Update Stop Gate
Use when the user describes a bad Claude behavior pattern to add as a stop-gate rule. Handles updating both autonomy-rules.md and the classifier prompt in stop-gate.py. Trigger phrases: update stop gate, add stop gate rule, new autonomy rule, add stall class, update autonomy rules, add behavior to stop gate.
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 update-stop-gategit clone --depth 1 https://github.com/npow/claude-skills.git /tmp/claude-skills
mkdir -p ~/.claude/skills
cp -r /tmp/claude-skills/update-stop-gate ~/.claude/skills/update-stop-gatePersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Update Stop Gate Add a new stall-detection rule to the autonomy classifier. Two files must be updated in sync. ## Files | File | Role | |------|------| | `~/.claude/autonomy-rules.md` | Source of truth — human-readable rules the classifier LLM reads | | `~/.claude/hooks/stop-gate.py` | Classifier prompt — contains lettered stall checks (a)-(z) in `build_classifier_prompt()` | ## Procedure ### 1. Read both files Read `~/.claude/autonomy-rules.md` and `~/.claude/hooks/stop-gate.py` in parallel. Note: - The last lettered classifier check (to know what letter comes next) - The structure of existing rule bullets in the "WHAT DOES NOT REQUIRE ASKING" section ### 2. Generalize from the user's example The user gives a specific incident. Extract the **class of behavior**, not the specific case. Ask: - What cognitive error causes this? (e.g., "silencing the symptom feels like fixing the problem") - What are 5-8 concrete manifestations across different domains? - What is the ONE narrow exception where this behavior is legitimate? Never use the user's specific variable names, function names, or project details in the rule. ### 3. Scrub for internal/proprietary language Before writing anything, scan the user's description for company-specific terms (product names, internal tool names, team names, proprietary library names). The rules files must be generic — they contain NO employer-specific language. Replace any such terms with generic equivalents.
Details
- Skill name
update-stop-gate- Repository
- npow/claude-skills
- Path
update-stop-gate/SKILL.md- License
- Apache-2.0
- Repo updated
- 20 August 2026
FAQ
What does the Update Stop Gate skill do?
Use when the user describes a bad Claude behavior pattern to add as a stop-gate rule. Handles updating both autonomy-rules.md and the classifier prompt in stop-gate.py. Trigger phrases: update stop gate, add stop gate rule, new autonomy rule, add stall class, update autonomy rules, add behavior to stop gate.
How do I install the Update Stop Gate 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 Update Stop Gate 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"
Guashuai
1DENGYUFAN0/guashuai-junshi
挂帅模式(orchestrator):主会话模型(STRONG)挂帅坐镇,把任务拆成边界清晰的子任务,点将派给子代理模型(CHEAP,worker 子代理)并行执行,帅只做拆解、派兵、验收、整合,省下执行环节的贵模型额度。适合多文件批量修改、多线并行的大任务。MANUAL-INVOKE ONLY — 平时绝不自动触发;即使用户说"任务很大""帮我并行做""拆一下任务"也不激活(就算 CLAUDE.md 里配置了开工前弹提示规则,那也只是建议弹窗,不算触发本模式)。仅当用户显式输入 /guashuai,或消息以「挂帅」开头时才进入。本轮任务打完即收兵;用户说「收兵」「退出」立即结束。
Team Temporal
5npow/claude-skills
Use when coordinating multiple agents on a staged pipeline — plan → PRD → exec → verify → fix — via a durable Temporal-backed workflow that survives session crashes. Trigger phrases include "team temporal", "sagaflow team", "durable team", "temporal-backed agent team". File-based state, independent critic/verifier gates, two-stage review on every source modification, honest termination labels. Fire-and-forget while you do other work.
Junshi
1DENGYUFAN0/guashuai-junshi
军师模式(advisor):主会话模型(CHEAP)做主帅在前线干活,军师子代理(STRONG)只在架构取舍、疑难 bug 定位、方案评审等关键决策点被请出来问一次,日常执行不动用,最大限度省贵模型额度。适合日常开发的省钱默认姿势。MANUAL-INVOKE ONLY — 平时绝不自动触发;即使用户说"帮我省点额度""这个问题很难"也不激活(就算 CLAUDE.md 里配置了开工前弹提示规则,那也只是建议弹窗,不算触发本模式)。仅当用户显式输入 /junshi,或消息以「军师」开头时才进入。持续生效直到用户说「散帐」「退出」。
Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.