agent-sh
Official@agent-sh
DX focused ecosystem for AI-powered research and development
Agent Skills by agent-sh
Showing 35 vetted skills indexed across 3 GitHub repositories.
agent-shvalidate-delivery
Validates task completion by running tests, builds, and requirement checks with pass/fail output.
agent-shorchestrate-review
Orchestrates multi-pass code review with parallel agents, finding aggregation, and fix iteration.
agent-shdiscover-tasks
Discovers, filters, scores, and ranks open tasks from GitHub, GitLab, and local files.
agent-shrepo-intel
Analyzes git history, AST symbols, and project metadata to generate repository intelligence maps.
agent-shaudit-project
Automates iterative code review and fix across multiple files with specialized agents.
agent-shmaintain-cross-platform
Coordinate cross-platform release checks and configuration alignment across Claude Code, OpenCoder, and Codex.
agent-shperf-benchmarker
Run sequential performance benchmarks with strict duration and warmup rules.
agent-shdeslop
Detect and remove AI-generated artifacts from codebases with structured JSON output.
agent-shperf-theory-tester
Run a controlled performance test comparing metrics against baseline data.
agent-shenhance-hooks
Automate safety and correctness reviews for Claude Code hook definitions and scripts.
agent-shperf-analyzer
Synthesize performance investigation results into structured, evidence-backed recommendations.
agent-shenhance-claude-memory
Analyze CLAUDE.md and AGENTS.md files to identify redundancy and propose memory-optimization edits.
agent-shenhance-skills
Analyze SKILL.md files and report quality issues with optional auto-fixes.
agent-shenhance-cross-file
Detect cross-file inconsistencies across prompts, frontmatter, agents, and workflows.
agent-shlearn
Generate structured learning guides with ranked online sources and study sections.
agent-shdebate
Orchestrate structured multi-round debates between AI tools with evidence-backed verdicts.
agent-shperf-baseline-manager
Store a single performance baseline JSON per version in a state directory.
agent-shrepo-mapping
Construct and maintain AST-based repository maps tracking symbols and imports.
agent-shdrift-analysis
Identify and summarize plan, documentation, issue, and scope drift in software projects.
agent-shenhance-agent-prompts
Analyze agent prompt files and output structured best-practice improvement reports.
agent-shsync-docs
Analyze changed files and docs to report documentation issues.
agent-shenhance-orchestrator
Coordinate parallel enhancement analyzers into a unified report with per-enhancer summaries.
agent-shenhance-docs
Analyze documentation structure and readability to produce retrieval-ready guidance.
agent-shweb-browse
Navigate URLs, click elements, fill forms, and capture screenshots via headless browser.
Frequently Asked Questions About agent-sh
FAQPage SchemaWhat specific tasks can I perform using these capabilities?▼
You can execute performance profiling, generate AST-based repository maps, perform drift analysis on project documentation, sanitize codebases of generated artifacts, and orchestrate multi-pass code reviews to ensure delivery readiness.
Which technical personas benefit most from these capabilities?▼
Software engineers, technical leads, and site reliability engineers benefit from these capabilities by gaining structured insights into codebase performance, documentation accuracy, and cross-file consistency across large-scale development projects.
What are the primary prerequisites for running these performance and analysis tasks?▼
These tasks require a local environment configured for repository access, standard git history availability for evidence gathering, and JFR or perf data sources for deep-dive performance profiling and flame graph generation.