菜单
SkillsMP 已收集 Abilityai/trinity-skills 中的 28 个 Skill。打开任一 Skill 可查看来源和详情。
已展示 28 / 28 个已收集 Skill。
Explain a complex topic back to you with visuals - the right diagram for each facet (flowchart, timeline, sequence, schema/ER, state machine, chart, comparison, mind map) plus optional conceptual illustrations - rendered in a style you control, then bundled…
原文语言：英语
Generate a brand-locked, information-dense single-page PDF that lets a reader understand an entire topic - a company, a product, a project, a status update, any subject - in one page. Distills a raw brief into a composed grid of reusable blocks (hero-stat,…
原文语言：英语
Generate a brand-locked multi-slide presentation deck (16:9, 1920x1080) and assemble into a PDF. Mirrors the social-carousel pattern - each slide is an HTML+Playwright PNG render with its own textless soft-futurism hero image. Final step combines all slide…
原文语言：英语
Build an animated, data-driven explainer film for a real system — a canvas film that renders live from the product's own data and cannot drift, not an exported video. Can additionally stamp the finished film into a voiced MP4 (deterministic frame render +…
原文语言：英语
Build a brand-locked, animated single-page microsite (locked to YOUR palette - the shipped tokens are a swappable default) - a self-contained scrolling HTML page that presents any topic or dataset as a visual story with text, diagrams, charts, KPI strips, and…
原文语言：英语
Make any agent a system-aware orchestrator — installs /discover-agents (discover the fleet from live Trinity and/or a repo list into a descriptive fleet/system-map.yaml), /compose-system (turn the map into a Trinity SystemManifest and deploy_system), and…
原文语言：英语
Scaffold a Trinity-compatible long-running pipeline inside any agent — creates projects/<slug>/{project.md, pipeline.yaml, instances/}, copies pipeline-tick/status/recover/pause/resume skills into .claude/skills/, sets up the ~/.trinity/ read surface,…
原文语言：英语
Modify an existing playbook based on conversation context or explicit instructions. Use when user wants to update, fix, extend, or refine a playbook they already have.
原文语言：英语
Scan one or more directories of agents in ANY paradigm — Claude Code, n8n workflow exports, framework apps (LangChain/CrewAI/AutoGen), or freeform-coded agents — assess quality (fleet maturity for Claude Code, migration readiness for the rest), design the…
原文语言：英语
Create a new skill or playbook. Guides through requirements gathering and generates the appropriate template based on complexity.
原文语言：英语
Lint a pipeline.yaml — schema check, DAG acyclicity, referenced-skill existence, precondition kind registration. Pure linter — prints a report, writes no files. Heartbeat does not require validation to have run; this is a developer convenience.
原文语言：英语
Add git-as-state hooks to an agent — auto-commits on Stop, rebases on SessionStart, snapshots on PreCompact. Gives agents durable cross-session memory through their own repo.
原文语言：英语
Install cross-actor project management into this agent — GitHub Issues as single source of truth, uniform task anatomy with approval-ready completion lattice (open → pending-verification → done), loop closure in both directions (the agent closes loops with…
原文语言：英语
Give any agent a shared canonical-data layer — installs /canon-publish (commit this agent's own folder in the fleet's shared canon repo), /canon-consume (read other agents' published data at a cited ref), /canon-reconcile (scheduled freshness pass over the…
原文语言：英语
Build a verified Claude Code fleet from an agent-fleet-analysis work order — non-destructive migration of mixed fleets (Claude Code, n8n exports, LangChain/CrewAI/AutoGen apps, freeform-coded loops). Sources are never mutated; each agent is copied or…
原文语言：英语
Add GitHub Issues backlog workflow to any agent — creates the full development cycle (backlog, claim, close, groom, roadmap, autoplan, commit, sprint, work-loop)
原文语言：英语
Add a memory system to an agent — file awareness, knowledge graph, structured state, or multi-session tracking
原文语言：英语
Create a meaningful git commit to checkpoint current agent state. Use when the user says "commit", "save changes", "checkpoint", "commit my work", or asks to save progress to git.
原文语言：英语
Generate explanatory diagrams and infographics that visually communicate concepts. Iterates autonomously until images are logically correct, text is clean, and the concept explanation is clear. Uses Nano Banana 2 (Gemini 3.1 Flash Image).
原文语言：英语
Extracts key information from documents (PDFs, images, text files) in a folder and creates structured markdown summaries with the same filename but .md extension. Use when you need to analyze and extract insights from multiple documents in a directory.
原文语言：英语
Extract all chapters from an EPUB file into separate markdown files. Use when the user wants to split an EPUB into individual chapter files, extract EPUB chapters, or convert an ebook to separate markdown documents.
原文语言：英语
Generate a comprehensive file system index with directory tree, file sizes, and modification dates. Use when re-indexing files, updating file index, exploring directory structure, or when user says "re-index files".
原文语言：英语
Ask Gemini's most powerful model for an independent second opinion - critique code with fresh eyes, evaluate an article, challenge a plan. The calling agent controls the exact question and material; this skill just executes the call and returns Gemini's…
原文语言：英语
Generate images using Google's Nano Banana 2 (Gemini 3.1 Flash Image Preview). Use when creating infographics, diagrams, thumbnails, social media graphics, or any AI-generated images. Costs $0.067/image.
原文语言：英语
Measure the development speed / velocity / activity of any GitHub repository using objective metrics from the GitHub API — commits, lines added/deleted, merged-PR throughput, active contributors, time-to-merge, and release cadence. Compares multiple repos…
原文语言：英语
Run self-diagnostics on the agent to verify skills, commands, agents, and dependencies are working. Use when troubleshooting, after configuration changes, or for regular health checks.
原文语言：英语
Expert guide for creating Claude Code skills. Use when user wants to create a new skill, build a skill, design a slash command, or needs help with SKILL.md files, frontmatter, or skill structure. Also use when reviewing or improving existing skills.
原文语言：英语
Enforce workspace organization rules when creating files, writing documents, or generating assets. Use when about to create any file, write output, save reports, or generate artifacts. Ensures files are placed in proper locations - never in root directory.
原文语言：英语