AxelMrak/ai
0 installs 5 GitHub stars
codex-review
Integrates Codex AI into professional code review workflows. Includes automatic changelog generation.
Community score
0
0 up0 down THE AGENT SKILLS DIRECTORY
Small skills.
Big possibilities.
Your agent can do more. Find the skill that makes it happen.
Find your next superpower If you are an agent, refer to our llms.txt for full access.Fast-rising skills.
bryanzk/MyCodexEnv
0 installs 0 GitHub stars
codex-runtime-capability-repair
Use when Codex tools or plugins appear installed but unavailable, including browser/computer-use/GitHub capability loss, missing MCP tools, plugin enablement drift, ~/.codex/config.toml rewrite issues, marketplace state loss, or MyCodexEnv sync automation regressions.
Community score
0
0 up0 downbryanzk/MyCodexEnv
0 installs 0 GitHub stars
codex-state-maintenance
Use when inspecting, pruning, archiving, or scheduling maintenance for local Codex state, session history, archived sessions, worktrees, logs, or GitHub-hosted maintenance skills.
Community score
0
0 up0 downx402agent/SolanaOS
0 installs 9 GitHub stars
coding-agent
Delegate coding tasks to Codex, Claude Code, or Pi agents via background process. Use when: (1) building/creating new features or apps, (2) reviewing PRs (spawn in temp dir), (3) refactoring large codebases, (4) iterative coding that needs file exploration. NOT for: simple one-liner fixes (just edit), reading code (use read tool), thread-bound ACP harness requests in chat (for example spawn/run Co…
Community score
0
0 up0 downShulkwiSEC/bb-huge
0 installs 23 GitHub stars
colang-gen
Generates NeMo Guardrails Colang (.co) files and YAML config blocks from a plain-language description of a chatbot's purpose, allowed behaviors, and constraints. Use this skill whenever a user wants to build guardrails for a chatbot, define allowed intents for an LLM, create an AI firewall with NeMo Guardrails, generate Colang flow definitions, or configure a semantic allow-list for a bot. Trigger…
Community score
0
0 up0 downmeltedinhex/analyst-ai-pack
0 installs 22 GitHub stars
collecting-volatile-evidence-from-a-suspect-host
Collects volatile evidence from a potentially compromised host in correct order of volatility: memory, network state, running processes, logged-on users, and open handles, while preserving integrity and minimizing footprint. Activates for requests to collect volatile evidence, perform live response, or capture host state before shutdown.
Community score
0
0 up0 downbryanzk/MyCodexEnv
0 installs 0 GitHub stars
colorize
Add strategic color to features that are too monochromatic or lack visual interest. Makes interfaces more engaging and expressive.
Community score
0
0 up0 downJPscript/mv3
0 installs 1 GitHub stars
comentador-css
Provides detailed explanations of CSS code tailored to beginners.
Community score
0
0 up0 downShulkwiSEC/bb-huge
0 installs 23 GitHub stars
command-injection-os-level
Identify and exploit OS Command Injection vulnerabilities where web applications insecurely pass user input into system shell commands. Use this skill when applications feature ping utilities, file conversions, network diagnostics, or PDF generators to execute arbitrary system commands and achieve Remote Code Execution (RCE).
Community score
0
0 up0 downrrcampbell-exe/real-fake-birds
0 installs 1 GitHub stars
commit
Generate semantic commit groups from changed files. Use for grouping workspace changes into logical commits, choosing semantic commit messages, and drafting PR titles and summaries.
Community score
0
0 up0 downnetanel-abergel/pa-skills
0 installs 6 GitHub stars
commitment-tracker
Reviews replies containing commitments such as sending updates, reporting results, or following up. Aims to prevent agents from promising actions without carrying them out.
Community score
0
0 up0 downbryanzk/MyCodexEnv
0 installs 0 GitHub stars
committee-review-loop
Use when a user explicitly asks for a committee or subagents to iteratively review, score, and revise an output until a calibrated target such as 10/10 is reached with evidence.
Community score
0
0 up0 downLESS SETUP. MORE POSSIBILITY.Find it. Add it.
Find it. Add it.
Make something.
Skills give your agent reusable instructions for a specific job. Pick one, read what it does, and bring it into your workflow.
Search the actual skill.
A name only tells half the story. Search the full description and instructions to find the right fit.
Get to know it.
Read the skill, visit its source, and see exactly what you’re adding to your agent.
Give your agent a new ability.
Copy the install command from a skill page and run it in your project.
npx skillycli add owner/repo --skill name