MCP Server Builder
anthropics/skills
Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.
Transforms vague prompts into optimized Claude Code prompts.
$ npx skills add MoizIbnYousaf/ai-agent-skills --skill best-practices -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install MoizIbnYousaf/ai-agent-skills best-practices --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/MoizIbnYousaf/ai-agent-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/best-practices .claude/skills/best-practices && 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 "best-practices" agent skill from https://github.com/MoizIbnYousaf/ai-agent-skills/tree/main/skills/best-practices into .claude/skills/best-practices/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "best-practices", 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/MoizIbnYousaf/ai-agent-skills/tree/main/skills/best-practicesType 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 MoizIbnYousaf/ai-agent-skills --skill best-practices -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install MoizIbnYousaf/ai-agent-skills best-practices --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/MoizIbnYousaf/ai-agent-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/best-practices .agents/skills/best-practices && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "best-practices" agent skill from https://github.com/MoizIbnYousaf/ai-agent-skills/tree/main/skills/best-practices into .agents/skills/best-practices/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "best-practices", 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 MoizIbnYousaf/ai-agent-skills --skill best-practices -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install MoizIbnYousaf/ai-agent-skills best-practices --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/MoizIbnYousaf/ai-agent-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/best-practices .cursor/skills/best-practices && 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 "best-practices" agent skill from https://github.com/MoizIbnYousaf/ai-agent-skills/tree/main/skills/best-practices into .cursor/skills/best-practices/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "best-practices", 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/MoizIbnYousaf/ai-agent-skills.git --path skills/best-practices--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 MoizIbnYousaf/ai-agent-skills --skill best-practices -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install MoizIbnYousaf/ai-agent-skills best-practices --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/MoizIbnYousaf/ai-agent-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/best-practices .gemini/skills/best-practices && 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 "best-practices" agent skill from https://github.com/MoizIbnYousaf/ai-agent-skills/tree/main/skills/best-practices into .gemini/skills/best-practices/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "best-practices", 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 MoizIbnYousaf/ai-agent-skills best-practicesInstalls 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 MoizIbnYousaf/ai-agent-skills --skill best-practices -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/MoizIbnYousaf/ai-agent-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/best-practices .github/skills/best-practices && 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 "best-practices" agent skill from https://github.com/MoizIbnYousaf/ai-agent-skills/tree/main/skills/best-practices into .github/skills/best-practices/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "best-practices", 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 MoizIbnYousaf/ai-agent-skills --skill best-practices -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install MoizIbnYousaf/ai-agent-skills best-practices --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/MoizIbnYousaf/ai-agent-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/best-practices .opencode/skills/best-practices && 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 "best-practices" agent skill from https://github.com/MoizIbnYousaf/ai-agent-skills/tree/main/skills/best-practices into .opencode/skills/best-practices/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "best-practices", 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.
best-practicesTransforms vague prompts into optimized Claude Code prompts.
Best Practices is an agent skill from MoizIbnYousaf/ai-agent-skills. Transforms vague prompts into optimized Claude Code prompts. Adds verification, specific context, constraints, and proper phasing. Invoke with /best-practices.
Its SKILL.md is about 4.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 10 other files, including reference files (for example `agents/best-practices-referencer.md`, `agents/codebase-context-builder.md` and `agents/task-intent-analyzer.md`).
It sits in Agent Workflows. The repository describes itself as: Universal skill installer and package manager for AI coding agents. One command, 12+ runtimes. npx ai-agent-skills. The licence is MIT.
5 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit 6d95c78. 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.
Shell commands in SKILL.md call:
claudeFrom the folder's file list and the shell code blocks in SKILL.md.
Links to these hosts (documentation or services it may open):
code.claude.comdocs.anthropic.comgithub.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.
Best Practices loads about 4.2k tokens when it runs, and up to ~29k if it reads all its reference files. Until then it costs about 44 tokens; SKILL.md has 1,200 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); files beside SKILL.md are not scanned.
