Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
etetoolkit
Phylogenetic tree toolkit (ETE). Tree manipulation (Newick/NHX), evolutionary event detection, orthology/paralogy, NCBI taxonomy, visualization (PDF/SVG), for phylogenomics.
majiayu000/claude-skill-registry 163
-
competitive-landscape
This skill should be used when the user asks to "analyze competitors", "assess competitive landscape", "identify differentiation", "evaluate market positioning", "apply Porter's Five Forces", or requests competitive strategy analysis.
majiayu000/claude-skill-registry 163
-
ui-guidelines
UIコンポーネントを新規作成・編集する際に使用。Emotion styled/テーマトークン/Atomic Designのルールを確認。
majiayu000/claude-skill-registry 163
-
orcaflex-post-processing
Post-process OrcaFlex simulation results using OPP (OrcaFlex Post-Process). Use for extracting summary statistics, linked statistics, range graphs, time series, histograms, and generating interactive HTML reports from .sim files.
majiayu000/claude-skill-registry 163
-
analyze-ci
Analyze failed GitHub Action jobs for a pull request.
majiayu000/claude-skill-registry 163
-
ln-629-lifecycle-auditor
Application lifecycle audit worker (L3). Checks bootstrap initialization order, graceful shutdown, resource cleanup, signal handling, liveness/readiness probes. Returns findings with severity, location, effort, recommendations.
majiayu000/claude-skill-registry 163
-
api-request-validation
A skill for implementing robust API request validation in Python web frameworks like FastAPI using Pydantic. Covers Pydantic models, custom validators (email, password), field-level and cross-field validation, query/file validation, and structured error responses. Use when you need to validate incoming API requests.
majiayu000/claude-skill-registry 163
-
nx-workspace-patterns
Configure and optimize Nx monorepo workspaces. Use when setting up Nx, configuring project boundaries, optimizing build caching, or implementing affected commands.
majiayu000/claude-skill-registry 163
-
benchmark-datasets
Standard datasets and benchmarks for evaluating AI security, robustness, and safety
majiayu000/claude-skill-registry 163
-
learner
Extract a learned skill from the current conversation
majiayu000/claude-skill-registry 163
-
walk-the-store-quality-review
A multidisciplinary process to operationalize product quality by experiencing critical user journeys first-hand, logging friction, and calibrating standards across leadership. Use this when product quality is regressing over time, when teams are too siloed in feature-level thinking, or as part of a quarterly planning cycle.
majiayu000/claude-skill-registry 163
-
database-migration-orchestrator
Plan zero-downtime migrations and rollback.
majiayu000/claude-skill-registry 163
-
gpui-patterns
GPUI framework patterns for Script Kit. Use when writing UI code, handling keyboard events, managing state, or working with layouts. Covers layout chains, lists, themes, events, focus, and window management.
majiayu000/claude-skill-registry 163
-
initialization
Use when starting a new session without feature-list.json, setting up project structure, or breaking down requirements into atomic features. Load in INIT state. Detects project type (Python/Node/Django/FastAPI), creates feature-list.json with priorities, initializes .claude/progress/ tracking.
majiayu000/claude-skill-registry 163
-
solve-challenge
Solve CTF challenges by analyzing files, connecting to services, and applying exploitation techniques. Orchestrates category-specific CTF skills.
majiayu000/claude-skill-registry 163
-
localization-engineer
Expert in internationalization (i18n), multi-language support, and localization
majiayu000/claude-skill-registry 163
-
gemini
Gemini CLI for one-shot Q&A, summaries, and generation.
majiayu000/claude-skill-registry 163
-
agent-invocation
Agent invocation syntax and boundary rules
majiayu000/claude-skill-registry 163
-
community-ops-playbook
majiayu000/claude-skill-registry 163
-
deduplication
Event deduplication with canonical selection, reputation scoring, and hash-based grouping for multi-source data aggregation. Handles both ID-based and content-based deduplication.
majiayu000/claude-skill-registry 163
-
multi-model-reviewer
協調多個 AI 模型（ChatGPT、Gemini、Codex、QWEN、Claude）進行三角驗證，確保「Specification == Program == Test」一致性。過濾假警報後輸出報告，大幅減少人工介入時間。
majiayu000/claude-skill-registry 163
-
task-handoff-writing
Write high-signal handoffs (`HANDOFF.md` or `docs/handoffs/<slug>.md`) with concrete validation evidence and actionable next steps.
majiayu000/claude-skill-registry 163
-
discover-database
Automatically discover database skills when working with SQL, PostgreSQL, MongoDB, Redis, database schema design, query optimization, migrations, connection pooling, ORMs, or database selection. Activates for database design, optimization, and implementation tasks.
majiayu000/claude-skill-registry 163
-
scientific-writing
Core skill for the deep research and writing tool. Write scientific manuscripts in full paragraphs (never bullet points). Use two-stage process with (1) section outlines with key points using research-lookup then (2) convert to flowing prose. IMRAD structure, citations (APA/AMA/Vancouver), figures/tables, reporting guidelines (CONSORT/STROBE/PRISMA), for research papers and journal submissions.
majiayu000/claude-skill-registry 163