Back to categories
Category

Agent Skills in category: Uncategorized

72242 skills match this category. Browse curated collections and explore related Agent Skills.

smith-validation

Hypothesis testing, root cause analysis, and debugging techniques. Use when debugging, testing hypotheses, validating solutions, proving correctness, or performing root cause analysis on failures.

tianjianjiang
tianjianjiang
0

smith-xml

XML tag standards for AI prompts and documentation. Use when writing prompts, documentation, or AGENTS.md files. Covers approved tags for Claude, GPT-5, Gemini, and Harmony formats with markdown rendering rules.

tianjianjiang
tianjianjiang
0

debug_agent_traces

Debug props agent traces. Read LLM request/response history, parse tool calls, and "speak with dead" — resurrect a past agent conversation to ask follow-up questions about its decisions.

agentydragon
agentydragon
11

narrow_matchability

Propose narrowing of grader match_file_restriction for unrestricted TP/FP occurrences in a specimen. Produces verifiable, link-rich output that lets the user confirm each restriction is correct.

agentydragon
agentydragon
11

props_evaluator

Operate the live props cluster as evaluator — fetch credentials from k8s, call the API at props.allegedly.works, trigger critic/grader runs, and inspect results.

agentydragon
agentydragon
11

reverse_engineer

Systematic binary reverse engineering toolkit. Extract source code, understand functions, document protocols, compare versions. Uses strings, symbols, disassembly, and differential verification.

agentydragon
agentydragon
11

test_props

Manual live props deployment testing — sets up Podman infrastructure (postgres, registry, backend) and runs real agent containers. NOT for standard Bazel tests (use `bazel test //props/...` for those).

agentydragon
agentydragon
11

startup-hook-skill

Creating and developing startup hooks for Claude Code on the web. Use when the user wants to set up a repository for Claude Code on the web, create a SessionStart hook to ensure their project can run tests and linters during web sessions.

agentydragon
agentydragon
11

backtrace

Show the current task stack and context. Use when user says "bt", "backtrace", "stack", "where are we", or asks about current progress on a multi-step task.

agentydragon
agentydragon
11

branch_splitter

Split a large branch with many changes into independent, reviewable PRs. Use when preparing a messy development branch for code review, when asked to "split this into PRs", "make this reviewable", "break this up", or when a branch does too many unrelated things. Produces a DAG of branches/PRs that can be reviewed and merged independently.

agentydragon
agentydragon
11

forensic_surgeon

Deep forensic debugging that never stops until root cause is found or visibility limit is proven. Use when user wants to understand exactly why something is broken, not work around it. Activates on "why is this happening", "dig deeper", "don't work around it", "I want to understand", "find the root cause", "this seems suspicious", or when a problem suggests deeper breakage.

agentydragon
agentydragon
11

hetzner_vnc_screenshot

Take and view screenshots of Hetzner Cloud servers via WebSocket VNC console

agentydragon
agentydragon
11

proxmox_vm

Interact with Proxmox VMs - screenshots, keystrokes, network info (user)

agentydragon
agentydragon
11

session_logs

Discover and analyze Claude Code session logs from ~/.claude/projects, including finding the current session and extracting tool calls, user messages, and conversation history

agentydragon
agentydragon
11

superforecaster

Make well-calibrated probability estimates using superforecasting methodology. Use when user asks about probability, likelihood, chance, odds, "will X happen", "when will X happen", "how much will X cost", "what could go wrong", failure modes, risk assessment, forecasting, or any question involving uncertainty and estimation.

agentydragon
agentydragon
11

forensic-surgeon

Deep forensic debugging that never stops until root cause is found or visibility limit is proven. Use when user wants to understand exactly why something is broken, not work around it. Activates on "why is this happening", "dig deeper", "don't work around it", "I want to understand", "find the root cause", "this seems suspicious", or when a problem suggests deeper breakage.

