coding-task-templates
Provides standard templates for consistent, verifiable coding tasks.
Install
mkdir -p .claude/skills/coding-task-templates && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/11139" && unzip -o skill.zip -d .claude/skills/coding-task-templates && rm skill.zipInstalls to .claude/skills/coding-task-templates
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Structured task templates for agent coding work. Use when creating, assigning, or executing coding tasks that need clear structure, deliverables, and verification steps. Covers implementation, error analysis, fixes, and refactoring workflows with timeouts, checkpoints, and rollback plans.Key capabilities
- →Structure coding tasks
- →Define task deliverables
- →Verify task completion
- →Manage rollback plans
How it works
It provides pre-defined templates that enforce constraints on task size and complexity to prevent context window overflows.
Inputs & outputs
When to use coding-task-templates
- →Creating new features
- →Debugging error reports
- →Refactoring code modules
About this skill
Coding Task Templates
Structured templates for consistent task execution across agents.
⚠️ Agenten-Limitierungen (kritisch seit 2026-04-26)
Kontextfenster überlastet bei >2 Dateien oder >500 Code-Zeilen.
Agenten (Softeware, Sir Stern) produzieren leere/abgebrochene Ergebnisse bei zu großen Tasks.
Regeln:
- Max. 2 Dateien pro Task — bei mehr: Splitte in Sub-Tasks
- Max. 500 Code-Zeilen pro Task — bei mehr: Phase aufteilen
- Keine Phase mit >3 Fixes — bei mehr: Neue Phase starten
- Timeout an Task-Größe anpassen:
- Micro-Fix (1 Datei, <50 Zeilen): 5 Min
- Klein (1-2 Dateien, <200 Zeilen): 10 Min
- Mittel (2 Dateien, <500 Zeilen): 20 Min
- Groß (>2 Dateien oder >500 Zeilen): AUFSPLITTEN
Warum das wichtig ist:
- Agenten lesen Dateien → Kontextfenster füllt sich
- Bei Überlastung: Output wird leer oder Timeout
- Besser: 10 kleine Tasks die funktionieren als 1 großer der scheitert
Quick Select
Choose template based on task type:
| Task Type | Template File | Use When |
|---|---|---|
| Implementation | TEMPLATE_IMPLEMENTATION.md | Building new features |
| Error Analysis | TEMPLATE_ERROR_ANALYSIS.md | Debugging, understanding failures |
| Fix After Analysis | TEMPLATE_FIX.md | Applying known fixes |
| Refactor | TEMPLATE_REFACTOR.md | Restructuring code |
| Cody Multi-Phase | TEMPLATE_CODY.md | Complex multi-phase tasks |
Common Rules (All Templates)
Timeouts
- Max 5 minutes per phase/sub-task
- Save checkpoint, report status, continue
Checkpoints
- Save intermediate state after each deliverable
- Never keep everything in memory until the end
Decision Gates
- If unclear: pause and ask, don't guess
- Document assumptions if decision required
Rollback
- Always have a way back
- Test rollback before destructive changes
Verification
- Syntax check:
python3 -m py_compile <file> - Import test:
python3 -c "from module import Class" - Run tests if available
Usage
- Read appropriate template based on task type
- Fill in
{PLACEHOLDERS}with concrete values - Execute task following template structure
- Create status file as specified
- Report completion with summary
When not to use it
- →Tasks exceeding 500 lines of code
- →Tasks involving more than 2 files
Limitations
- →Max 2 files per task
- →Max 500 lines of code per task
How it compares
It enforces strict task-splitting rules to ensure agent reliability, unlike unstructured task assignment.
Compared to similar skills
coding-task-templates side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| coding-task-templates (this skill) | 0 | 2mo | No flags | Intermediate |
| codex | 32 | 2mo | Review | Advanced |
| deepwiki-rs | 25 | 9mo | Review | Intermediate |
| senior-fullstack | 35 | 7mo | Review | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
You might also like
codex
Lucklyric
Invoke Codex CLI for complex coding tasks requiring high reasoning capabilities. This skill should be invoked when users explicitly mention "Codex", request complex implementation challenges, advanced reasoning, or need high-reasoning model assistance. Automatically triggers on codex-related requests and supports session continuation for iterative development.
deepwiki-rs
sopaco
AI-powered Rust documentation generation engine for comprehensive codebase analysis, C4 architecture diagrams, and automated technical documentation. Use when Claude needs to analyze source code, understand software architecture, generate technical specs, or create professional documentation from any programming language.
senior-fullstack
davila7
Comprehensive fullstack development skill for building complete web applications with React, Next.js, Node.js, GraphQL, and PostgreSQL. Includes project scaffolding, code quality analysis, architecture patterns, and complete tech stack guidance. Use when building new projects, analyzing code quality, implementing design patterns, or setting up development workflows.
typescript-write
metabase
Write TypeScript and JavaScript code following Metabase coding standards and best practices. Use when developing or refactoring TypeScript/JavaScript code.
korean-skill-creator
clwmfksek
한글 기반 클로드 스킬 자동 생성 도구. 사용자가 "클로드 스킬을 만들어줘" 또는 "[요구사항] 스킬 만들어줘"라고 요청할 때 사용. Progressive disclosure 원칙을 따르는 한글 문서 구조(SKILL.md + references/)를 자동으로 생성하고, 실전 예시를 포함한 일관성 있는 스킬 템플릿을 제공.
skill-forge
WilliamSaysX
Automated skill creation workshop with intelligent source detection, smart path management, and end-to-end workflow automation. This skill should be used when users want to create a new skill or convert external resources (GitHub repositories, online documentation, or local directories) into a skill. Automatically fetches, organizes, and packages skills with proactive cleanup management.