← all publishers

CatCorner22

@catcorner22 source repo

187 published skills · page 1 of 2

  1. Pipeline Preflight · catcorner22
    Pre-execution audit before AI generation: required inputs, files, constraints, tools, and prior outputs present. Halt instead of running cold. Use before agent runs, RAG pipelines, or multi-step chains. Scope boundary: human/study prep → `workspace-mise-en-place`; craft routing → `craft-systems-primer`.
    0 installs
  2. Proofreading Marks · catcorner22
    Granular annotation layer between draft and delivery: QUERY, DELETE, STET, TRANSPOSE, INSERT — not wholesale rewrite. Use for AI self-review and human-in-the-loop edit. Scope boundary: full rewrite → domain writing skills.
    0 installs
  3. Sidechain Priority · catcorner22
    When the answer/solution/result arrives, duck the supporting intro so the signal sits on top. Use when preambles bury the payload. Scope boundary — zoom compression → `cartographic-zoom`; dual-axis completeness → `score-study-dual-axis`.
    0 installs
  4. Coding Ecosystem Primer · catcorner22
    Router for general software engineering in this library: deliverable-first planning, clean minimal code, stable architecture, real-time testing, and UI/UX engineering. Use when building or refactoring application code with no framework-specific pack already chosen, or when the user asks for coding standards, clean code, TDD, architecture, or how to implement a feature well. Scope boundary: framework-specific work routes out — Next.js/React UI details → `nextjs`/`shadcn`/`react-best-practices`; end-to-end product verification after a feature ships → `verification`; Playwright/browser automation → `playwright-cli`; PR/CI workflow → `cursor-team-kit`; LangChain/Python agents → those packs.
    0 installs
  5. Migrate To Builds · catcorner22 bundle
    Test that a Cloud Agent environment will work with prebuilt environment builds and recommend any required changes. Use when the user wants to migrate to builds, test build compatibility, or follow the Builds page setup-agent flow.
    0 installs
  6. Huggingface Gradio · catcorner22 bundle
    Build Gradio web UIs and demos in Python. Use when creating or editing Gradio apps, components, event listeners, layouts, or chatbots.
    0 installs
  7. Huggingface Papers · catcorner22
    Look up and read Hugging Face paper pages in markdown, and use the papers API for structured metadata such as authors, linked models/datasets/spaces, Github repo and project page. Use when the user shares a Hugging Face paper page URL, an arXiv URL or ID, or asks to summarize, explain, or analyze an AI research paper.
    0 installs
  8. Huggingface Spaces · catcorner22 bundle
    Build, deploy, and maintain applications on Hugging Face Spaces — Gradio / Docker / Static SDKs, ZeroGPU and dedicated hardware, model loading, debugging, buckets, inference providers, community grants. Use whenever the user asks to create or host an app on Hugging Face, port code onto ZeroGPU, fix a Space that won't build or run, or otherwise work with `hf spaces …`, `@spaces.GPU`, Space README frontmatter, or the `spaces` Python package.
    0 installs
  9. Langchain Middleware · catcorner22
    Middleware on a LangChain `create_agent` / `createAgent` agent: `HumanInTheLoopMiddleware` to approve dangerous tool calls, writing custom middleware hooks, `Command` resume patterns, and structured output with Pydantic/Zod. Use when the agent being extended is a LangChain agent. Scope boundary: structured output on the Vercel AI SDK (`Output.object`) belongs to `ai-sdk`; interrupts in a hand-written LangGraph graph belong to `langgraph-human-in-the-loop`.
    0 installs
  10. After Action Review · catcorner22
    Post-generation debrief: intended vs actual vs gap vs prescription. Log for recurring pattern fixes. Use after agent tasks complete. Scope boundary: five whys on hard failures → `five-whys-failure-recovery`.
    0 installs
  11. Double Entry Claims · catcorner22
    Hallucination suppression via structural claim/evidence pairing: every factual claim must balance with a supporting source before output delivers. Use when verifying AI outputs, building RAG gates, or when the user asks for claim checking, evidence balance, or hallucination suppression. Scope boundary: human workspace prep → `workspace-mise-en-place`; source citation style → `citation-literacy`.
    0 installs
  12. Seismic Flexibility · catcorner22
    Insert modular joints (paragraph/section seams) so a later edit does not collapse the whole piece. Use on long docs that will be revised. Scope boundary — warp/weft threads → `weaving-warp-weft`; load-bearing claims stay tagged → `load-bearing-structure`.
    0 installs
  13. Stratigraphy Memory · catcorner22
    Layer memory by session strata plus disturbance markers; retrieve with integrity confidence. Use for long-horizon agents. Scope boundary: flat RAG → `library-taxonomy-retrieval`; cross-session bridges → `wildlife-corridor-bridging`.