The full file from MoizIbnYousaf/ai-agent-skills at commit 6d95c78, republished under its MIT licence (© MoizIbnYousaf). 1,200 words, ~4,206 tokens.
.claude/skills/best-practices/SKILL.md (or your agent's skills folder). This skill also uses 8 other files; get the full folder from GitHub.Transform prompts by adding what Claude needs to succeed.
Based on user's request:
User provides a prompt to transform: → Ask using AskUserQuestion:
User asks to learn/understand: → Show the 5 Transformation Principles section
User asks for examples: → Link to references/before-after-examples.md
User asks to evaluate a prompt: → Use the Success Criteria eval rubric at the end of this document
Apply the 5 principles below and output the improved prompt immediately.
Launch 3 parallel agents to gather context:
Run these agents IN PARALLEL using the Task tool:
- Task task-intent-analyzer("[user's prompt]")
- Task best-practices-referencer("[user's prompt]")
- Task codebase-context-builder("[user's prompt]")| Agent | Mission | Returns |
|---|---|---|
| task-intent-analyzer | Understand what user is trying to do | Task type, gaps, edge cases, transformation guidance |
| best-practices-referencer | Find relevant patterns from references/ | Matching examples, anti-patterns to avoid, transformation rules |
| codebase-context-builder | Explore THIS codebase | Specific file paths, similar implementations, conventions |
The agents are defined in agents/:
agents/task-intent-analyzer.md — Analyzes intent, gaps, and edge casesagents/best-practices-referencer.md — Finds relevant examples and patterns from references/agents/codebase-context-builder.md — Explores codebase for files and conventionsWhen transforming (after mode selection):
Apply these in order of priority:
The single highest-leverage improvement. Claude performs dramatically better when it can verify its own work.
| Missing | Add |
|---|---|
| No success criteria | Test cases with expected inputs/outputs |
| UI changes | "take screenshot and compare to design" |
| Bug fixes | "write a failing test, then fix it" |
| Build issues | "verify the build succeeds after fixing" |
| Refactoring | "run the test suite after each change" |
| No root cause enforcement | "address root cause, don't suppress error" |
| No verification report | "summarize what you ran and what passed" |
BEFORE: "implement email validation"
AFTER: "write a validateEmail function. test cases: user@example.com → true,
invalid → false, user@.com → false. run the tests after implementing"BEFORE: "fix the API error"
AFTER: "the /api/orders endpoint returns 500 for large orders. check
OrderService.ts for the error. address the root cause, don't suppress
the error. after fixing, run the test suite and summarize what passed
and what you verified."Replace vague references with precise locations and details.
| Vague | Specific |
|---|---|
| "the code" | src/auth/login.ts |
| "the bug" | "users report X happens when Y" |
| "the API" | "the /api/users endpoint in routes.ts" |
| "that function" | processPayment() on line 142 |
Four ways to add context:
| Strategy | Example |
|---|---|
| Scope the task | "write a test for foo.py covering the edge case where user is logged out. avoid mocks." |
| Point to sources | "look through ExecutionFactory's git history and summarize how its API evolved" |
| Reference patterns | "look at HotDogWidget.php and follow that pattern for the calendar widget" |
| Describe symptoms | "users report login fails after session timeout. check src/auth/, especially token refresh" |
Respect Project CLAUDE.md:
If the project has a CLAUDE.md, the transformed prompt should:
BEFORE: "add a new API endpoint"
AFTER: "add a GET /api/products endpoint. check CLAUDE.md for API conventions
in this project. follow the pattern in routes/users.ts. run the API
tests after implementing."BEFORE: "fix the login bug"
AFTER: "users report login fails after session timeout. check the auth flow
in src/auth/, especially token refresh. write a failing test that
reproduces the issue, then fix it"Tell Claude what NOT to do. Prevents over-engineering and unwanted changes.
| Constraint Type | Examples |
|---|---|
| Dependencies | "no new libraries", "only use existing deps" |
| Testing | "avoid mocks", "use real database in tests" |
| Scope | "don't refactor unrelated code", "only touch auth module" |
| Approach | "address root cause, don't suppress error", "keep backward compat" |
| Patterns | "follow existing codebase conventions", "match the style in utils.ts" |
BEFORE: "add a calendar widget"
AFTER: "implement a calendar widget with month selection and year pagination.
follow the pattern in HotDogWidget.php. build from scratch without
libraries other than the ones already used in the codebase"For larger tasks, separate exploration from implementation.
