agentleFS

Claude skills and agent skills

Skills real projects publish on GitHub, most starred first. Each one says what it will make an agent do before you copy it.

Worked for most · soon
MicrosoftSkill

agent-lightning

microsoft/agent-lightning/skills/agent-lightning/SKILL.md

Provides the action space, tradeoffs, and evaluation context for improving an editable AI agent against a benchmark while preserving its deployment contract. Use when optimizing agent accuracy, cost, latency, or reliability.

19k3mo agoReviewMountCreate a free account to mount
MicrosoftSkill

rnw-integration

microsoft/react-native-windows/.github/skills/rnw-integration/SKILL.md

Automate React Native Windows integration with upstream React Native nightly versions. Use when: upgrading RNW to a newer React Native nightly, finding target nightly versions, preparing integration PRs, updating package dependencies.

17k12mo agoReviewMountCreate a free account to mount
MicrosoftSkill

error-handling

microsoft/data-formulator/.cursor/skills/error-handling/SKILL.md

统一错误处理系统。在添加 API 端点、修改错误处理、添加前端 API 调用、编写错误相关测试时使用。

17k7mo agoReviewMountCreate a free account to mount
MicrosoftSkill

language-injection

microsoft/data-formulator/.cursor/skills/language-injection/SKILL.md

LLM Agent 多语言注入规范。在修改 Agent 提示词、添加新的 Agent 端点、处理用户可见的后端消息(message_code)时使用。

17k7mo agoReviewMountCreate a free account to mount
MicrosoftSkill

path-safety

microsoft/data-formulator/.cursor/skills/path-safety/SKILL.md

服务端路径安全与文件访问编码规范。在编写文件下载路由、Agent 工具(文件读取/目录列出)、数据连接器/Loader、Workspace 路径操作、沙箱配置时使用。

17k7mo agoReviewMountCreate a free account to mount
MicrosoftSkill

core

microsoft/data-formulator/py-src/data_formulator/analyst/skills/core/SKILL.md

The analyst's built-in capabilities: data-inspection tools and the always-available actions (visualize and ask_user).

17k7mo agoReviewMountCreate a free account to mount
MicrosoftSkill

data-loading

microsoft/data-formulator/py-src/data_formulator/analyst/skills/data-loading/SKILL.md

Discover connected data sources, add new data connectors through a user-confirmed form, inspect table metadata, and run bounded read-only probes when the current workspace data is insufficient.

17k7mo agoReviewMountCreate a free account to mount
MicrosoftSkill

report

microsoft/data-formulator/py-src/data_formulator/analyst/skills/report/SKILL.md

Turn an exploration (threads, findings, charts) into a single Markdown report — note, blog post, executive summary, KPI dashboard, slide brief, or multi-section analytical report, with embedded charts.

17k7mo agoReviewMountCreate a free account to mount
MicrosoftSkill

evaluation-tracing

microsoft/pyright/.github/skills/evaluation-tracing/SKILL.md

Investigate Pyright type-inference or cache regressions, unexpected or lost diagnostics, speculative or reentrant evaluation, evaluator state changes, and repeated evaluator work using local evaluation traces.

16k6d agoReviewMountCreate a free account to mount
MicrosoftSkill

pyright-issue-analysis

microsoft/pyright/.github/skills/pyright-issue-analysis/SKILL.md

Investigate Pyright issues using minimal repros, CPython semantics, the typing specification, and mypy comparisons. Use for issue triage, maintainer response drafts, or evidence-backed issue fixes and PRs.

16k6d agoReviewMountCreate a free account to mount
MicrosoftSkill

pyright-pr-typespec-review

microsoft/pyright/.github/skills/pyright-pr-typespec-review/SKILL.md

Investigate whether a Pyright PR changes typing behavior safely by tracing its diff, designing adversarial cases, comparing exact revisions, and checking relevant CPython behavior. Use for requests to find regressions, assess merge safety, or test effects beyond a PR's own examples.

16k6d agoReviewMountCreate a free account to mount
MicrosoftSkill

dev

microsoft/playwright-cli/.claude/skills/dev/SKILL.md

Development workflows for the playwright-cli repository. Use when the user asks about rolling dependencies, releasing, or other repo maintenance tasks.

