发现 Skills

Deployment/Service/ConfigMap/Secret patterns, Horizontal Pod Autoscaler, Ingress configuration, Health probes (liveness/readiness/startup), Resource requests and limits, Helm chart basics, Kustomize overlays, Rolling updates

Systematic technical debt reduction and code optimization agent. Use when refactoring code, reducing complexity, eliminating code smells, improving performance, cleaning up unused code, or modernizing legacy patterns. Handles dependency updates, architecture improvements, and codebase health metrics.

Provides patterns for unit testing external REST APIs using WireMock to mock HTTP endpoints. Use when testing service integrations with external APIs.

Delegate to the GPT Code Reviewer expert to perform code reviews. Triggers: "code review", "review this code", "find issues", "what's wrong with" Use cases: (1) PR/MR review, (2) self-review after implementation, (3) bug detection, (4) code with security concerns

Fetch meetings, transcripts, summaries, and action items from the Fathom API. Use when a user asks to retrieve Fathom recordings, sync meeting transcripts, or fetch recent calls.

Execute a Flow epic or task systematically with git setup, task tracking, quality checks, and commit workflow. Use when implementing a plan or working through a spec. Triggers on /flow-next:work with Flow IDs (fn-1, fn-1.2).

Manage .flow/ tasks and epics. Triggers: 'show me my tasks', 'list epics', 'what tasks are there', 'add a task', 'create task', 'what's ready', 'task status', 'show fn-1-add-oauth'. NOT for /flow-next:plan or /flow-next:work.

Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.

Explains code in simple terms with visual diagrams. Use when the user asks for a code explanation, wants to understand how something works, or requests a code walkthrough.

Manages GenAI tuning jobs in Agent Platform. Use this to list, get, or cancel ongoing model tuning jobs. Don't use for fine-tuning models (use `agent-platform-tuning`), deploying models to endpoints (use `agent-platform-deploy`), or managing serving endpoints (use `agent-platform-endpoint-management`).

Reverse-engineer “image-format PPT documents / slide screenshots / any image page” back into an editable .pptx. Enforced four-layer pipeline: replicate the background image + chroma-key (green-screen) extraction of the overall frame (skeleton) + chroma-key extraction of element icons/decorations + GPT visual text extraction, then compose. The text becomes real editable text boxes, and frame images/icons become movable images; frames are split into sub-parts only when the user explicitly requests it. Use when the user wants to “convert PPT images/screenshots into editable PPTX, restore image-based PPT to editable PPT, extract icons, replicate background, extract text, or restore layout.” Input: images. Output: an editable .pptx.

Use when the task involves reading, creating, or editing `.docx` documents, especially when formatting or layout fidelity matters; prefer `python-docx` plus the bundled `scripts/render_docx.py` for visual checks.

Intelligently triage bug reports and error messages by searching for duplicates in Jira and offering to create new issues or add comments to existing ones. When Claude needs to: (1) Triage a bug report or error message, (2) Check if an issue is a duplicate, (3) Find similar past issues, (4) Create a new bug ticket with proper context, or (5) Add information to an existing ticket. Searches Jira for similar issues, identifies duplicates, checks fix history, and helps create well-structured bug reports.

Validate organized eBFE/BLE model using ras-commander dataframes. Uses init_ras_project() then checks plan_df, boundary_df, rasmap_df to verify: - All plan files exist - All DSS files exist with relative paths - All terrain files exist with relative paths - All HDF results accessible - No absolute paths (would cause GUI popups) Use after organizing eBFE model to verify it's actually runnable. Generates validation report and script for user re-verification.

Detect antimicrobial resistance genes using AMRFinderPlus, ResFinder, and CARD. Screen isolates and metagenomes for resistance determinants. Use when characterizing resistance profiles in clinical isolates, surveillance samples, or metagenomic data.

Installs 425 bioinformatics skills covering sequence analysis, RNA-seq, single-cell, variant calling, metagenomics, structural biology, and 56 more categories. Use when setting up bioinformatics capabilities or when a bioinformatics task requires specialized skills not yet installed.

Cell segmentation from multiplexed tissue images. Covers deep learning (Cellpose, Mesmer) and classical approaches for nuclear and whole-cell segmentation. Use when extracting single-cell data from IMC or MIBI images after preprocessing.

Alpha and beta diversity analysis for microbiome data. Calculate within-sample richness, evenness, and between-sample dissimilarity with phyloseq and vegan. Use when comparing community composition across samples or testing for group differences in microbiome structure.

Perform flux balance analysis (FBA) and flux variability analysis (FVA) on genome-scale metabolic models using COBRApy. Predict growth rates, metabolic fluxes, and optimal resource utilization. Use when predicting metabolic phenotypes or optimizing flux distributions.

Validate Ribo-seq data quality by checking 3-nucleotide periodicity and calculating P-site offsets. Use when assessing library quality or determining read offsets for downstream analysis.

Calculate translation efficiency (TE) as the ratio of ribosome occupancy to mRNA abundance. Use when comparing translational regulation between conditions or identifying genes with altered translation independent of transcription.

Extract, process, and deduplicate reads using Unique Molecular Identifiers (UMIs) with umi_tools. Use when library prep includes UMIs and accurate molecule counting is needed, such as in single-cell RNA-seq, low-input RNA-seq, or targeted sequencing to distinguish PCR from biological duplicates.

How to author Triggerfish skills. Covers SKILL.md format, frontmatter fields, security metadata, the three-tier hierarchy, approval workflow, triggers, and best practices. Use when creating new skills for an agent.

Manages external skill repos in a project using the git submodule + symlink pattern: adds skill repos as submodules under vendor/, symlinks individual skills into the project's skills/ directory and .claude/skills/ for Claude Code discovery, handles updates and removal. Use when the user says 'add skill repo', 'add external skills', 'manage skills', or 'update skills submodule'.