The 4-Phase Pattern:
Phase 1: EXPLORE
"read src/auth/ and understand how we handle sessions and login.
also look at how we manage environment variables for secrets."
Phase 2: PLAN
"I want to add Google OAuth. What files need to change?
What's the session flow? Create a plan."
Phase 3: IMPLEMENT
"implement the OAuth flow from your plan. write tests for the
callback handler, run the test suite and fix any failures."
Phase 4: COMMIT
"commit with a descriptive message and open a PR"When to use phases:
Skip phases when:
BEFORE: "add OAuth"
AFTER: "read src/auth/ and understand current session handling. create a plan
for adding OAuth. then implement following the plan. write tests and
verify they pass"Provide supporting materials that Claude can use directly.
| Content Type | How to Provide |
|---|---|
| Files | Use @filename to reference files |
| Images | Paste screenshots directly |
| Errors | Paste actual error messages, not descriptions |
| Logs | Pipe with cat error.log | claude |
| URLs | Link to relevant documentation |
BEFORE: "make the dashboard look better"
AFTER: "[paste screenshot] implement this design for the dashboard.
take a screenshot of the result and compare it to the original.
list any differences and fix them. ensure responsive behavior
at 768px and 1024px breakpoints"BEFORE: "the build is failing"
AFTER: "the build fails with this error: [paste actual error]. fix it
and verify the build succeeds. address the root cause, don't
suppress the error"When transforming a prompt, output:
**Original:** [their prompt]
**Improved:**[transformed prompt in code block]
**Added:**
- [what was missing and added]
- [another improvement]
- [etc.]BEFORE: "fix the login bug"
AFTER: "users report login fails after session timeout. check the auth flow
in src/auth/, especially token refresh. write a failing test that reproduces
the issue, then fix it. verify by running the auth test suite."
ADDED: symptom, location, verification (failing test), success criteriaBEFORE: "add a search feature"
AFTER: "implement search for the products page. look at how filtering works
in ProductList.tsx for the pattern. search should filter by name and category.
add tests for: empty query returns all, partial match works, no results shows
message. no external search libraries."
ADDED: location, reference pattern, specific behavior, test cases, constraintBEFORE: "make the code better"
AFTER: "refactor utils.js to use ES2024 features while maintaining the same
behavior. specifically: convert callbacks to async/await, use optional
chaining, add proper TypeScript types. run the existing test suite after
each change to ensure nothing breaks."
ADDED: specific changes, constraint (same behavior), verification after each stepBEFORE: "add tests for foo.py"
AFTER: "write tests for foo.py covering the edge case where the user is
logged out. avoid mocks. use the existing test patterns in tests/. test
cases: logged_out_user returns 401, expired_session redirects to login,
invalid_token raises AuthError."
ADDED: specific edge case, constraint (no mocks), pattern reference, test casesBEFORE: "the API is slow"
AFTER: "the /api/orders endpoint takes 3+ seconds. profile the database
queries in OrderService.ts. look for N+1 queries or missing indexes.
fix the performance issue and verify response time is under 500ms."
ADDED: specific endpoint, location, what to look for, measurable success criteriaBEFORE: "fix the button styling"
AFTER: "[paste screenshot of design] update the primary button to match this
design. check Button.tsx and the theme in tailwind.config.js. take a
screenshot after changes and compare to the design. list any differences."
ADDED: design reference, file locations, visual verificationBEFORE: "how does auth work?"
AFTER: "read src/auth/ and explain how authentication works in this codebase.
cover: how sessions are created, how tokens are refreshed, where secrets
are stored. summarize in a markdown doc."
