Engineering Advanced Skills
alirezarezvani/claude-skills
Index of 37 advanced engineering agent skills for Claude Code, Codex, Gemini CLI, Cursor, OpenClaw.
Guidance for Valkey-specific behavior. An agent skill from valkey-io/valkey-admin.
Install Valkey
$ npx skills add valkey-io/valkey-admin --skill valkey -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install valkey-io/valkey-admin valkey --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/valkey-io/valkey-admin.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/valkey .claude/skills/valkey && 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 "valkey" agent skill from https://github.com/valkey-io/valkey-admin/tree/main/.agents/skills/valkey into .claude/skills/valkey/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "valkey", 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/valkey-io/valkey-admin/tree/main/.agents/skills/valkeyType 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 valkey-io/valkey-admin --skill valkey -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install valkey-io/valkey-admin valkey --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/valkey-io/valkey-admin.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/valkey .agents/skills/valkey && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "valkey" agent skill from https://github.com/valkey-io/valkey-admin/tree/main/.agents/skills/valkey into .agents/skills/valkey/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "valkey", 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 valkey-io/valkey-admin --skill valkey -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install valkey-io/valkey-admin valkey --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/valkey-io/valkey-admin.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/valkey .cursor/skills/valkey && 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 "valkey" agent skill from https://github.com/valkey-io/valkey-admin/tree/main/.agents/skills/valkey into .cursor/skills/valkey/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "valkey", 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/valkey-io/valkey-admin.git --path .agents/skills/valkey--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 valkey-io/valkey-admin --skill valkey -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install valkey-io/valkey-admin valkey --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/valkey-io/valkey-admin.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/valkey .gemini/skills/valkey && 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 "valkey" agent skill from https://github.com/valkey-io/valkey-admin/tree/main/.agents/skills/valkey into .gemini/skills/valkey/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "valkey", 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 valkey-io/valkey-admin valkeyInstalls 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 valkey-io/valkey-admin --skill valkey -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/valkey-io/valkey-admin.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/valkey .github/skills/valkey && 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 "valkey" agent skill from https://github.com/valkey-io/valkey-admin/tree/main/.agents/skills/valkey into .github/skills/valkey/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "valkey", 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 valkey-io/valkey-admin --skill valkey -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install valkey-io/valkey-admin valkey --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/valkey-io/valkey-admin.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/valkey .opencode/skills/valkey && 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 "valkey" agent skill from https://github.com/valkey-io/valkey-admin/tree/main/.agents/skills/valkey into .opencode/skills/valkey/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "valkey", 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.
Facts
- Skill name
valkey- GitHub stars
- 148
- Token cost
- ~635 tokens
- SKILL.md length
- 303 words
- Files
- 1
- Skills in repo
- 5
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Guidance for Valkey-specific behavior. An agent skill from valkey-io/valkey-admin.
- Changing Valkey connections
- SKILL.md covers Client Behavior, Data Domains, Cluster Handling and Errors And Logging, plus 1 more section
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
- Key browser behavior
What it does
Valkey is an agent skill from valkey-io/valkey-admin. Guidance for Valkey-specific behavior. Use when changing Valkey connections, commands, dashboard data, metrics, key browser behavior, monitoring, cluster routing, response normalization, or unsupported capability handling.
Its SKILL.md is about 640 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in DevOps & Cloud, covering Database schema design. The repository describes itself as: Valkey Admin is a web-based administration tool for Valkey clusters and standalone instances. It provides an intuitive interface to monitor, manage, and interact with your Valkey… The licence is Apache-2.0.
When your agent uses it
- Changing Valkey connections
- Key browser behavior
- Cluster routing
- Response normalization
Example prompts
- “/valkey”
What it can do on your machine
Read from SKILL.md and the folder at commit 64f5fb4. It shows what the files ask for, not the result of running them.
Tool permissions
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.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Valkey loads about 635 tokens when it runs. Until then it costs about 57 tokens; SKILL.md has 303 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.
Safety
Auto-check passed
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); files beside SKILL.md are not scanned.
SKILL.md
The full file from valkey-io/valkey-admin at commit 64f5fb4, republished under its Apache-2.0 licence (© valkey-io). 303 words, ~635 tokens.
Download SKILL.mdSave it as
.claude/skills/valkey/SKILL.md (or your agent's skills folder).- name
- valkey
- description
- Guidance for Valkey-specific behavior. Use when changing Valkey connections, commands, dashboard data, metrics, key browser behavior, monitoring, cluster routing, response normalization, or unsupported capability handling.
Valkey Skill
Use this skill when changing Valkey connection, command, dashboard, metrics, key-browser, monitoring, or cluster behavior.
Client Behavior
- Distinguish standalone and cluster clients. Cluster calls may return fanout records or routed single-node responses.
- Route explicitly when querying a specific cluster node.
- Normalize Valkey command responses at backend, middleware, or parser boundaries before frontend components consume them.
- Treat unsupported commands and unavailable server capabilities as expected errors when they can happen in real deployments.
- Keep raw Valkey transport details out of React components.
Data Domains
- Dashboard info, memory metrics, CPU metrics, key browser data, command output, hot keys, slow logs, large replies, large requests, and monitor output are separate domains.
- Do not reuse a response shape across domains just because the transport is the same.
- Shared parsing/formatting logic that is useful across apps belongs in
common/. - Preserve useful command semantics, but expose typed domain-shaped data to UI and selectors.
