josephgoksu/taskwing/taskwing-next
Claude Code and agent skill by josephgoksu/taskwing
- community
Checking that the SKILL.md file is still in the repository.
Use when you are ready to start the next approved TaskWing task with full context.
Install
npx vskill@latest install josephgoksu/taskwing/taskwing-nextSKILL.md
Start Next TaskWing Task with Full Context
The Workflow Contract lives in CLAUDE.md (single source of truth). Obey it always.
Kill Table
| Impulse | Do Instead | |
|---|---|---|
Skip ask calls for context | Always fetch scope + task context before coding | |
| Start coding without approval | Present the brief, wait for explicit checkpoint approval | |
| Ignore patterns/constraints from ask | Patterns are binding, constraints are mandatory |
Operating Principles
- Context before code. Always run
taskwing askfor both scope and task-specific context before presenting the brief. - The brief is the contract. The task brief (Step 5) defines what you will build. Do not deviate without re-checking.
- Patterns are binding. If
askreturns patterns for the task scope, follow them. If constraints exist, respect them.
Execute these steps IN ORDER. Do not skip any step.
Step 1: Get Next Task
Run:
Extract from the JSON response:
- task_id, title, description
- scope (e.g., "auth", "vectorsearch", "api")
- keywords array
- acceptance_criteria
- suggested_ask_queries (if present)
If the command reports no pending task, inform the user: "No pending tasks. Use /taskwing:context to check plan status."
Step 2: Fetch Scope-Relevant Context
Run taskwing ask with a query based on the task scope:
Examples:
- scope "auth" →
taskwing ask "authentication cookies session patterns" - scope "api" →
taskwing ask "api handlers middleware patterns" - scope "vectorsearch" →
taskwing ask "lancedb embedding vector patterns"
Extract: patterns, constraints, related decisions.
Step 3: Fetch Task-Specific Context
Run taskwing ask with keywords from the task. Use suggested_ask_queries if available, otherwise extract keywords from the title.
Step 4: Claim the Task
Run:
(<task_id> is the value from Step 1.)
Step 5: Present Unified Task Brief
Display in this format:
Step 6: Implementation Start Gate (Hard Gate)
Before writing or editing code, ask for an explicit checkpoint: "Implementation checkpoint: proceed with task [task_id] now?"
If approval is missing or unclear, STOP and respond with: "REFUSAL: I can't start implementation yet. Plan/task checkpoint is incomplete. Please approve this task checkpoint first."
Step 7: Begin Implementation (Only After Approval)
Proceed with the task, following the patterns and respecting the constraints shown above.
CRITICAL: You MUST run all four CLI commands (task next, ask x2, task start) before showing the brief and before requesting implementation approval.
Useful Variants
Use /taskwing:context to check active plan progress.
Security
- Security scanPassed, 95 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/taskwing-next/SKILL.md
Popularity
- Repository stars
- 87
- Repository forks
- 6
- 7-day trend score
- 22
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/josephgoksu/taskwing/taskwing-next)