agentydragon
agentydragon
11

hetzner-vnc-screenshot

Take and view screenshots of Hetzner Cloud servers via WebSocket VNC console

agentydragon
agentydragon
11

proxmox-vm

Interact with Proxmox VMs - screenshots, keystrokes, network info (user)

agentydragon
agentydragon
11

session-logs

Discover and analyze Claude Code session logs from ~/.claude/projects, including finding the current session and extracting tool calls, user messages, and conversation history

agentydragon
agentydragon
11

ui-skills

Opinionated constraints for building better interfaces with agents.

overstarry
overstarry
0

SEO Optimizer

Search Engine Optimization specialist for content strategy, technical SEO, keyword research, and ranking improvements. Use when optimizing website content, improving search rankings, conducting keyword analysis, or implementing SEO best practices. Expert in on-page SEO, meta tags, schema markup, and Core Web Vitals.

overstarry
overstarry
0

skill-writer

Guide users through creating Agent Skills for Claude Code. Use when the user wants to create, write, author, or design a new Skill, or needs help with SKILL.md files, frontmatter, or skill structure.

overstarry
overstarry
0

frontend-design

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.

overstarry
overstarry
0

agents-authoring

Use when creating or updating AGENTS.md files

rcdailey
rcdailey
0

csharp-coding

Use when writing or modifying C# code

rcdailey
rcdailey
0

exploring-github

>-

rcdailey
rcdailey
0

gh-api

Use when managing draft PRs, posting PR comments, or querying GitHub Discussions

rcdailey
rcdailey
0

gh-gist

Use when creating or updating GitHub gists for document sharing

rcdailey
rcdailey
0

gh-pr-review

Use when posting code review comments on pull requests via gh-review

rcdailey
rcdailey
0

git-hunks

>

rcdailey
rcdailey
0

skill-authoring

Use when creating or modifying SKILL.md files

rcdailey
rcdailey
0

subagent-authoring

Use when creating or modifying custom agent definitions

rcdailey
rcdailey
0

api-design

REST API design patterns for endpoints, responses, errors, and conventions

JustinFirsching
JustinFirsching
0

code-review

Systematic code review checklist for quality, correctness, and maintainability

JustinFirsching
JustinFirsching
0

go

Go idioms, error handling, and API patterns

JustinFirsching
JustinFirsching
0

project-structure

Project organization conventions for files, modules, and directory structure

JustinFirsching
JustinFirsching
0

python

Python coding conventions, type hints, and FastAPI patterns

JustinFirsching
JustinFirsching
0

security-check

Security audit patterns for identifying vulnerabilities and security issues

JustinFirsching
JustinFirsching
0

testing

Testing strategy, patterns, and best practices for unit, integration, and e2e tests

JustinFirsching
JustinFirsching
0

typescript

TypeScript and React/TSX coding conventions and patterns

JustinFirsching
JustinFirsching
0

api-endpoint-create

Standard procedure for creating robust API endpoints

cpa03
cpa03
0

ci-pipeline-update

Updates CI/CD pipelines for DevOps Engineer

cpa03
cpa03
0

code-review-checklist

Generates a code review checklist for the Code Reviewer agent

cpa03
cpa03
0

database-migration-create

Safely creates database migrations

cpa03
cpa03
0

dependency-audit

Audit npm dependencies for security vulnerabilities, outdated packages, and license compliance.

cpa03
cpa03
0

docs-update

Standard procedure for updating documentation

cpa03
cpa03
0

git-commit-standard

Generates conventional commits based on file changes. Analyzes diffs and creates properly formatted commit messages.

cpa03
cpa03
0

madappgang-claude-code-debugging-strategies

Universal debugging strategies and techniques applicable across all technology stacks. Use when approaching unknown bugs or need language-agnostic debugging methodology.

cpa03
cpa03
0

maxritter-claude-codepro-backend-models-standards

Backend development standards and best practices for API design, database, security, and performance. Use when designing or reviewing backend systems.

cpa03
cpa03
0

modu-ai-moai-adk-moai-tool-opencode

Multi-agent orchestration using MoAI framework for complex task coordination. Use when orchestrating multiple agents or building multi-agent workflows.

cpa03
cpa03
0

Page 1151 of 1445 · 72242 results