delivery-agent
Delivery integration agent for code commit, branch creation, PR/MR generation, and automated delivery workflow.
Skill by Celia-veey
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/celia-veey-delivery-agent
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: productivity, agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/delivery-agent
What's inside
- Skill name
delivery-agent- Description
- Delivery integration agent for code commit, branch creation, PR/MR generation, and automated delivery workflow. TRIGGER when: code review passed, ready for integration and deployment. DO NOT TRIGGER when: code review not completed or tests failing.
- License
- MIT
- Metadata
- version: 1.0.0 · category: devops
- Instructions
- 286 lines in SKILL.md · view on GitHub
Agent Skills spec issues
- name: "delivery-agent" does not match folder "Delivery"
- files: referenced but missing: references/release-checklist.md, references/environment-management.md
Files (1)
- SKILL.md
SKILL.md (first lines)
# Delivery Agent ## Role You are a DevOps engineer responsible for automating code integration into the codebase after review approval, generating standardized PR/MR. ## Usage Scenarios 1. Receive approved code change set after review 2. Automatically create feature branch 3. Commit code changes 4. Generate standardized PR/MR description 5. Call Git API to create PR/MR ## Mandatory Workflow ### Step 1: Pre-Delivery Validation Run the pre-delivery validation checklists below (build, test, code quality, documentation). ### Step 2: Git Operations (via GitHub_PR_Delivery skill) Invoke the `GitHub_PR_Delivery` skill from `.trae/skills` to handle all Git operations. The skill provides: 1. **Task Branch Discovery**: Check if a relevant branch already exists for the current task. 2. **Branch Management**: Ensure NOT working on `main`. Create descriptive branch if needed. 3. **Commit Changes**: Verify all changes are committed with descriptive messages. 4. **Locate Template**: Find and read the PR template. 5. **Draft Description**: Create PR description following the template. 6. **Preflight Check**: Run `npm run preflight` before creating PR. 7. **Push Branch**: Push the branch to remote (NEVER push to main). 8. **PR Idempotency Check**: Check if PR already exists; update instead of creating duplicate. 9. **Create PR**: Use `gh pr create` with the drafted description. **Safety Rails from the skill:** - NEVER push to `main` — this is the highest priority - Never ignore the PR template - Don't check boxes for tasks not done ### Step 3: Output Delivery Result After the PR is created, output the result in Markdown format. ## Pre-Delivery Validation Checklist ### Build Validation ```bash # Backend build check cd server && npm run build # Frontend build check cd client && npm run build # Ensure no compilation errors ``` **Checklist:** - [ ] Backend compiles without errors - [ ] Frontend compiles without errors - [ ] TypeScript type checks pass - [ ] Lint checks pass (no warnings/errors) - [ ] All dependencies installed and version compatible ### Test Validation ```bash # Run test suite npm test # Generate coverage report npm run test:coverage ``` **Checklist:** - [ ] All unit tests pass (coverage ≥80%) - [ ] All integration tests pass - [ ] All E2E tests pass (critical paths) - [ ] No failed or skipped tests - [ ] Coverage report generated ### Code Quality Validation **Checklist:** - [ ] Code review passed (overall score ≥7/10) - [ ] No critical security issues - [ ] No major architectural violations - [ ] All review suggestions addressed or deferred with reason ### Documentation Validation **Checklist:** - [ ] API documentation updated (OpenAPI/Swagger) - [ ] README updated (if new dependencies or config changes) - [ ] .env.example updated (if new environment variables) - [ ] Database migration documentation updated - [ ] CHANGELOG updated See [release-checklist.md](references/release-checklist.md) for complete release criteria. ## Production Hardening Checklist ### Security Hardening ``` ✅ All secrets configured via environment variables (not hardcoded) ✅ .env files in .gitignore ✅ CORS explicitly specifies allowed origins (not *) ✅ Rate limiting configured ✅ Security headers set (helmet or equivalent) ✅ Input validation enabled on all endpoints ✅ Error responses do not expose stack traces ✅ Sensitive data not logged ``` ### Performance Hardening ``` ✅ Database connection pool configured ✅ N+1 query issues resolved ✅ Large list queries paginated ✅ Caching strategy implemented (if applicable) ✅ Static assets optimized (compression, cache headers) ✅ Database indexes created (frequently queried fields) ``` ### Observability Hardening ``` ✅ Structured JSON logging configured ✅ Request ID propagation implemented
From Celia-veey/orchestration-engine, MIT.
More from Celia-veey/orchestration-engine
- 0.520score
pm-agent
Celia-veey
Product Manager agent for requirement clarification, multi-round questioning, solution design, and structured PRD output.
SkillBFreshness: BClaude Code +9 - 0.520score
architect-agent
Celia-veey
Architect agent for technical solution design, architecture analysis, and executable implementation plans.
SkillBFreshness: BClaude Code +9 - 0.520score
architect-api-designer
Celia-veey
API design specialist architect.
SkillBFreshness: BClaude Code +9 - 0.520score
architect-auth-specialist
Celia-veey
Authentication and authorization specialist architect.
SkillBFreshness: BClaude Code +9 - 0.520score
architect-db-architect
Celia-veey
Database architecture specialist specialist.
SkillBFreshness: BClaude Code +9 - 0.520score
coder-agent
Celia-veey
Full-stack developer agent for writing executable code and test cases based on product solutions.
SkillBFreshness: BClaude Code +9 - 0.520score
coder-backend
Celia-veey
Backend developer specialist.
SkillBFreshness: BClaude Code +9 - 0.520score
coder-database
Celia-veey
Database developer specialist.
SkillBFreshness: BClaude Code +9 - 0.520score
coder-frontend
Celia-veey
Frontend developer specialist.
SkillBFreshness: BClaude Code +9 - 0.520score
debugger-agent
Celia-veey
Debugging wizard agent for systematic error investigation, root cause analysis, and bug resolution.
SkillBFreshness: BClaude Code +9 - 0.520score
documenter-agent
Celia-veey
Documentation agent for generating docstrings, API specs, user guides, and documentation reports.
SkillBFreshness: BClaude Code +9 - 0.516score
reviewer-agent
Celia-veey
Code review agent for quality assessment, security scanning, standards compliance, and professional review reports.
SkillBFreshness: BClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Aug 16, 2026 (2 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- Version
- 1.0.0
- License
- MIT
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from Celia-veey
- 0.520score
architect-agent
Celia-veey
Architect agent for technical solution design, architecture analysis, and executable implementation plans.
SkillBFreshness: BClaude Code +9 - 0.520score
architect-api-designer
Celia-veey
API design specialist architect.
SkillBFreshness: BClaude Code +9 - 0.520score
architect-auth-specialist
Celia-veey
Authentication and authorization specialist architect.
SkillBFreshness: BClaude Code +9 - 0.520score
architect-db-architect
Celia-veey
Database architecture specialist specialist.
SkillBFreshness: BClaude Code +9 - 0.520score
coder-agent
Celia-veey
Full-stack developer agent for writing executable code and test cases based on product solutions.
SkillBFreshness: BClaude Code +9 - 0.520score
coder-backend
Celia-veey
Backend developer specialist.
SkillBFreshness: BClaude Code +9
Cite this page
delivery-agent skill. Agent Mart. https://agentmart.dev/skills/celia-veey-delivery-agent (last updated 2026-10-24)