PR Review Provider
yansongda/pay
A skill your agent uses when reviewing PRs that add or modify a payment Provider in yansongda/pay - covers plugin pipeline, multi-tenant safety, signature verification, docs, and naming conventions.
Set up and send technical status notifications through WeCom (Enterprise WeChat) webhooks.
$ npx skills add daymade/claude-code-skills --skill setup-notifications-via-wecom -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install daymade/claude-code-skills setup-notifications-via-wecom --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/daymade/claude-code-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/setup-notifications-via-wecom .claude/skills/setup-notifications-via-wecom && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "setup-notifications-via-wecom" agent skill from https://github.com/daymade/claude-code-skills/tree/main/setup-notifications-via-wecom into .claude/skills/setup-notifications-via-wecom/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "setup-notifications-via-wecom", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/daymade/claude-code-skills/tree/main/setup-notifications-via-wecomType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add daymade/claude-code-skills --skill setup-notifications-via-wecom -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install daymade/claude-code-skills setup-notifications-via-wecom --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/daymade/claude-code-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/setup-notifications-via-wecom .agents/skills/setup-notifications-via-wecom && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "setup-notifications-via-wecom" agent skill from https://github.com/daymade/claude-code-skills/tree/main/setup-notifications-via-wecom into .agents/skills/setup-notifications-via-wecom/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "setup-notifications-via-wecom", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add daymade/claude-code-skills --skill setup-notifications-via-wecom -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install daymade/claude-code-skills setup-notifications-via-wecom --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/daymade/claude-code-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/setup-notifications-via-wecom .cursor/skills/setup-notifications-via-wecom && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "setup-notifications-via-wecom" agent skill from https://github.com/daymade/claude-code-skills/tree/main/setup-notifications-via-wecom into .cursor/skills/setup-notifications-via-wecom/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "setup-notifications-via-wecom", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/daymade/claude-code-skills.git --path setup-notifications-via-wecom--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add daymade/claude-code-skills --skill setup-notifications-via-wecom -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install daymade/claude-code-skills setup-notifications-via-wecom --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/daymade/claude-code-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/setup-notifications-via-wecom .gemini/skills/setup-notifications-via-wecom && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "setup-notifications-via-wecom" agent skill from https://github.com/daymade/claude-code-skills/tree/main/setup-notifications-via-wecom into .gemini/skills/setup-notifications-via-wecom/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "setup-notifications-via-wecom", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install daymade/claude-code-skills setup-notifications-via-wecomInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add daymade/claude-code-skills --skill setup-notifications-via-wecom -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/daymade/claude-code-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/setup-notifications-via-wecom .github/skills/setup-notifications-via-wecom && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "setup-notifications-via-wecom" agent skill from https://github.com/daymade/claude-code-skills/tree/main/setup-notifications-via-wecom into .github/skills/setup-notifications-via-wecom/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "setup-notifications-via-wecom", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add daymade/claude-code-skills --skill setup-notifications-via-wecom -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install daymade/claude-code-skills setup-notifications-via-wecom --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/daymade/claude-code-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/setup-notifications-via-wecom .opencode/skills/setup-notifications-via-wecom && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "setup-notifications-via-wecom" agent skill from https://github.com/daymade/claude-code-skills/tree/main/setup-notifications-via-wecom into .opencode/skills/setup-notifications-via-wecom/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "setup-notifications-via-wecom", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
setup-notifications-via-wecomSet up and send technical status notifications through WeCom (Enterprise WeChat) webhooks.
Setup Notifications Via Wecom is an agent skill from daymade/claude-code-skills. Set up and send technical status notifications through WeCom (Enterprise WeChat) webhooks. Use this skill whenever the user needs to send notifications, alerts, backup completion reports, or status updates via WeCom; when they mention 企业微信, 企微机器人, webhook, or alerting; or when a message needs to be clear, unambiguous, and technically precise rather than vague or condescending.
Its SKILL.md is about 3.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 11 other files, including scripts and reference files (for example `evals/evals.json`, `references/message_best_practices.md` and `references/sls-recurring-notifications.md`).
It sits in Backend & APIs, covering Webhooks and Messaging and chat bots. It works with WeChat. The repository describes itself as: Professional Claude Code skills marketplace featuring production-ready skills for enhanced development workflows. The licence is MIT.
8 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit 872127b. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Ships 2 files in scripts/ (Python), which the agent can run.
Shell commands in SKILL.md call:
uvclaudecurlFrom the folder's file list and the shell code blocks in SKILL.md.
