Read a plan document, decompose it into steps, design a per-step agent chain from the ECC catalogue, and emit ready-to-paste /orchestrate custom prompts. Generative only — never invokes /orchestrate itself. Use when the user has a multi-step plan and wants to drive it through orchestrate without composing chains by…
Codified expertise for quality control, non-conformance investigation, root cause analysis, corrective action, and supplier quality management in regulated manufacturing. Informed by quality engineers with 15+ years experience across FDA, IATF 16949, and AS9100 environments. Includes NCR lifecycle management, CAPA…
A Chinese-language skill that guides interactions in a fictional palace-court role-play style based on the television drama Empresses in the Palace. Its description covers setup, behaviour rules, interaction methods, and reports.
Run a counterbalanced A/B knob block end to end and produce a report. Orchestrates the whole validation loop the other skills do piecemeal — for each arm it starts a clawback proxy with that arm's knobs and its OWN --state file (fresh SESSION KEY, no clawback-side carry-over), drives N turns of load through it (pty or…
Paired shadow-capture — one real claude session that captures the no-clawback baseline AND applies the armed knobs at the same time. This is the "shadow mode" knob for baseline capture: instead of forfeiting the optimizations for the measurement window (a plain passthrough baseline), the tee fans every turn to TWO…
Quiet operator watch for a detached clawback proxy — stream ONLY legitimate errors and never the benign flood. Wakes on [error]/[fatal] lines, crash signatures (uncaught/EADDRINUSE/ECONN/Error:/self-loop), server-side 5xx that are NOT the transient 529, real (non-keep-alive) request failures, and a loud "PROXY DOWN"…
Controls Obsidian vaults via the official CLI (1.12+). Reads, creates, appends to, and searches notes. Manages daily notes, tasks, tags, properties, templates, bookmarks, and plugins. Analyzes knowledge graph structure including backlinks, orphans, and unresolved links. Triggers on Obsidian, vault, notes, daily notes…
When the user wants to apply to startup accelerators, incubators, or fellowship programs. Also use when the user mentions "YC application", "Techstars", "accelerator", or "apply to programs".
When the user needs to analyze, categorize, or extract actionable insights from customer feedback across multiple sources, especially feature requests.
Use when a full GitHub repository URL (github.com/owner/repo) appears in conversation, when the user asks to check, review, or analyze a GitHub repo, or when the user runs /gitgauge. Does not trigger on npm packages, file paths, org pages, or issue/PR links.
Automatically calibrate response effort and token usage to match task complexity. Use this skill at the START of every response to classify the incoming task and select the appropriate effort tier before generating any output. Trigger whenever you're about to answer a question or complete a task — this skill saves…
Shape output for a reader with ADHD: lead with the next action, number multi-step work, restate state across turns, suppress tangents, give specific time estimates, make wins visible. Invoke with /i-have-adhd; stays on until "stop adhd mode".
Create stunning, animation-rich HTML presentations from scratch or by converting PowerPoint files. Use when the user wants to build a presentation, convert a PPT/PPTX to web, or create slides for a talk/pitch. Helps non-designers discover their aesthetic through visual exploration rather than abstract choices.
Divide a specced pastiche task into sub-task GitHub issues with autonomy and dependency labels, mirror them into dev/TODO.md, and update the parent issue. Use after grill-to-spec completes for a task, or when the user invokes /divide-task.
Convert a completed grill-me session into a spec file. Captures only the task and the decisions locked during grilling — no implementation details, no invented decisions. Use when the user asks to write a spec from a grill, save grill decisions, or after a grill-me session concludes.
Pick up or resume a task from dev/TODO.md — marks [WIP], creates or switches to the task's feature branch, rebases with main. Use when the user invokes /pick-up-task or asks to grab/resume a pastiche task.
Assess or re-assess the innovation-vs-implementation classification and 0-100 innovation weight for one feature or the whole Product/Features set, then regenerate the ranked features-index.md and run the portfolio sanity check. Use when features need (re)ranking or after editing the UVP.
Create or revise a single Product feature file with a complete user story, Given/When/Then acceptance criteria, and an innovation-vs-implementation classification. Use when adding one feature to Product/Features/, or refining an existing feature, outside a full /innovate run.
The front door / orchestrator for the I-Framework. Reads the Product/ folder, determines which stage (Intent, Ideation, Innovation) you're in from the artifacts and their gates, reports the risk-burndown state, and routes you to the next step. Use to start or resume the Intent → Ideation → Innovation flow.
Generate AI images using Midjourney through the Legnext API. Use this skill when users request Midjourney-style image generation, visual content creation, or ask to create/generate images with natural language descriptions. Handles prompt engineering, API calls, task polling, and result retrieval.
Expert Midjourney prompt engineering skill. Use this skill when users need help crafting effective Midjourney prompts, converting natural language descriptions into optimized prompts, or want guidance on Midjourney parameters and techniques. Specializes in V7 best practices, the 7-Element Framework, and photography…
★not rated 4 8mo agoA67 tokens
originalMIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: