Loop Until Done
The single loop skill for ALL recurring and drive-to-completion work. Subsumes the built-in loop (periodic polling), ralph (iterative completion with verification), and loop-until-done (PRD-driven execution). Durable Temporal-backed — survives session crashes. Trigger phrases include "loop", "loop until done", "keep trying", "fix until", "until X passes", "check every N minutes", "keep checking", "poll for", "don't stop until", "ralph", "persist until done", "sagaflow loop", "durable loop".
Install
/plugin marketplace add npow/claude-skillsThe repo is a Claude Code plugin marketplace. Run /plugin afterwards to pick the plugin that includes this skill.
npx skills add npow/claude-skills --skill loop-until-donegit clone --depth 1 https://github.com/npow/claude-skills.git /tmp/claude-skills
mkdir -p ~/.claude/skills
cp -r /tmp/claude-skills/loop-until-done ~/.claude/skills/loop-until-donePersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# loop-until-done The canonical loop skill. Two modes, one entry point: ## Mode 1: Drive-to-completion (default) PRD-driven execution — breaks work into stories with acceptance criteria, iterates story-by-story with independent verification, terminates only when every criterion has fresh passing evidence. **Phases:** 1. **PRD planner** — generates stories with testable acceptance criteria 2. **Falsifiability judge** — marks each criterion pass/fail for falsifiability 3. **Executor** — completes each story, runs verification 4. **Verifier** — per-criterion evidence check 5. **Reviewer** — final verdict with configurable reviewer (--critic) **From ralph:** session persistence, structured story tracking (prd.json), progress tracking across iterations, reviewer verification before completion. **From autopilot:** autopilot should invoke this skill for its Phase 3 verify loop rather than implementing its own. ## Mode 2: Periodic polling (--poll) Recurring check on a schedule — fires the same probe on an interval, stops when a condition is met or the user cancels. **From built-in loop:** ScheduleWakeup-based recurring execution, CronCreate for fixed intervals, Monitor for event-driven waking. When `--poll <interval>` is present, skip PRD generation and run the task as a recurring check. ## Execution routing (sagaflow-first)
Details
- Skill name
loop-until-done- Repository
- npow/claude-skills
- Path
loop-until-done/SKILL.md- License
- Apache-2.0
- Repo updated
- 20 August 2026
FAQ
What does the Loop Until Done skill do?
The single loop skill for ALL recurring and drive-to-completion work. Subsumes the built-in loop (periodic polling), ralph (iterative completion with verification), and loop-until-done (PRD-driven execution). Durable Temporal-backed — survives session crashes. Trigger phrases include "loop", "loop until done", "keep trying", "fix until", "until X passes", "check every N minutes", "keep checking", "poll for", "don't stop until", "ralph", "persist until done", "sagaflow loop", "durable loop".
How do I install the Loop Until Done skill?
Claude Code plugin: /plugin marketplace add npow/claude-skills. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Loop Until Done popular?
It lives in npow/claude-skills, which has 5 GitHub stars and 1 forks.
Related skills
Autopilot
5npow/claude-skills
Use when the user says "autopilot", "build this", "make it", "ship it", "just do it", "do it", "implement this", or gives a vague idea, spec, task list, or bug fix and expects autonomous execution. Handles decomposition, agent coordination, and verification automatically. "build me end to end", "go from idea to code", "do everything", "run this autonomously". Follows the Spec-Driven Development workflow: specify → clarify → plan → tasks → analyze → implement.
Build Python Library
5npow/claude-skills
Implements pip-installable Python libraries from scratch using src layout, pyproject.toml, and pytest. Use when the user asks to build, create, implement, or scaffold a Python library, package, pip package, middleware, SDK, or wrapper. Covers project scaffolding, proxy/wrapper patterns, provider-agnostic interfaces, async/sync support, and test infrastructure.
Canon Design Review
5npow/claude-skills
Architecture-level design review evaluating 15 Tier 2 best practices drawn from DDD (Evans), POEAA (Fowler), Release It! (Nygard), DDIA (Kleppmann), Team Topologies (Skelton/Pais), How Buildings Learn (Brand), and Systemantics (Gall). Auto-invoke when a PR touches: - Service definitions, infrastructure code, API boundaries, or database schemas - Files matching **/architecture*, **/design*, **/api/*, **/schema*, **/migrations/* - Any directory named services/, infrastructure/, platform/, domain/, core/ Also invoke when the user says: - "design review", "architecture review", "review the design"
Platform Friction Detector
5npow/claude-skills
Use when scanning for silent user workarounds, platform friction signals, dependency removals, or users routing around your libraries. Trigger phrases: platform friction, user workarounds, who's dropping our libs, silent churn, friction scan, are users working around us.
Historical Vlog Creator
5GAGAA-HUE/ASHUO-claude-skills
历史名人第一视角Vlog脚本生成器。历史人物用第一人称自述自己的真实生平,像在录短视频vlog一样讲经历。 人物不穿越,待在自己的时代——但说话方式、情绪表达全用现代网络语言,让观众在笑声中真正了解这个人。 本技能强调"深层内容挖掘":不只停留在人物标签,而是追问其行为背后的权力结构、阶层矛盾与真实动机,形成"表层行为→深层动机→结构性后果"的因果链,让视频具有认知反差和深度。 当用户提到以下任何情形时立即触发:历史名人vlog脚本、历史人物的一生/生平、把历史事件做成短视频、 历史人物第一视角讲述、古代名人用现代语言自述、历史反差喜剧脚本、历史人物生平短视频。 即使用户只是说"帮我把苏轼的故事做成视频"或"王阳明一生怎么拍成短视频",也应立即以此技能介入。 本技能输出两阶段:先出创意框架(供用户确认),用户明确同意后才写完整台词与发布信息。
Seedance 2.5 Scene Director
5GAGAA-HUE/ASHUO-claude-skills
Seedance 2.5 连续叙事电影提示词生成器。默认输出一整段、无标题无标签无分段无时间轴、可直接复制给模型的成品级中文提示词;强调连续摄影机调度、群像空间关系、对白动作同步与视觉锚点回收。仅在用户明确要求结构化提示词、分段版、按模块输出或重型版时使用带标签结构。
Browse the most popular Claude skills, all other skills, or write your own with the skills generator.