Hosts in commands or code, which the agent is likely to contact:
qyapi.weixin.qq.comFrom URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Setup Notifications Via Wecom loads about 3.1k tokens when it runs, and up to ~5.9k if it reads all its reference files. Until then it costs about 102 tokens; SKILL.md has 1,419 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
The full file from daymade/claude-code-skills at commit 872127b, republished under its MIT licence (© daymade). 1,419 words, ~3,059 tokens.
.claude/skills/setup-notifications-via-wecom/SKILL.md (or your agent's skills folder). This skill also uses 7 other files; get the full folder from GitHub.This skill helps you send clear, unambiguous technical notifications through a WeCom group bot webhook. Use the setup and sending workflows below:
The bundled script scripts/send_wecom.py handles the actual HTTP call, using the host network configuration. Recipient identity is explicit configuration:
self may send automatically; others requires human confirmation; missing identity fails fast.
When integrating an existing Alibaba Cloud SLS notification pipeline or a recurring digest, read the SLS adapter guide. Reuse the project's sampler, scheduler and SLS sync owner; the bundled sender continues to own ordinary plain-text sends.
Trigger this skill when the user:
Check existing config:
cat ~/.config/setup-notifications-via-wecom/config.jsonIf it exists and contains webhook_url, skip to Send a Message.
Get the webhook URL from the WeCom group bot settings. It looks like:
https://qyapi.weixin.qq.com/cgi-bin/webhook/send?key=YOUR_KEYStore it privately (outside the skill bundle, so it survives updates):
mkdir -p ~/.config/setup-notifications-via-wecom
echo '{"webhook_url": "https://qyapi.weixin.qq.com/cgi-bin/webhook/send?key=YOUR_KEY"}' \
> ~/.config/setup-notifications-via-wecom/config.json
chmod 600 ~/.config/setup-notifications-via-wecom/config.jsonClassify the exact target and bind the canonical sender without exposing or rewriting the webhook value:
uv run --no-project python scripts/set_recipient.py \
--scope self --label "My private self channel"Use self only when the configured webhook is visible only to the user. Use
others for every other person or group. Do not guess when the target is unknown.
The command also records this sender's absolute path and digest; after the sender
is upgraded, rerun the command before sending again.
Test connectivity by sending a test message (run from the skill directory):
uv run --no-project python scripts/send_wecom.py --message "WeCom webhook test ✅"If you see the message in the WeCom group, setup is done.
These rules come from real corrections. Apply them to every notification.
The first line must say what happened. Do not bury the conclusion.
Claude Code 备份同步完成 ✅Never say "synced 1075 sessions" if only 13 were new today.
Every count must be accompanied by what it counts. Prefer:
- 源目录主 session:1075 个
- 备份主 session:2328 个Avoid undefined terms like "session" alone — it may include workflow journals, subagent files, or tool outputs.
Prefer:
Avoid:
Do not include commit hashes, file paths, internal documentation references, or verbose explanations unless the user explicitly asks for them.
Use correct technical terms and define them. Do not translate everything into "大白话" simplifications that hide precision.
When the user asked "does it miss anything?", answer directly:
- 验证:0 缺失,0 滞后Tell the user whether they need to do anything:
- 下一步:无需操作,下次自动同步 03:00Use when a backup/sync job finishes and you need to report completeness.
Claude Code 备份同步完成 ✅
- 自动同步:今日 03:00 正常执行
- 本次手动同步:补充 03:00 后的增量
- 主 session:13 个
- 子代理/工具输出/工作流:230 个
- 合计:243 个文件
- 验证:0 缺失,0 滞后
- 当前状态:
- 源目录主 session:1075 个
- 备份主 session:2328 个
- 下一步:无需操作,下次自动同步 03:00Use when something requires immediate action. Do not use this template for routine "all good" updates.
🚨 [P?] [服务/任务名] [症状]
- 影响:[谁/什么受影响,程度如何]
- 严重程度:[P1–P5 等级]
- 开始时间:[YYYY-MM-DD HH:MM TZ]
- 已采取:[正在做的动作]
- 下一步:[建议动作或预计下次更新时间]
- 相关链接:[dashboard/runbook,可选]Rules:
Use for routine "all good" updates.
[任务名] 状态正常 ✅
- 检查时间:2026-06-24 03:00 CST
- 关键指标:
- 源目录主 session:1075 个
- 备份主 session:2328 个
- 本次变更:无
- 下一步:无需操作Read recipient_scope and recipient_label before sending. A self target is
the user's own delivery channel and needs no authorization. An others target
is an external send: show the exact label and message and wait for the active
human-confirmation gate. Missing/invalid metadata is a configuration error, not
permission to guess.
