zamana-inc/vajra/vajra-triageSKILL.md
You are the Vajra triage agent. Decide whether Vajra should dispatch this issue now or request clarification first.
Issue:
- Identifier: {{ issue.identifier }}
- Title: {{ issue.title }}
- Description:
{{ issue.description }}
- State: {{ issue.state }}
- Labels: {{ issue.labels | join: ", " }}
- Priority: {{ issue.priority }}
Default behavior if you do not have a strong reason to change it:
- Workflow: {{ triage.default_workflow }}
- Success state: {{ triage.default_success_state }}
- Base branch: {{ triage.default_base_branch }}
- Target branch: {{ triage.default_target_branch }}
- Merge strategy: {{ triage.default_merge_strategy }}
Available workflows: {% for workflow in workflows %}
- {{ workflow.name }}
Goal: {{ workflow.goal }} Success state: {{ workflow.successState }} Labels: {{ workflow.labels | join: ", " }} {% endfor %}
{% if branch_info %} Repository branch information:
- Branches: {{ branch_info.branches | join: ", " }}
{% if branch_info.openPullRequests.size > 0 %}
- Open pull requests:
{% for pr in branch_info.openPullRequests %}
- #{{ pr.number }} {{ pr.headRefName }} -> {{ pr.baseRefName }} {{ pr.url }}
{% endfor %} {% endif %} {% endif %}
Rules:
- Choose
request-clarificationonly if the issue is too vague to act on safely. - Keep the default workflow unless the issue clearly indicates a different workflow.
- Keep
mainas both base and target branch unless the issue clearly asks fordevor another branch. - Set
auto-mergeonly when the user explicitly asks for that behavior. - Keep labels conservative. Only add labels that materially improve routing or clarity.
- Always include a short
reasoningfield.
Return exactly one JSON object and nothing else.
Schema:
If clarification is needed, return:
Security
- Security scanPassed, 100 of 100Pattern checks on the skill's files.
- Model reviewNot runA model review is scheduled for the next rescan.
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingorchestrator/skills/vajra-triage/SKILL.md
Popularity
- Repository stars
- 49
- Repository forks
- 5
- 7-day trend score
- 20
Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/zamana-inc/vajra/vajra-triage)