archive-tasks
Archiva tareas completadas de TASKS.md a TASKS-DONE.md. Usar automáticamente cuando TASKS.md tenga muchas tareas completadas o supere 20K tokens.
Best use case
archive-tasks is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Archiva tareas completadas de TASKS.md a TASKS-DONE.md. Usar automáticamente cuando TASKS.md tenga muchas tareas completadas o supere 20K tokens.
Teams using archive-tasks should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/archive-tasks/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How archive-tasks Compares
| Feature / Agent | archive-tasks | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Archiva tareas completadas de TASKS.md a TASKS-DONE.md. Usar automáticamente cuando TASKS.md tenga muchas tareas completadas o supere 20K tokens.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Archive Tasks Archiva tareas completadas de `docs/llm/TASKS.md` a `docs/llm/TASKS-DONE.md`. ## Cuándo Usar Este Skill (Automático) Aplicar automáticamente cuando: - TASKS.md tiene más de 50 tareas completadas `[x]` - TASKS.md supera los 20,000 tokens (error al leer completo) - El usuario menciona que TASKS.md es muy grande - Se detecta que TASKS.md no se puede leer entero ## Modelo **OBLIGATORIO**: Usar `haiku`. Notificar: "Usando Haiku para archivar tareas" ## Proceso 1. Leer `docs/llm/TASKS.md` (en partes si es muy grande) 2. Identificar tareas completadas (líneas con `[x]` o `- [x]`) 3. Leer o crear `docs/llm/TASKS-DONE.md` 4. Añadir tareas completadas al inicio con fecha 5. Eliminar tareas completadas de TASKS.md 6. Guardar ambos archivos 7. Reportar cuántas tareas fueron archivadas ## Formato de TASKS-DONE.md ```markdown # Tareas Completadas ## Archivado: YYYY-MM-DD ### [Sección original] - [x] Tarea completada 1 - [x] Tarea completada 2 --- ## Archivado: YYYY-MM-DD (anterior) ... ``` ## Reglas - **NO eliminar** tareas pendientes `[ ]` o en progreso - **NO modificar** la estructura de secciones de TASKS.md - **PRESERVAR** el contexto de cada tarea (su sección padre) - **AÑADIR** fecha de archivado para trazabilidad ## Ejemplo de Output ``` Usando Haiku para archivar tareas Analizando TASKS.md... - 73 tareas completadas encontradas - 12 tareas pendientes Archivando a TASKS-DONE.md... Done: 73 tareas movidas, TASKS.md reducido ```
Related Skills
archive-obsidian-vault
Archives monthly work items from Obsidian vault Area/ and Projects/ to Archive/ with proper organization and attachment handling. Use when archiving completed monthly work.
tasks-code-review
Use for QUICK PR reviews with structured checklists (architecture, patterns, security, performance). Provides step-by-step review process, git diff commands, and review report templates. Best for pull request reviews and pre-commit checks. NOT for deep refactoring analysis (use code-review instead).
manage-tasks
Manage implementation tasks with sequential sub-steps within a plan
file-archiver
创建和解压ZIP、TAR和GZIP压缩包，支持密码保护。
chatgpt-archive-topic-background-report
Build a topic-focused research collection from ChatGPT archive viewer conversations (latest archive or all archives), run a background Responses API consolidation job with web search, and save markdown plus raw response artifacts. Use when the user asks to find archive threads by topic, reconcile repetition/contradictions, and generate a saved report with minimal polling noise.
pixi-tasks
Complex pixi task workflows and orchestration. Use when building task dependency chains, configuring caching with inputs/outputs, creating parameterized tasks, or setting up CI pipelines—e.g., "pixi task depends-on", "task caching for build automation", "multi-environment test matrices".
mise-tasks
Orchestrate workflows with mise [tasks]. TRIGGERS - mise tasks, mise run, task runner, depends, depends_post, workflow automation, task dependencies.
github-archive
Investigate GitHub security incidents using tamper-proof GitHub Archive data via BigQuery. Use when verifying repository activity claims, recovering deleted PRs/branches/tags/repos, attributing actions to actors, or reconstructing attack timelines. Provides immutable forensic evidence of all public GitHub events since 2011.
archive
Archive completed task/spec work to ./.gtd/archive/
archive-work
Archive completed scratchpads and session logs to project history. Invoke when user says "archive this work", "clean up scratchpad", "archive scratchpad", or after PR is merged.
archive-ticket
Archive completed tickets by moving them to .archived/
archive-project
Archive a completed project by creating an AI-generated summary in Knowledge/, storing the git commit hash for reference, and deleting the original project file. Use when user says a project is "done", "complete", "finished", or wants to "archive" it.