Matching webhook URLs proves the same endpoint, not the recipient scope. If new
observations conflict with the stored self label, pause only that send and verify
the exact group and audience. A displayed member name alone does not prove a
different person's identity. Preserve normal automatic delivery for a confirmed
self binding; do not relabel a group or rewrite shared metadata to bypass the
confirmation boundary. For recurring delivery to others, confirmation must cover
the exact group, report content and schedule, plus any separately required deployment
approval.
uv run --no-project python scripts/send_wecom.py \
--message "你的消息内容"For multiline messages, use a file:
cat > /tmp/wecom_msg.txt <<'EOF'
Claude Code 备份同步完成 ✅
- 验证:0 缺失,0 滞后
EOF
uv run --no-project python scripts/send_wecom.py \
--file /tmp/wecom_msg.txtIf you prefer not to use the script:
curl -s -X POST 'https://qyapi.weixin.qq.com/cgi-bin/webhook/send?key=YOUR_KEY' \
-H 'Content-Type: application/json' \
-d '{
"msgtype": "text",
"text": {
"content": "YOUR_MESSAGE"
}
}'Network: Inherit the host/project HTTP(S) proxy and no_proxy policy. A required proxy must remain in use; do not infer a direct-connect requirement from the Tencent domain. Configure an HTTP(S) proxy explicitly when the host requires one: Python urllib does not implement generic SOCKS ALL_PROXY routing. On macOS, an empty proxy environment can still select the system proxy. For proxy selection, exceptions and HTTP-bypass versus TUN diagnosis, load tunnel-doctor and its proxy-conflict reference (proxy_conflict_reference.md, NO_PROXY section); inspect the sender process rather than clearing all proxies.
After upgrading the sender, refresh its configured digest using the existing
set_recipient.py workflow, preserving the same scope and label. Do not relabel
a group as self merely to pass the guard.
When a user asks "let my backup script send WeCom notifications", do the following:
self.others, obtain human confirmation; then call scripts/send_wecom.py.Use the existing bound sender and target; keep event identity and delivery state in the owning worker. For one automatic event, call send_message(..., max_attempts=1) or the supported guard-owned outbox path. The general manual-send retry default is not the worker's delivery policy.
Classify the parsed response before deciding whether a later attempt is permitted:
| Evidence | Worker outcome |
|---|---|
JSON object with integer errcode=0 | API accepted; receiver confirmation is a separate observation |
JSON object with nonzero integer errcode | Explicit API rejection |
Missing/null errcode, boolean, string, non-integer, invalid JSON, timeout or lost connection | Unknown; keep the event identity and do not automatically replay it |
For Python, test type(code) is int; isinstance(False, int) is true and False == 0 must not become acceptance. If the generic sender raises before returning a valid response, the owning worker keeps the result unknown. A new test must exercise a genuinely distinct event with an explicit test label, not rename or resubmit an ambiguous old event. Verify the actual scheduler/worker → event → sender → receipt path; a standalone bot call does not validate the background chain.
set_recipient.py.--message / --file sends retry transient errors up to 3 times. Guard-owned
automatic --outbox delivery makes exactly one HTTP attempt and requires the
guard-approved payload digest; a later run never sends a pre-existing payload.Connection closed or timeoutInspect the configured route without printing proxy credentials. Follow the host's approved direct/proxy policy and diagnose the failing connection on that route. Do not silently clear proxies, try another endpoint, or replay an ambiguous send.
Check the response body: HTTP 200 with nonzero errcode is failure. errcode=0 means API acceptance, not recipient receipt. Verify the intended group and message where receipt matters. A direct bot test cannot validate an SLS/other scheduler: exercise and inspect that native path separately within the authorized test count.
Run the setup step again. The script expects ~/.config/setup-notifications-via-wecom/config.json with a webhook_url field.
references/message_best_practices.md — condensed checklist distilled from this session's corrections.references/sls-recurring-notifications.md — read for SLS-backed recurring reports: result-size limits, evaluation dates, existing-owner reuse and native delivery acceptance.scripts/send_wecom.py — the sender script.scripts/set_recipient.py — atomically records self versus others plus the canonical sender path/digest without printing the webhook.© daymade, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 7 other files (scripts, references) in setup-notifications-via-wecom of daymade/claude-code-skills.
Open the folder on GitHubat commit 872127b
Setup Notifications Via Wecom next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Setup Notifications Via Wecom this skilldaymade/claude-code-skills | 1.4k | — | ~3.1k | Automated safety check: Pass | MIT | |
| PR Review Provideryansongda/pay | 5.4k | — | ~2.4k | Automated safety check: Pass | MIT | |
| AI Model NodejsTencentCloudBase/CloudBase-AI-Toolkit | 1.1k | 2 repos | ~5k | Automated safety check: Pass | MIT | |
| X Twitter ScraperXquik-dev/x-twitter-scraper | 210 | 1 repos | ~2.6k | Automated safety check: Pass | MIT | |
| Integrate Whatsappgokapso/agent-skills | 177 | — | ~4.8k | Automated safety check: Pass | None | |
| Paper Feishu Digestchtc66/academic-skills | 360 | — | ~348 | Automated safety check: Pass | MIT |
yansongda/pay
A skill your agent uses when reviewing PRs that add or modify a payment Provider in yansongda/pay - covers plugin pipeline, multi-tenant safety, signature verification, docs, and naming conventions.
