Skills by risk · page 162

Highest-trust agent skills

9,826 skills rated SAFE with grade A or B, best score first. All are grade B today: grade A needs a sandboxed run we do not do for skills yet. Ties are broken by stars, so a repository with many skills can fill a page.

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

ModelsAtlas. “Highest-trust agent skills”. Retrieved 30 Oct 2026. https://modelsatlas.com/skills/trusted/page/162
9,826 SAFE skills · page 162 of 410 · ranked by trust score, then stars
Playwright Screen Recording✓SAFE B

liaohch3/claude-tap

Record browser test videos with Playwright for PR review and bug fix verification

★ 3.3kGitHub stars
Pr Preflight✓SAFE B

liaohch3/claude-tap

Full pre-PR merge-readiness check. Run this before opening or merging a pull request — it validates local gates (lint, format, tests), CI status, screenshot evidence, and PR metadata in one pass. Also useful for…

★ 3.3kGitHub stars
Push Release✓SAFE B

liaohch3/claude-tap

Push to GitHub and optionally bump version to trigger PyPI release

★ 3.3kGitHub stars
Real E2e Test✓SAFE B

liaohch3/claude-tap

Run real E2E tests against Claude CLI in pytest and tmux modes

★ 3.3kGitHub starsTesting
Screenshot Validation✓SAFE B

liaohch3/claude-tap

Validate screenshot and viewer HTML quality for PR evidence. Run this after adding or modifying images under .agents/evidence/pr/ or .agents/recordings/, or after generating a new viewer HTML file. Combines image…

★ 3.3kGitHub stars
Translate I18n✓SAFE B

liaohch3/claude-tap

Fill missing i18n translations in the viewer source JSON. Run this after adding or modifying English or Chinese UI strings in claude_tap/viewer_i18n.json — it auto-translates to ja, ko, fr, ar, de, ru via OpenRouter.

★ 3.3kGitHub stars
agentic✓SAFE B

bergside/awesome-design-skills

Conversational AI-first interface with minimal controls, clear outcomes, and delegated task flows for agentic workflows.

★ 3.3kGitHub starsAutomation
difit-review✓SAFE B

yoshiko-pg/difit

Review a specific diff (branch, commit, or GitHub PR) and show the findings as comments inside difit, the local diff viewer. Explicit opt-in only — use when the user explicitly names difit, asks to open or annotate the…

★ 3.3kGitHub starsCoding & review
difit✓SAFE B

yoshiko-pg/difit

Ask the user for a code review by opening the changes in difit, a local diff viewer. Explicit opt-in only — use when the user names difit, asks to open or show the diff in the viewer, or has a standing instruction to…

★ 3.3kGitHub stars
eas-workflows✓SAFE B

expo/skills

Helps understand and write EAS workflow YAML files for Expo projects. Use this skill when the user asks about CI/CD or workflows in an Expo or EAS context, mentions .eas/workflows/, or wants help with EAS build…

★ 3.3kGitHub starsAutomation
finance✓SAFE B

jjyaoao/helloagents

Comprehensive Finance API integration skill for real-time and historical financial data analysis, market research, and investment decision-making. Priority use cases: stock price queries, market data analysis, company…

★ 3.3kGitHub stars
data-quality-checker✓SAFE B

tradermonty/claude-trading-skills

Validate data quality in market analysis documents and blog articles before publication. Use when checking for price scale inconsistencies (ETF vs futures), instrument notation errors, date/day-of-week mismatches,…

★ 3.2kGitHub starsData & analysis
comet-verify✓SAFE B

rpamis/comet

验证 Classic change 并记录结果。在用户调用 /comet-verify,或 Classic Runtime 进入 Verify 时使用。

★ 3.2kGitHub starsCoding & review
qwenchance✓SAFE B

thananon/9arm-skills

Keeps a long Claude Code task on-track — breaks out of looping/circular thinking, watches the context budget, bounds internal reasoning, and triggers a clean handoff before the window fills. Use when the model is…

★ 3.2kGitHub stars
scrutinize✓SAFE B

thananon/9arm-skills

Outsider-perspective end-to-end review of a plan, PR, or code change. First questions intent and whether a simpler/more elegant approach would achieve the same goal, then traces the actual code path (not just the diff)…

★ 3.2kGitHub stars
comet-open✓SAFE B

rpamis/comet

创建 Classic change,整理需求并请用户确认。在用户调用 /comet-open,或 Classic 进入 Open、恢复初始化时使用。

★ 3.2kGitHub starsCoding & review
qwen-agent✓SAFE B

thananon/9arm-skills

Delegate menial, well-scoped coding tasks to a cheap Qwen-backed subagent via the `claude-9arm` command instead of burning Claude tokens/quota. Use when the work is mechanical and low-risk — bulk renames, formatting,…

★ 3.2kGitHub stars
wecomcli-doc✓SAFE B

wecomteam/wecom-cli

企业微信在线 doc 文档技能。能够新建 doc、导入本地 .doc/.docx/.txt 为 doc、读取 doc 内容、向 doc 追加或覆盖写入。仅当用户明确出现「doc」「docx」「word」「在线文档」「office 文档」等强类型词,或提供 https://doc.weixin.qq.com/doc/xxx…

★ 3.2kGitHub starsDocs & writing
post-mortem✓SAFE B

thananon/9arm-skills

Write the canonical engineering record of a fixed bug — root cause, mechanism, fix, validation, and how it slipped through. Engineer-audience, code identifiers welcome. Use after a debug session lands a fix, before…

★ 3.2kGitHub stars
management-talk✓SAFE B

thananon/9arm-skills

Rewrite engineer-to-engineer content for engineering-org leadership (VPs, directors, PMs, release managers, execs in an engineering-savvy company) and shape it for the channel it is going to — JIRA comment, Slack post,…

★ 3.2kGitHub stars
wecomcli-contact✓SAFE B

wecomteam/wecom-cli

使用 wecom-cli 按姓名、拼音、英文名或别名搜索企业微信通讯录中的人员,并查询匹配人员的 userid、部门和职务。适用于查找联系人、区分同名人员、获取用户 userid,以及列出全部同名人员。

★ 3.2kGitHub stars
comet-design✓SAFE B

rpamis/comet

完成 Classic 技术设计并请用户确认。在用户调用 /comet-design,或 Classic Runtime 进入 Design 时使用。

★ 3.2kGitHub starsCoding & review
Claude-Code-Everything-You-Need-to-Know✓SAFE B

wesammustafa/Claude-Code-Everything-You-Need-to-Know

Audit a CLAUDE.md file for the patterns that actually degrade Claude Code's output — vagueness, unnamed files, stale facts, and bloat. Use when asked to review, audit, improve, shrink, or fix a CLAUDE.md, and when a…

★ 3.2kGitHub starsCoding & review
comet-archive✓SAFE B

rpamis/comet

归档并交付 Classic change。在用户调用 /comet-archive,或 Classic Runtime 进入 Archive、恢复交付时使用。

★ 3.2kGitHub starsCoding & review