    0 installs
  14. Tidal Pacing Rhythm · catcorner22
    Measure sentence-length tide (high/mid/low) and even the rhythm when variance is extreme. Use on long prose that feels rushed or swampy. Scope boundary — token budget cuts → `prompt-optimizer`; zoom depth → `cartographic-zoom`.
    0 installs
  15. Get Pr Comments · catcorner22
    Fetch and summarize review comments from the active pull request
    0 installs
  16. Review And Ship · catcorner22
    Review the current branch for bugs, intent fit, and test coverage; run or write tests; commit focused work; open or update a PR.
    0 installs
  17. Skill Library Audit · catcorner22 bundle
    Audit a multi-vendor agent-skill library for routing pathology — the defect classes that appear only when many packs from different vendors share one router: vendor steering, SKILL.md/overlay.yaml drift, silently disabled rules, unreachable guards, greedy descriptions, cross-pack territory claims, shadowed and cyclic routes, dangling references. Use when adding a skill pack, merging two libraries, or when skills fire on the wrong thing. Ships a runnable analyzer at scripts/audit_skill_library.py. Scope boundary: this audits a SKILL LIBRARY's routing metadata, not application code — for authoring a single new skill use skill-creator, and for reviewing ordinary source changes use code-review.
    0 installs
  18. Huggingface Trackio · catcorner22 bundle
    Track and visualize ML training experiments with Trackio. Use when logging metrics during training (Python API), firing alerts for training diagnostics, or retrieving/analyzing logged metrics (CLI). Supports real-time dashboard visualization, alerts with webhooks, HF Space syncing, and JSON output for automation.
    0 installs
  19. Huggingface Zerogpu · catcorner22 bundle
    AI demos and GPU compute with Gradio Spaces and Hugging Face Spaces ZeroGPU. Use when writing or reviewing code that uses `@spaces.GPU`, configuring `python_version` or `requirements.txt` for a ZeroGPU Space, or handling ZeroGPU-specific code constraints — pickle-based process isolation, `gr.State` semantics across the worker boundary, no `torch.compile` (use AoTI instead), CUDA wheel-only **builds** (no `nvcc` at build; runtime has `nvcc` for AoTI), large vs xlarge sizing, and dynamic duration callables. Make sure to use this skill whenever the user mentions ZeroGPU, `@spaces.GPU`, or the `spaces` Python package, or hits ZeroGPU-specific code errors like `PicklingError` across the worker boundary, `illegal duration`, or `flash-attn` wheel-build failures — even when the user does not explicitly ask for ZeroGPU coding guidance. Trigger on `import spaces` or `@spaces.GPU` in code.
    0 installs
  20. Langgraph Persistence · catcorner22
    Persist LangGraph state: checkpointers, `thread_id`, time travel over checkpoint history, the cross-thread `Store`, and subgraph checkpointer scoping. Use when a LangGraph graph must survive a restart, remember a conversation across turns, replay or fork history, or share memory between threads. Scope boundary: graph construction belongs to `langgraph-fundamentals`, pausing and resuming for a human to `langgraph-human-in-the-loop`, and application database or session storage that is not a LangGraph checkpointer to that provider's own skill (`supabase`, `vercel-storage`).
    0 installs
  21. AI Transfer Adaptive · catcorner22
    Router for adaptive AI-transfer techniques: compute triage, AAR debriefs, mid-flight feedback, wayfinding telemetry, annealing phases. Use when tuning dynamic agent behavior. Scope boundary: full catalog → `ai-transfer-ecosystem-primer`.
    0 installs
  22. AI Transfer Advanced · catcorner22
    Router for advanced AI-transfer techniques: seismic joints, sidechain ducking, genre cross-pollination, containment layers, sail trim, interaction tables, parallax depth. Use when composing stacks or tuning long-running outputs. Scope boundary: full catalog → `ai-transfer-ecosystem-primer`.
    0 installs
  23. Color Grading Output · catcorner22
    Grade pass on luminance (information density), chroma (emotional intensity), hue (stance consistency). Use for tone/ clarity review of drafts. Scope boundary: faceting passes → `gemstone-faceting-refinement`.
    0 installs
  24. Metamorphosis Stages · catcorner22
    Force larva (brainstorm) → pupa (structure) → adult (polish) as separate artifacts. Use instead of polishing a first dump. Scope boundary — annealing lock temperatures → `glass-annealing-hardening`; faceting angles → `gemstone-faceting-refinement`.
    0 installs
  25. Survey Triangulation · catcorner22
    Require three independent retrieval paths per factual claim; score agreement 3/3, 2/3, or contested. Use when single-source RAG is insufficient. Scope boundary: double-entry gate → `double-entry-claims`.