ADDED: specific files, specific questions to answer, output formatBEFORE: "upgrade to React 18"
AFTER: "migrate from React 17 to React 18. first, read the migration guide
at [URL]. then identify all components using deprecated APIs. update one
component at a time, running tests after each. don't change unrelated code."
ADDED: phased approach, reference docs, incremental verification, scope constraintBEFORE: "fix the API error"
AFTER: "the /api/orders endpoint returns 500 for large orders. check
OrderService.ts for the error. address the root cause, don't suppress
the error. after fixing, run the test suite and summarize what passed
and what you verified."
ADDED: symptom, location, root cause enforcement, verification reportBefore outputting, verify the improved prompt has:
Rate the prompt against these dimensions:
| Dimension | 0 (Missing) | 1 (Partial) | 2 (Complete) |
|---|---|---|---|
| Verification | None | "test it" | Specific test cases + report |
| Location | "the code" | "auth module" | src/auth/login.ts:42 |
| Constraints | None | Implied | "avoid X, no Y, root cause only" |
| Scope | Vague | Partial | Single clear task |
Quick assessment:
If user chose "Transform directly" but the prompt lacks enough context, ask one natural question:
"What would Claude need to know to do this well?"
Don't interrogate — one question is enough. Transform with what you learn.
| Anti-Pattern | Problem | Fix |
|---|---|---|
| "fix the bug" | No symptom, no location | Add what users report + where to look |
| "add tests" | No scope, no cases | Specify edge cases + test patterns |
| "make it better" | No criteria for "better" | Define specific improvements |
| "implement X" | No verification | Add test cases or success criteria |
| "update the code" | No constraints | Add what to preserve, what to avoid |
A well-transformed prompt passes these checks:
| Check | Pass | Fail |
|---|---|---|
| Has success criteria | "run tests", "screenshot matches" | Nothing |
| Measurable outcome | "response < 500ms" | "make it faster" |
| Self-verifiable | Claude can check its own work | Requires human judgment |
| Root cause enforced | "don't suppress error" | Silent about approach |
| Check | Pass | Fail |
|---|---|---|
| File locations | src/auth/login.ts | "the auth code" |
| Function/class names | processPayment() | "that function" |
| Line numbers (if relevant) | :42 | "somewhere in there" |
| CLAUDE.md respected | "check project conventions" | Ignores project rules |
| Check | Pass | Fail |
|---|---|---|
| What NOT to do | "avoid mocks", "no new deps" | Open-ended |
| Scope boundaries | "only touch auth module" | Unlimited scope |
| Pattern to follow | "match UserService.ts style" | No reference |
| Check | Pass | Fail |
|---|---|---|
| Single task | One clear objective | Multiple goals |
| Phased (if complex) | "explore → plan → implement" | Jump straight to code |
| Appropriate depth | Matches task complexity | Over/under-specified |
| Check | Pass | Fail |
|---|---|---|
| Actual errors | Pasted error message | "it's broken" |
| Screenshots (UI) | Image attached | "the button looks wrong" |
| File references | @filename or path | "that file" |
| Score | Meaning | Principles Passed |
|---|---|---|
| ⭐⭐⭐⭐⭐ | Excellent | All 5 |
| ⭐⭐⭐⭐ | Good | 4 of 5 |
| ⭐⭐⭐ | Acceptable | 3 of 5 |
| ⭐⭐ | Needs work | 2 of 5 |
| ⭐ | Poor | 1 or 0 |
Target: Every transformed prompt should score ⭐⭐⭐⭐ or ⭐⭐⭐⭐⭐
For more examples and patterns:
© MoizIbnYousaf, 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 8 other files (references) in skills/best-practices of MoizIbnYousaf/ai-agent-skills.
