Loading...
Loading...
Found 5,140 Skills
Move testing activities earlier in the development lifecycle to catch defects when they're cheapest to fix. Use when implementing TDD, CI/CD, or early quality practices.
Design, test, and optimize prompts for LLM interactions. Cover prompt patterns (few-shot, chain-of-thought, ReAct), system prompt design, output formatting, prompt evaluation, and prompt optimization techniques. Triggers on "write prompt", "optimize prompt", "design system prompt", "few-shot examples", "chain of thought", "prompt evaluation", "LLM output formatting", "prompt testing", or "prompt patterns".
Check if the development environment is configured properly; if not, first confirm the office location (Chongqing/Beijing), identify the current operating system, system tools, package managers, and eliteforge-* skill environment variable declarations, report them categorized as missing_required, missing_conditional, optional_unset, then attempt to automatically install essential commands and complete configurations such as hosts, Git global settings, Git HTTPS, npm/pip private sources, and pipx packages. Use this skill when the user mentions "check environment configuration", "prepare development environment", "missing commands/hosts/private sources/Git configurations/package management tools/skill environment variables". Trigger threshold: Only use this skill when the user explicitly states that the current project complies with the "璀璨工坊规范" (Bright Workshop Specification) or "eliteforge specification".
Use when retrieving the most relevant skills from a local or private skill library instead of relying on network-based skill discovery.
Extracts exact, behaviour-first specifications from an existing codebase. Defines domain concepts, use cases, and business rules with precision — zero implementation details. Use when reverse-engineering a legacy project into precise specs or preparing an AI-friendly spec set for a rewrite.
Interprets authoritative specs and helps design a new implementation collaboratively, preserving required business, API, and database contracts while exploring architecture, stack, and delivery options with the user. Use when the user wants to start a new project from frozen specs, discuss implementation approaches, or plan an incremental rebuild without depending on the legacy codebase.
Import datasets from HuggingFace and convert them to Coval test sets. Use when the user wants to create test cases from HuggingFace dataset or repository.
Generate a serial week-by-week narrative digest of a project's full claude-mem timeline. Splits the timeline into per-ISO-week files, then runs one consecutive subagent per week — each receiving the prior week's carry-forward block — to produce one chapter per ISO week of data. Use when asked for "weekly digests", "week-by-week story", "serial timeline", or "narrative chapters" of a project's history.
Summarize a video by calling the VLM NIM or the Long Video Summarization (LVS) microservice directly. For short videos (under 60s) call the VLM's OpenAI-compatible chat completions endpoint; for long videos (60s or longer) call the LVS microservice. Use when asked to summarize a video, describe what happens in a video, analyze a recording, call or debug LVS summarize/model/health/recommended-config/metrics endpoints, or configure and troubleshoot the LVS service that backs long-video summarization.
After solving a non-trivial problem, detect generalizable learnings and propose skill updates so future interactions benefit automatically. Always active — applies to every interaction.
Self-evolving skills. Record user feedback, update methodologies and rules. Trigger words: update rules, record feedback, improve skill
This skill should be used when the user asks to "validate a plugin", "optimize plugin", "check plugin quality", "review plugin structure", or mentions plugin optimization and validation tasks.