# Ck:fix

> ALWAYS activate this skill before fixing ANY bug, error, test failure, CI/CD issue, type error, lint, log error, UI issue, code problem.

- **Type:** Skill
- **Install:** `agentstack add skill-manhvann-codexkit-fix`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [manhvann](https://agentstack.voostack.com/s/manhvann)
- **Installs:** 0
- **Category:** [Developer Tools](https://agentstack.voostack.com/c/developer-tools)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [manhvann](https://github.com/manhvann)
- **Source:** https://github.com/manhvann/codexkit/tree/main/.agents/skills/fix

## Install

```sh
agentstack add skill-manhvann-codexkit-fix
```

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

## About

# Fixing

Unified skill for fixing issues of any complexity with intelligent routing.

## Arguments

- `--auto` - Activate autonomous mode (**default**)
- `--review` - Activate human-in-the-loop review mode
- `--quick` - Activate quick mode
- `--parallel` - Activate parallel mode: route to parallel `fullstack_developer` agents per issue

## Workflow

### Step 1: Mode Selection

**First action:** If there is no "auto" keyword in the request, ask the user to determine workflow mode:

| Option | Recommend When | Behavior |
|--------|----------------|----------|
| **Autonomous** (default) | Simple/moderate issues | Auto-approve if score >= 9.5 & 0 critical |
| **Human-in-the-loop Review** | Critical/production code | Pause for approval at each step |
| **Quick** | Type errors, lint, trivial bugs | Fast debug → fix → review cycle |

See `references/mode-selection.md` for the mode-selection prompt format.

### Step 2: Debug

- Activate `ck:debug` skill.
- Guess all possible root causes.
- Prefer multiple `Explore`/scout agents in parallel to verify each hypothesis when the runtime exposes delegation; otherwise use parallel searches and report the limitation.
- Create report with all findings for the next step.

### Step 3: Complexity Assessment & Task Orchestration

Classify before routing. See `references/complexity-assessment.md`.

| Level | Indicators | Workflow |
|-------|------------|----------|
| **Simple** | Single file, clear error, type/lint | `references/workflow-quick.md` |
| **Moderate** | Multi-file, root cause unclear | `references/workflow-standard.md` |
| **Complex** | System-wide, architecture impact | `references/workflow-deep.md` |
| **Parallel** | 2+ independent issues OR `--parallel` flag | Parallel `fullstack_developer` agents |

**Task Orchestration (Moderate+ only):** After classifying, use available task-tracking tools for all phases upfront with dependencies. See `references/task-orchestration.md`.
- Skip for Quick workflow (< 3 steps, overhead exceeds benefit)
- Create tracked tasks with dependency chains when task tools exist
- Update task/checklist state as each phase completes
- For Parallel: create separate task trees per independent issue

### Step 4: Fix Implementation & Verification

- Implement fix per selected workflow, updating Tasks as phases complete.
- Prefer multiple scout agents to verify no regressions when available.
- Prevent future issues by adding comprehensive validation.

### Step 5: Finalize (MANDATORY - never skip)

1. Report summary: confidence score, changes, files
2. Prefer `docs_manager` subagent → update the configured docs path if changes warrant
3. Update task state/checklists and mark all tracked tasks completed
4. Ask user if they want to commit via `git_manager` subagent

---

## IMPORTANT: Skill/Subagent Activation Matrix

See `references/skill-activation-matrix.md` for complete matrix.

**Always activate:** `ck:debug` (all workflows)
**Conditional:** `ck:problem-solving`, `ck:sequential-thinking`, `ck:brainstorm`, `ck:context-engineering`
**Subagents:** `debugger`, `researcher`, `planner`, `code_reviewer`, `tester`, `Bash`
**Parallel:** Multiple `Explore` agents for scouting, `Bash` agents for verification

## Output Format

Unified step markers:
```
✓ Step 0: [Mode] selected - [Complexity] detected
✓ Step 1: Root cause identified - [summary]
✓ Step 2: Fix implemented - [N] files changed
✓ Step 3: Tests [X/X passed]
✓ Step 4: Review [score]/10 - [status]
✓ Step 5: Complete - [action taken]
```

## References

Load as needed:
- `references/mode-selection.md` - Prompt format for mode
- `references/complexity-assessment.md` - Classification criteria
- `references/task-orchestration.md` - Native Codex Task patterns for moderate+ workflows
- `references/workflow-quick.md` - Quick: debug → fix → review
- `references/workflow-standard.md` - Standard: full pipeline with Tasks
- `references/workflow-deep.md` - Deep: research + brainstorm + plan with Tasks
- `references/review-cycle.md` - Review logic (autonomous vs HITL)
- `references/skill-activation-matrix.md` - When to activate each skill
- `references/parallel-exploration.md` - Parallel Explore/Bash/Task coordination patterns

**Specialized Workflows:**
- `references/workflow-ci.md` - GitHub Actions/CI failures
- `references/workflow-logs.md` - Application log analysis
- `references/workflow-test.md` - Test suite failures
- `references/workflow-types.md` - TypeScript type errors
- `references/workflow-ui.md` - Visual/UI issues (requires design skills)

## Source & license

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

- **Author:** [manhvann](https://github.com/manhvann)
- **Source:** [manhvann/codexkit](https://github.com/manhvann/codexkit)
- **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-manhvann-codexkit-fix
- Seller: https://agentstack.voostack.com/s/manhvann
- 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%.