# Task Completer

> Use when finishing a task — moves the v3.0.0 task folder to completed/, updates project_state.md, suggests next task. Runs all 5 quality gates and blocks completion if any gate fails. Trigger: 'finish task', 'done with task', 'move to completed'.

- **Type:** Skill
- **Install:** `agentstack add skill-camoa-claude-skills-task-completer`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [camoa](https://agentstack.voostack.com/s/camoa)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [camoa](https://github.com/camoa)
- **Source:** https://github.com/camoa/claude-skills/tree/main/ai-dev-assistant/skills/task-completer

## Install

```sh
agentstack add skill-camoa-claude-skills-task-completer
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Task Completer

Finalize tasks and update project memory.

## Required References

**Load before completing any task:**

| Reference | Enforces |
|-----------|----------|
| `references/quality-gates.md` | Gates 2, 3, 4 (must ALL pass) |
| framework security guide (use `/dev-guides-navigator security` to resolve for the project's stack) | Gate 4 security review |

## Activation

Activate when you detect:
- `/ai-dev-assistant:complete` command
- "Done with X task" or "Task complete"
- "Finish this task"
- All acceptance criteria appear met

## Gate Enforcement

**Task CANNOT be completed until ALL gates pass:**

| Gate | Check | Blocking? |
|------|-------|-----------|
| Gate 1 | Code standards (invoke `code-pattern-checker`) | YES |
| Gate 2 | Tests pass (user confirms) | YES |
| Gate 3 | Architecture compliance | YES |
| Gate 4 | Security review (invoke `guide-integrator` with the framework's security topic, resolved via `/dev-guides-navigator security`; do NOT WebFetch directly) | YES |
| Gate 5 | All acceptance criteria in `task.md` are `[x]` and `## Phase Status` shows Phases 1–3 complete | YES |

## Workflow

### 1. Verify Completion

Use `Read` on the task tracker file: `{project_path}/implementation_process/in_progress/{task_name}/task.md` (v3.0.0 folder structure; task.md lives inside the task folder).

Check each acceptance criterion. Ask user:
```
Completion checklist for {task_name}:

Acceptance Criteria:
- [ ] {criterion 1} - Is this done?
- [ ] {criterion 2} - Is this done?
- [ ] {criterion 3} - Is this done?

Confirm all acceptance criteria are met (yes/no):
```

If NO, identify what's remaining and continue working.

### 2. Run Quality Gates (references/quality-gates.md)

**ALL gates must pass before completion:**

#### Gate 1: Code Standards
Invoke `code-pattern-checker` skill on modified files.
- [ ] Linting passes (configured for the project's language and framework)
- [ ] Static analysis passes (if configured)

#### Gate 2: Tests Pass
Ask user to confirm:
```
Tests verification (user must run):
   {test_path}

- [ ] All existing tests pass?
- [ ] New code has test coverage?
- [ ] No skipped tests without documented reason?

Confirm tests pass (yes/no):
```

#### Gate 3: Architecture Compliance
Check against architecture/main.md:
- [ ] SOLID principles followed (references/solid.md)
- [ ] DRY - no code duplication (references/dry-patterns.md)
- [ ] Library-First pattern used (references/library-first.md)

#### Gate 4: Security — invoke `guide-integrator` with the framework's security topic (resolved via `/dev-guides-navigator security`; do NOT WebFetch directly)
- [ ] Input validated
- [ ] Output escaped properly
- [ ] No raw queries built from user input
- [ ] Access checks on all routes

#### Gate 5: Task Artifacts Complete
- [ ] All acceptance criteria in `task.md` are `[x]`
- [ ] `## Phase Status` in `task.md` shows Phases 1, 2, 3 all `[x]`
- [ ] `research.md`, `architecture.md`, `implementation.md` all present in the task folder

**If ANY blocking gate fails:** Task completion is BLOCKED. Fix issues first.

### 3. Update Task File

Use `Edit` to add completion section to the task file:

```markdown
---

## Completion

**Completed:** {YYYY-MM-DD}
**Final Status:** Complete

### Summary
{Brief description of what was implemented}

### Files Changed
| File | Action |
|------|--------|
| src/... | Created |
| tests/... | Created |
| config/... | Modified |

### Test Results
- Unit tests: {count} passing
- Integration tests: {count} passing
- Total: All passing

### Notes
{Any implementation notes, deviations, or decisions made}
```

### 4. Move Task Folder

v3.0.0 tasks are folders (task.md + research.md + architecture.md + implementation.md + any component files). Move the entire folder, not a single file.

```bash
mkdir -p "{project_path}/implementation_process/completed"
mv "{project_path}/implementation_process/in_progress/{task_name}" "{project_path}/implementation_process/completed/{task_name}"
```

(`{task_name}` is the folder name — no `.md` suffix. The folder contains `task.md` and all phase artifacts.)

### 5. Update project_state.md

Use `Edit` to update:

```markdown
## Progress

### Completed Tasks
| Task | Completed | Notes |
|------|-----------|-------|
| {task_name} | {date} | {one-line summary} |

## Current Focus
{Update to next task or "Ready for next component"}
```

### 6. Suggest Next Task

Use `Bash` to list remaining in-progress task directories (v3.0.0 folder structure — tasks are directories, not `.md` files):
```bash
ls -1d "{project_path}/implementation_process/in_progress/"*/ 2>/dev/null
```

Each result is a task folder; read its `task.md` to inspect `## Phase Status` and acceptance criteria before ranking.

Analyze dependencies and priorities. Present:
```
Task complete: {task_name}

Next task options:
1. {next_task} - {reason: dependency unblocked / priority}
2. {alternative} - {reason}
3. No more tasks - component complete

Which task next? (1/2/3 or other):
```

### 7. Invoke Verification

If this was the last task for a component, suggest:
```
Component {name} appears complete.

Run final validation?
- superpowers:verification-before-completion
- Full test suite
- Integration tests

Proceed? (yes/no)
```

## Stop Points

STOP and wait for user:
- After showing completion checklist (confirm all done)
- If code-pattern-checker finds issues
- After suggesting next task (let user choose)
- Before running verification

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [camoa](https://github.com/camoa)
- **Source:** [camoa/claude-skills](https://github.com/camoa/claude-skills)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-camoa-claude-skills-task-completer
- Seller: https://agentstack.voostack.com/s/camoa
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.