Orchestrate agile development workflows for Gitea repositories using the tea CLI. Use when working with Gitea-hosted repos and asking to 'run the workflow', 'continue working', 'what's next', 'complete the task cycle', 'start my day', 'end the sprint', 'implement the next task', or wanting guided step-by-step development assistance. Keywords: workflow, orchestrate, agile, task cycle, sprint, daily, implement, review, PR, standup, retrospective, gitea, tea.
npx skills add https://github.com/jwynia/agent-skills --skill gitea-workflow
A skill that guides agents through structured agile development workflows for Gitea repositories by intelligently invoking commands in sequence. Uses checkpoint-based flow control to auto-progress between steps while pausing at key decision points.
Use this skill when:
Do NOT use this skill when:
/status directly)/review-code directly)Before using this skill:
tea login)context-network/backlog/context-network/backlog/by-status/*.mdWORKFLOW TYPES
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
TASK CYCLE (Primary) DAILY SPRINT
────────────────────── ────────────────── ──────────────────
sync Morning: Start:
↓ sync --last 1d sync --all
next → [CHECKPOINT] status --brief groom --all
↓ groom --ready plan sprint-goals
implement status
↓ Evening:
[CHECKPOINT] checklist End:
↓ discovery sync --sprint
review-code sync --last 1d retrospective
review-tests audit --sprint
↓ maintenance --deep
[CHECKPOINT]
↓
apply-recommendations (if issues)
↓
pr-prep → [CHECKPOINT]
↓
pr-complete
↓
update-backlog & status
↓
END
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
The skill determines current workflow state automatically. No manual tracking needed.
| Signal | How to Check | Indicates |
|--------|--------------|-----------|
| Worktree exists | git worktree list | Task in progress |
| Task branch active | git branch --show-current matches task/* | Active implementation |
| Uncommitted changes | git status --porcelain | Active coding |
| PR exists | tea pulls list --state open | In review |
| PR merged | tea pulls + check state | Ready for cleanup |
STATE DETECTION LOGIC
─────────────────────────────────────────────────────────────
Check → State → Next Step
─────────────────────────────────────────────────────────────
No worktree, no in-progress → IDLE → sync, next
Worktree exists, uncommitted → IMPLEMENTING → continue implement
Worktree exists, all committed → READY_REVIEW → review-code
PR open, CI pending → AWAITING_CI → wait or address
PR open, CI pass → READY_MERGE → pr-complete
PR merged, worktree exists → CLEANUP → pr-complete
─────────────────────────────────────────────────────────────
For detailed detection algorithms, see references/state-detection.md.
# Auto-detect state and continue from where you are
/gitea-workflow
# Start specific workflow phase
/gitea-workflow --phase task-cycle
/gitea-workflow --phase daily-morning
/gitea-workflow --phase daily-evening
/gitea-workflow --phase sprint-start
/gitea-workflow --phase sprint-end
# Resume work on specific task
/gitea-workflow --task TASK-123
# Preview what would happen without executing
/gitea-workflow --dry-run
The primary workflow for completing a single task from selection to merge.
Ensure context network matches actual project state.
Run: sync --last 1d --dry-run
Purpose: Detect drift between documented and actual state
Output: Sync report showing completions, partial work, divergences
Identify the next task to work on.
Run: next
Purpose: Find highest priority ready task
Output: Task ID, title, branch name suggestion
CHECKPOINT: TASK_SELECTED
Test-driven development in isolated worktree.
Run: implement [TASK-ID]
Purpose: Create worktree, write tests first, implement, verify
Output: Working implementation with passing tests
CHECKPOINT: IMPL_COMPLETE
Quality validation of implementation.
Run: review-code --uncommitted
Run: review-tests --uncommitted
Purpose: Identify quality issues, security concerns, test gaps
Output: Review reports with issues and recommendations
CHECKPOINT: REVIEWS_DONE
Address review findings intelligently.
Run: apply-recommendations [review-output]
Purpose: Apply quick fixes now, defer complex changes to tasks
Output: Applied fixes + created follow-up tasks
Create pull request with full documentation.
Run: pr-prep
Purpose: Validate, document, and create PR
Output: PR created with description, tests verified
CHECKPOINT: PR_CREATED
Merge and cleanup.
Run: pr-complete [PR-NUMBER]
Purpose: Merge PR, delete branch, remove worktree, update status
Output: Task marked complete, cleanup done
Persist progress to source-of-truth documentation.
Run: Part of pr-complete (Phase 6)
Purpose: Update epic file (task → complete), unblock dependents, update project status
Output: Backlog and project status reflect actual progress
Why this step matters: Without it, completed tasks remain marked "ready" in backlog files and project status stays stale. Internal tracking files are session-scoped; the backlog and status files are the persistent source of truth.
For detailed task-cycle instructions, see references/phases/task-cycle.md.
Quick sequences for start and end of workday.
Run sequence:
1. sync --last 1d --dry-run # What actually happened yesterday
2. status --brief --sprint # Current sprint health
3. groom --ready-only # What's ready to work on
Output: Clear picture of today's priorities
Run sequence:
1. checklist # Ensure nothing lost
2. discovery # Capture learnings
3. sync --last 1d # Update task statuses
Output: Knowledge preserved, state synchronized
For detailed daily instructions, see references/phases/daily.md.