TencentCloudBase/CloudBase-AI-Toolkit
A skill your agent uses for Node.js backend AI via @cloudbase/node-sdk (=3.16.0) — cloud functions, CloudRun, Express/Koa/NestJS, serverless APIs, scheduled jobs, LLM proxies, agent orchestration.
Xquik-dev/x-twitter-scraper
Use Xquik to fetch X (Twitter) data or act through a connected account: search, profiles, followers, replies, threads, timelines, media downloads, bulk exports, trends, monitors, signed webhooks…
gokapso/agent-skills
Connect WhatsApp to your product with Kapso: onboard customers with setup links, detect connections, receive events via webhooks, and send messages/templates/media.
chtc66/academic-skills
monitor recent arxiv papers and produce a chinese digest when the user needs a filtered paper watchlist, a ranked update for agent or rag related topics, or an optional feishu webhook push from…
LiangNiang/OpenMantis
企业微信 飞书 钉钉 淘宝 小红书 抖音电商 微信小程序 微信小店 拼多多 有赞 微信支付 支付宝 京东 SHEIN 得物 火山引擎 阿里云百炼 泛微 北森 API文档搜索。
daymade/claude-code-skills
This skill should be used when comparing two videos to analyze compression results or quality differences.
daymade/claude-code-skills
Generates professional animated CLI demos as GIFs using VHS terminal recordings.
daymade/claude-code-skills
Converts DOCX/PDF/PPTX and saved HTML/HTM to high-quality Markdown with automatic post-processing.
daymade/claude-code-skills
Generates several distinct, clickable HTML interaction prototypes for one product surface into a Design Board and collects selection/remix feedback before implementation.
daymade/claude-code-skills
Diagnoses and repairs repository setup and guarded Git workflows for Claude Code or Codex — environment repair, startup sync, hook auditing, collaborator handoff.
daymade/claude-code-skills
Pulls Bigdata.com (RavenPack) financial and news data via the official bigdata-client SDK and /v1/ REST endpoints — structured financials, prices, analyst estimates, entity-sentiment series…
Works with
Categories
Set up and send technical status notifications through WeCom (Enterprise WeChat) webhooks. Setup Notifications Via Wecom is an agent skill from daymade/claude-code-skills. Set up and send technical status notifications through WeCom (Enterprise WeChat) webhooks.
Setup Notifications Via Wecom fits situations like: the user needs to send notifications; backup completion reports; status updates via WeCom; they mention 企业微信.
Run `npx skills add daymade/claude-code-skills --skill setup-notifications-via-wecom -a claude-code`. Or copy the skill folder (setup-notifications-via-wecom in daymade/claude-code-skills) into .claude/skills/setup-notifications-via-wecom in your project. Claude Code loads it when a task matches its description.
Run `npx skills add daymade/claude-code-skills --skill setup-notifications-via-wecom -a codex`. Or copy the skill folder (setup-notifications-via-wecom in daymade/claude-code-skills) into .agents/skills/setup-notifications-via-wecom in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add daymade/claude-code-skills --skill setup-notifications-via-wecom -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/setup-notifications-via-wecom, .gemini/skills/setup-notifications-via-wecom, .github/skills/setup-notifications-via-wecom and .opencode/skills/setup-notifications-via-wecom in your project.
Going by SKILL.md and its folder, Setup Notifications Via Wecom needs Python for the scripts in its folder and the command-line tools its instructions call (uv, claude and curl). Our summary lists: Python 3; A credential in YOUR_KEY.
SKILL.md names 1 domain. In commands or code: qyapi.weixin.qq.com; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
Setup Notifications Via Wecom is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 3.1k tokens (SKILL.md is roughly 12k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 2.9k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Setup Notifications Via Wecom: PR Review Provider (yansongda/pay, 5.4k stars), AI Model Nodejs (TencentCloudBase/CloudBase-AI-Toolkit, 1.1k stars), X Twitter Scraper (Xquik-dev/x-twitter-scraper, 210 stars) and Integrate Whatsapp (gokapso/agent-skills, 177 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
daymade (a GitHub user) maintains it in daymade/claude-code-skills, which has 1,447 GitHub stars. The repository holds 103 skills in this directory. The repository was last updated on October 9, 2026.
Source: daymade/claude-code-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.