Open the folder on GitHubat commit 6d95c78
Best Practices 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 |
|---|---|---|---|---|---|---|
| Best Practices this skillMoizIbnYousaf/ai-agent-skills | 1.1k | — | ~4.2k | Automated safety check: Pass | MIT | |
| MCP Server Builderanthropics/skills | 180k | 63 repos | ~2.3k | Automated safety check: Pass | Apache-2.0 | |
| Hook Development for Claude Code Pluginsanthropics/claude-plugins-official | 38k | 10 repos | ~4.1k | Automated safety check: Notes | Apache-2.0 | |
| Using Superpowersfarm-fe/farm | 5.6k | 35 repos | ~1.4k | Automated safety check: Pass | MIT | |
| Executing Plans Inlineobra/superpowers | 297k | 2 repos | ~5.1k | Automated safety check: Pass | MIT | |
| Skill CreatorAzure/azqr | 795 | 89 repos | ~8.2k | Automated safety check: Pass | Apache-2.0 |
anthropics/skills
Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.
anthropics/claude-plugins-official
Explains how to write Claude Code plugin hooks, both prompt-based checks and bash commands, for events such as PreToolUse, Stop and SessionStart.
farm-fe/farm
A skill your agent uses when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions
obra/superpowers
Has the agent carry out an implementation plan itself, task by task in the current session, keeping a ledger, proving each step with a test and ending with one whole-branch review.
Azure/azqr
Create new skills, modify and improve existing skills, and measure skill performance.
anthropics/claude-plugins-official
Explains how to write agents for Claude Code plugins: the markdown file with YAML frontmatter, trigger descriptions, model and color settings, and system prompt design.
MoizIbnYousaf/ai-agent-skills
Database schema design, optimization, and migration patterns for PostgreSQL, MySQL, and NoSQL databases.
MoizIbnYousaf/ai-agent-skills
Building applications with Large Language Models - prompt engineering, RAG patterns, and LLM integration.
MoizIbnYousaf/ai-agent-skills
A skill your agent uses when checking the overall health of a skills library.
MoizIbnYousaf/ai-agent-skills
Backend API design, database architecture, microservices patterns, and test-driven development.
MoizIbnYousaf/ai-agent-skills
A skill your agent uses when exploring the ai-agent-skills catalog to find, compare, and evaluate skills before installing.
MoizIbnYousaf/ai-agent-skills
Writing effective code documentation - API docs, README files, inline comments, and technical guides.
Categories
Transforms vague prompts into optimized Claude Code prompts. Best Practices is an agent skill from MoizIbnYousaf/ai-agent-skills. Transforms vague prompts into optimized Claude Code prompts.
Best Practices fits situations like: agent Workflows work in your project.
Run `npx skills add MoizIbnYousaf/ai-agent-skills --skill best-practices -a claude-code`. Or copy the skill folder (skills/best-practices in MoizIbnYousaf/ai-agent-skills) into .claude/skills/best-practices in your project. Claude Code loads it when a task matches its description.
Run `npx skills add MoizIbnYousaf/ai-agent-skills --skill best-practices -a codex`. Or copy the skill folder (skills/best-practices in MoizIbnYousaf/ai-agent-skills) into .agents/skills/best-practices 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 MoizIbnYousaf/ai-agent-skills --skill best-practices -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/best-practices, .gemini/skills/best-practices, .github/skills/best-practices and .opencode/skills/best-practices in your project.
Going by SKILL.md and its folder, Best Practices needs the command-line tools its instructions call (claude).
SKILL.md names 3 domains. As links in the text: code.claude.com, docs.anthropic.com and github.com. 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. Review the folder before installing.
Best Practices is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 4.2k tokens (SKILL.md is roughly 17k 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 25k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Best Practices: MCP Server Builder (anthropics/skills, 180k stars), Hook Development for Claude Code Plugins (anthropics/claude-plugins-official, 38k stars), Using Superpowers (farm-fe/farm, 5.6k stars) and Executing Plans Inline (obra/superpowers, 297k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
MoizIbnYousaf (a GitHub user) maintains it in MoizIbnYousaf/ai-agent-skills, which has 1,149 GitHub stars. The repository holds 15 skills in this directory. The repository was last updated on September 21, 2026.
Source: MoizIbnYousaf/ai-agent-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.