Ceremonies for sprint boundaries.
Run sequence:
1. sync --all # Full reality alignment
2. groom --all # Comprehensive grooming
3. plan sprint-goals # Architecture and goals
4. status --detailed # Baseline metrics
Output: Sprint plan with groomed, ready backlog
Run sequence:
1. sync --sprint # Final sprint sync
2. retrospective # Capture learnings
3. audit --scope sprint # Quality review
4. status --metrics # Sprint metrics
5. maintenance --deep # Context network cleanup
Output: Sprint closed, learnings captured, ready for next
For detailed sprint instructions, see references/phases/sprint.md.
Checkpoints are pauses for human decision-making.
At each checkpoint:
| Response | Action |
|----------|--------|
| "continue" / "proceed" / "yes" | Move to next step |
| "stop" / "pause" | Save state, exit workflow |
| "back" | Re-run previous step |
| "skip" | Skip current step (use cautiously) |
| Custom input | May adjust next step parameters |
Some checkpoints can auto-continue when conditions are met:
| Checkpoint | Auto-Continue If |
|------------|------------------|
| IMPL_COMPLETE | All tests pass, build succeeds |
| REVIEWS_DONE | No critical or high severity issues |
| PR_CREATED | CI passes (verified via API), required approvals obtained |
For detailed checkpoint handling, see references/checkpoint-handling.md.
Each workflow step uses embedded command instructions:
| Command | Reference | Purpose |
|---------|-----------|---------|
| sync | references/commands/sync.md | Reality synchronization |
| groom | references/commands/groom.md | Task refinement |
| next | references/commands/next.md | Task selection |
| implement | references/commands/implement.md | TDD implementation |
| review-code | references/commands/review-code.md | Code quality review |
| review-tests | references/commands/review-tests.md | Test quality review |
| apply-recommendations | references/commands/apply-recommendations.md | Triage and apply fixes |
| pr-prep | references/commands/pr-prep.md | PR creation |
| pr-complete | references/commands/pr-complete.md | PR merge and cleanup |
| discovery | references/commands/discovery.md | Learning capture |
| retrospective | references/commands/retrospective.md | Post-work analysis |
| maintenance | references/commands/maintenance.md | Context network cleanup |
Scenario: Start of day, implement next available task
Invocation:
/gitea-workflow --phase task-cycle
Flow:
Agent: Detecting current state...
No worktree found, checking ready tasks...
Agent: Running sync --last 1d --dry-run
[Sync output: 0 tasks completed but undocumented]
Agent: Running next
Found: TASK-042 - Add user preferences endpoint
Priority: High | Size: Small | Branch: task/TASK-042-preferences
╔═══════════════════════════════════════════╗
║ CHECKPOINT: Task Selection ║
╠═══════════════════════════════════════════╣
║ Selected: TASK-042 ║
║ Proceed with implementation? ║
║ ║
║ [continue] [stop] [other task] ║
╚═══════════════════════════════════════════╝
User: continue
Agent: Creating worktree at .worktrees/TASK-042/
Running implement TASK-042
[Implementation proceeds with TDD...]
Tests: 12 passing
Coverage: 87%
Build: Success
╔═══════════════════════════════════════════╗
║ CHECKPOINT: Implementation Complete ║
╠═══════════════════════════════════════════╣
║ All tests passing, ready for review ║
║ Proceed to code review? ║
║ ║
║ [continue] [stop] ║
╚═══════════════════════════════════════════╝
[Flow continues through review, PR, merge...]
Gitea uses external CI systems (Drone, Woodpecker, Jenkins, etc.). To check CI status:
scripts/gitea-ci-status.sh to query commit statuses| Operation | Tea CLI Command |
|-----------|-----------------|
| List open PRs | tea pulls list --state open |
| Create PR | tea pulls create --title "..." --description "..." --base main --head branch |
| View PR | tea pulls |
| Merge PR (squash) | tea pulls merge --style squash |
| Merge PR (merge) | tea pulls merge --style merge |
| Merge PR (rebase) | tea pulls merge --style rebase |
| Approve PR | tea pulls approve |
| List issues | tea issues list |
For operations not available in the tea CLI, use the provided API scripts:
scripts/gitea-ci-status.sh - Check CI status via Gitea APIscripts/gitea-pr-checks.sh - Get PR review/approval statustea CLI for PR operations)Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.
Intelligently organizes your files and folders across your computer by understanding context, finding duplicates, suggesting better structures, and automating cleanup tasks. Reduces cognitive load and keeps your digital workspace tidy without manual effort.
Generates creative domain name ideas for your project and checks availability across multiple TLDs (.com, .io, .dev, .ai, etc.). Saves hours of brainstorming and manual checking.
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
Implements Manus-style file-based planning for complex tasks. Creates task_plan.md, findings.md, and progress.md. Use when starting complex multi-step tasks, research projects, or any task requiring >5 tool calls.
Creative research ideation and exploration. Use for open-ended brainstorming sessions, exploring interdisciplinary connections, challenging assumptions, or identifying research gaps. Best for early-stage research planning when you do not have specific observations yet. For formulating testable hypotheses from data use hypothesis-generation.
Comprehensive GitHub project management with swarm-coordinated issue tracking, project board automation, and sprint planning
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".
Take jwynia/gitea-workflow from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.