Cluster Handling
- Be careful with node IDs, cluster IDs, connection IDs, and sanitized host keys. Do not treat them as interchangeable.
- Prefer explicit route/address handling for per-node dashboard and metrics queries.
- Account for cluster endpoint discovery versus direct node connections.
- Avoid fanout surprises: check whether a Glide command returns a string, record keyed by address, or key/value rows.
Errors And Logging
- Return expected Valkey/domain errors as values where practical, then pattern-match at the UX/retry/logging boundary.
- Throw only for programmer errors, impossible states, startup/config failures, or framework-required exception flows.
- Never log passwords, IAM tokens, credentials, connection strings with secrets, or raw secure-storage payloads.
- Redact connection details in errors and debug logs.
Testing
- Add focused regression tests for parser changes, response normalization, cluster routing, and unsupported-command fallbacks.
- Mock both standalone and cluster response shapes when behavior depends on the client type.
- Test
undefinedandnullstates separately when Valkey data can be absent or explicitly null.
© valkey-io, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in .agents/skills/valkey of valkey-io/valkey-admin.
Open the folder on GitHubat commit 64f5fb4
Compare with similar skills
Valkey 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 |
|---|---|---|---|---|---|---|
| Valkey this skillvalkey-io/valkey-admin | 148 | — | ~635 | Automated safety check: Pass | Apache-2.0 | |
| Engineering Advanced Skillsalirezarezvani/claude-skills | 28k | — | ~1.1k | Automated safety check: Pass | MIT | |
| Service Remappingdatadog-labs/agent-skills | 177 | — | ~4.7k | Automated safety check: Pass | MIT | |
| Security Stancefjrevoredo/mini-diarium | 308 | — | ~11k | Automated safety check: Pass | MIT | |
| Test HTTP Intermediariescyberful/cyberful | 135 | — | ~630 | Automated safety check: Pass | AGPL-3.0 | |
| SQL Optimization Patternsynulihao/AgentSkillOS | 617 | 11 repos | ~3.3k | Automated safety check: Pass | None |
Similar skills
Service Remapping
datadog-labs/agent-skills
Create and manage APM service remapping rules — rewrite service names at ingestion time to collapse noisy inferred entities, clean up auto-generated names, handle org renames, or normalize naming…
Security Stance
fjrevoredo/mini-diarium
Mini Diarium's opinionated security, encryption, and privacy stance.
Test HTTP Intermediaries
cyberful/cyberful
Route HTTP intermediary testing across request normalization, web-cache behavior, and offline traffic evidence.
SQL Optimization Patterns
ynulihao/AgentSkillOS
Master SQL query optimization, indexing strategies, and EXPLAIN analysis to dramatically improve database performance and eliminate slow queries.
Add Mpk Task
mirage-project/mirage
Step-by-step guide for adding a new task implementation to Mirage Persistent Kernel (MPK).
More from valkey-io/valkey-admin
Ramda
valkey-io/valkey-admin
Guidance for using Ramda in transformation-heavy TypeScript or JavaScript.
React
valkey-io/valkey-admin
Guidance for React frontend work. An agent skill from valkey-io/valkey-admin.
Rx JS
valkey-io/valkey-admin
Guidance for Redux Toolkit and RxJS middleware patterns. An agent skill from valkey-io/valkey-admin.
Styling
valkey-io/valkey-admin
Guidance for frontend styling. An agent skill from valkey-io/valkey-admin.
Related
Categories
Questions about Valkey
What does Valkey do?
Guidance for Valkey-specific behavior. An agent skill from valkey-io/valkey-admin. Valkey is an agent skill from valkey-io/valkey-admin. Guidance for Valkey-specific behavior.
When should I use Valkey?
Valkey fits situations like: changing Valkey connections; key browser behavior; cluster routing; response normalization.
How do I install Valkey in Claude Code?
Run `npx skills add valkey-io/valkey-admin --skill valkey -a claude-code`. Or copy the skill folder (.agents/skills/valkey in valkey-io/valkey-admin) into .claude/skills/valkey in your project. Claude Code loads it when a task matches its description.
How do I install Valkey in Codex?
Run `npx skills add valkey-io/valkey-admin --skill valkey -a codex`. Or copy the skill folder (.agents/skills/valkey in valkey-io/valkey-admin) into .agents/skills/valkey in your project. Codex loads it when a task matches its description.
Can I use Valkey in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add valkey-io/valkey-admin --skill valkey -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/valkey, .gemini/skills/valkey, .github/skills/valkey and .opencode/skills/valkey in your project.
What does Valkey need to run?
SKILL.md names no scripts, command-line tools or credentials: Valkey is instructions for the agent only.
Does Valkey access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Valkey safe to install?
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. Review the folder before installing.
What licence does Valkey use?
Valkey is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Valkey use?
About 635 tokens (SKILL.md is roughly 2.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Valkey?
Skills that share tags, products or a category with Valkey: Engineering Advanced Skills (alirezarezvani/claude-skills, 28k stars), Service Remapping (datadog-labs/agent-skills, 177 stars), Security Stance (fjrevoredo/mini-diarium, 308 stars) and Test HTTP Intermediaries (cyberful/cyberful, 135 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Valkey?
valkey-io (a GitHub organization) maintains it in valkey-io/valkey-admin, which has 148 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on October 7, 2026.
Source: valkey-io/valkey-admin on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.