发现 Skills

Write effective resume bullets and content. Use when writing, rewriting, or improving resume bullets, sections, or any resume text. Covers bullet composition, length, word choice, tailoring, keyword placement, and gendered language.

Diagnose local container issues with Podman/Docker including image pull errors, container startup failures, OOM kills, and networking problems. Automates a multi-step diagnosis: container inspect, logs retrieval, image analysis, and resource-constraint checking. Use this skill when containers fail to run locally before deployment. Triggers on the /debug-container command or phrases like "container won't start", "podman run fails", "local container crashing", "container exits immediately".

This skill should be used when the user asks to "generate execution summary", "create execution report", "summarize what was used", "show execution summary", or "what agents/skills/tools were used". Generates a concise report of agents, skills, tools, and documentation accessed during a workflow for audit and learning purposes.

Review code against spec compliance - checks implementation matches spec requirements, identifies deviations, reports a compliance score, and triggers spec evolution if needed.

Plan a new feature through interactive questioning, producing domain requirements and architecture diagrams.

Interactive initialization script that generates a compliant lifecycle Hook for an AI Agent or Plugin. Use when you need to automate workflows based on events like PreToolUse or SessionStart.

Elite TypeScript and system architecture expert. Highly efficient, slightly sarcastic. Specializes in clean code, SOLID principles, and ruthless refactoring.

Use this skill when users request i18n/localization updates for Android string resources, especially when adding new keys or translating via locale-tui.

Get current weather and forecasts (no API key required).

Exploit development workflow. Use when: write exploit, PoC, payload, shellcode, bypass, buffer overflow, RCE, reverse shell.

Adversarial code review that breaks the self-review monoculture. Use when you want a genuinely critical review of recent changes, before merging a PR, or when you suspect Claude is being too agreeable about code quality. Forces perspective shifts through hostile reviewer personas that catch blind spots the author's mental model shares with the reviewer.

Use when the user asks to generate API tests, create integration test suites, test REST endpoints, or build contract tests.

Use when the user asks to design database schemas, plan data migrations, optimize queries, choose between SQL and NoSQL, or model data relationships.

Use when adding, retiring, or auditing feature flags. Triggers on "add a flag", "ship behind a flag", "rollout plan", "kill switch", "stale flags", "flag debt", "LaunchDarkly", "GrowthBook", "Statsig", "Unleash", "Flipt", or any progressive-delivery question. Ships flag debt scanner, rollout planner, and kill-switch auditor (all stdlib Python), 4 references on flag taxonomy + provider trade-offs + rollout strategies + lifecycle, plus a /flag-cleanup slash command.

Use when the user asks to capture a full-page screenshot, long screenshot, or complete page capture of a web page. Handles SPA scroll containers, lazy-loaded images, and very tall pages via Chrome DevTools Protocol with zero external dependencies.

Migrate from Cypress or Selenium to Playwright. Use when the user mentions "cypress", "selenium", "migrate tests", "convert tests", "switch to playwright", "move from cypress", or "replace selenium".

Use when writing Snowflake SQL, building data pipelines with Dynamic Tables or Streams/Tasks, using Cortex AI functions, creating Cortex Agents, writing Snowpark Python, configuring dbt for Snowflake, or troubleshooting Snowflake errors.

Activated for Atlassian API operations such as creating, searching, retrieving, and changing the status of Jira tickets, and creating, reading, merging, or approving Bitbucket PRs. Server-side filtering using JQL queries or the q parameter is mandatory. Used for requests like "create a Jira ticket", "search Jira issues", "create a Bitbucket PR", "merge a PR", and "approve a PR".

Intelligent skill router and creator. Analyzes ANY input to recommend existing skills, improve them, or create new ones. Uses deep iterative analysis with 11 thinking models, regression questioning, evolution lens, and multi-agent synthesis panel. Phase 0 triage ensures you never duplicate existing functionality.

This skill should be used when the GM needs to handle spellcasting situations, including resolving spell effects, managing spell slots, calculating spell save DCs, handling concentration, resolving spell attacks, determining spellcasting abilities, handling cantrips, or processing ritual casting. Provides spellcasting rules, formulas, and references for running magical gameplay.

Preflight environment validation. Use at session start or before running tests to verify the development environment is correctly configured.

Fine-tune LLMs using the Red Hat training-hub library with SFT, LoRA, and OSFT algorithms. Use it when preparing JSONL datasets, running training jobs, configuring hardware, scaling to clusters, evaluating models, or deploying with vLLM.

Maintain and evolve local Agent Skills for this repo. Use after implementing features or changing workflows so skills stay current.

Explore Dart's bitwise operations for both integers and booleans, including AND, OR (inclusive & exclusive), NAND, NOR, and XNOR, with practical code examples.