15k7mo agoReviewMountCreate a free account to mount
MicrosoftSkill

playwright-patch-release

microsoft/playwright-python/.claude/skills/playwright-patch-release/SKILL.md

Prepare a patch release of Playwright Python (v1.xx.1 and later) from a release branch. Picks the next version, writes the release notes as the list of fixes in microsoft/playwright between the driver of the previous release of the branch and the driver of its tip, and saves them as a draft GitHub release, in place of an old draft. Never publishes the release.

15k3d agoReviewMountCreate a free account to mount
MicrosoftSkill

playwright-release

microsoft/playwright-python/.claude/skills/playwright-release/SKILL.md

Prepare a new Playwright Python release, v1.xx.0, with the full release notes. For a patch release of a release branch, use playwright-patch-release. Checks open bugs, adds Python-specific changes to the Python release notes in microsoft/playwright, opens the release PR, cuts the release branch, and saves a draft GitHub release. Never publishes the release.

15k3d agoReviewMountCreate a free account to mount
MicrosoftSkill

playwright-roll

microsoft/playwright-python/.claude/skills/playwright-roll/SKILL.md

Roll Playwright Python to a new microsoft/playwright commit. Pins the commit, generates the API and builds the driver from it, and ports the upstream diff of the client and the tests.

2 projects use a version of this

15k3d agoReviewMountCreate a free account to mount
MicrosoftSkill

core

microsoft/RD-Agent/rdagent/scenarios/rl/autorl_bench/core/skill.md

你负责维护实验的累积运行总结文件 reports/summary.md。 每轮实验结束后,你需要用 file_editor 在 reports/summary.md *末尾追加*一个新 section。 如果 reports/summary.md 不存在,先创建文件,首行写 # 运行总结。 每轮追加的 section 格式(严格遵守,不增删字段): 数据来源建议(按优先级): - Score/Improvement/Best: scores.json 或服务器返回 - 状态/耗时/exit_code: run.log - 训练类型/关键配置/关键代码: code/train.py - 失败根因: agent.log + run.log 规则: 1. 追加,不要覆盖已有内容 2. 必须按 Iteration 递增写入:读取 reports/summary.md 中最后一个迭代号,当前必须是 N+1;若不满足先修正再写 3. 分析 code下面的 源码,提取训练类型和超参数;若无法确定写 unknown,不留空 4. 如果训练失败,必须给出可定位的根因(日志片段或错误类型),并标注 failure_type(如:code_error_runtime / rollout_logic_wrong / timeout_no_submission / copy_model_fallback / training_diverged / unknown) 5. “做了什么”“为什么”是最重要字段,必须可复现、可检验,且“为什么”必须引用上轮证据(scores.json/run.log/agent.log) 6. 问题/进步 必须包含过程指标或失败类型(如:valid_submission_rate / first_valid_idx / time_to_first_improvement / time_used_ratio / failure_type) 7. 长代码片段每轮最多 1 段,最多 40 行;优先贴本轮新增或改动处;若与上轮相同写“与 Iteration…

15k8mo agoReviewMountCreate a free account to mount
MicrosoftSkill

build-and-test

microsoft/agent-framework/dotnet/.github/skills/build-and-test/SKILL.md

How to build and test .NET projects in the Agent Framework repository. Use this when verifying or testing changes.

Steady10 mentions in 2 weeks

6 projects use a version of this

15k7d agoReviewMountCreate a free account to mount
MicrosoftSkill

project-structure

microsoft/agent-framework/dotnet/.github/skills/project-structure/SKILL.md

Explains the project structure of the agent-framework .NET solution

Steady10 mentions in 2 weeks

21 projects use a version of this

15k7d agoReviewMountCreate a free account to mount
MicrosoftSkill

pull-requests

microsoft/agent-framework/dotnet/.github/skills/pull-requests/SKILL.md

Guidance for creating pull requests and handling PR review comments in the Agent Framework repository. Use this when writing a PR description (filling out the PR template) or when responding to and resolving review comments on an existing PR.

Steady10 mentions in 2 weeks

15 projects use a version of this

15k7d agoReviewMountCreate a free account to mount
CLAUDE.md vs AGENTS.md

About skills

What is a Claude skill?

A folder with a SKILL.md file: a name, a description of when to use it, and instructions. Claude loads a skill only when the task matches its description.

How do I use one I find here?

Copy the folder into your project's .claude/skills/ directory, or into your own skills folder to use it everywhere.

What do the warnings mean?

We read each file for commands that read secrets, delete things or pipe downloads into a shell, and say so before you copy it. No warning is not a promise that a file is safe.

Which skills worked for people?

Open a skill to see its discussion. Reports from people and their agents are coming.