    0 installs
  26. Wine Blending Fusion · catcorner22
    Run prompt on models with different strengths; fusion pass extracts best elements selectively — not averaging. Use when models complement (reasoning + phrasing + facts). Scope boundary: single-model routing → `emergency-triage-compute`.
    0 installs
  27. Pr Review Canvas · catcorner22 bundle
    Generate an interactive PR review walkthrough as an HTML page. Fetches PR data via gh API, categorizes files into core vs mechanical changes, adds reviewer annotations, and renders diffs with moved-code detection. Use when the user pastes a GitHub PR URL and asks for a review, walkthrough, or summary, or says "review this PR".
    0 installs
  28. Huggingface Datasets · catcorner22
    Use this skill for Hugging Face Dataset Viewer API workflows that fetch subset/split metadata, paginate rows, search text, apply filters, download parquet URLs, and read size or statistics.
    0 installs
  29. Langchain Dependencies · catcorner22
    Package versions, installs, and dependency management for the LangChain stack in Python and TypeScript: required packages, minimum versions, environment requirements, versioning practice, and common community tool packages. Use when installing, pinning, or debugging versions of `langchain*`, `langgraph*`, `langsmith`, `deepagents`, or `@langchain/*`. Scope boundary: project scaffolding that is not LangChain-specific belongs to that framework's own bootstrap skill.
    0 installs
  30. Langchain Fundamentals · catcorner22
    Create LangChain agents with `create_agent` / `createAgent`: model and tool wiring, the agent loop, and where middleware attaches. Use when the code imports `langchain`, `langchain.agents`, or `@langchain/core`, or the user names LangChain agents or `create_agent`. Scope boundary: writing the middleware itself and structured output belong to `langchain-middleware`; hand-written graphs to `langgraph-fundamentals`; an agent request that has not chosen a framework to `build-agents`/`eve`.
    0 installs
  31. Langgraph Fundamentals · catcorner22
    Write LangGraph graphs in Python or TypeScript: StateGraph, state schemas and reducers, nodes, normal and conditional edges, Command, Send fan-out, invoke/stream modes, and error handling. Use when the code imports `langgraph` / `@langchain/langgraph`, or the user names LangGraph, StateGraph, or graph nodes and edges. Scope boundary: checkpointers and durable state belong to `langgraph-persistence`, `interrupt()` and approval flows to `langgraph-human-in-the-loop`, the prebuilt `create_agent` constructor to `langchain-fundamentals`, and running or shipping a graph to `langgraph-cli`.
    0 installs
  32. Teams Collaboration · catcorner22
    Collaborate in Microsoft Teams for school and work: channels, chat threads, meetings, screen share, file tabs, and group project norms. Use when setting up Teams for a group project, running class meetings, or coordinating async work. Scope boundary: email → `outlook-email-calendar`; file storage policy → `onedrive-organization`; Slack/Discord → not this pack.
    0 installs
  33. AI Transfer Extension · catcorner22
    Router for extension AI-transfer techniques: just-intonation parameter ratios, load-bearing claim locks, orchard grafts, differential query intent, stress tests, tidal pacing, underwriting gates, metamorphosis stages. Use when calibrating or staging generation beyond the original 30. Scope boundary: full catalog → `ai-transfer-ecosystem-primer`.
    0 installs
  34. Fermentation Feedback · catcorner22
    Mid-generation monitoring: user activity, corrections typing, deadlines, confidence — adjust or abort mid-stream. Use for long agent runs and streaming workflows. Scope boundary: post-hoc AAR → `after-action-review`.
    0 installs
  35. Ooda Adaptive Context · catcorner22
    Four-phase AI pipeline with logged Orient step: observe raw context, orient (filter/prioritize with inspectable log), decide approach, act. Use when debugging why context was ignored. Scope boundary: human OODA → `ooda-lean-loop`.
    0 installs
  36. Proof Trees Reasoning · catcorner22
    Declare reasoning DAG before prose: premises, claims, dependencies. Flag downstream if upstream fails. Use for multi-step arguments and agent plans. Scope boundary: dual-axis → `score-study-dual-axis`.
    0 installs
  37. Score Study Dual Axis · catcorner22
    Horizontal pass (narrative arc) plus vertical pass (parallel considerations at each step). Synthesize output satisfying both. Use for complex analysis and long-form reasoning. Scope boundary: dependency DAG → `proof-trees-reasoning`.
    0 installs
  38. Stage Blocking Layout · catcorner22
    Spatial emphasis: center stage = core message; flanks = evidence; opposing entrances = dialectic; center curtain = synthesis. Use for reports, docs, and structured responses. Scope boundary: warp/weft structure → `weaving-warp-weft`.
    0 installs
  39. New Branch And Pr · catcorner22
    Create a fresh branch, complete work, and open a pull request
    0 installs
  40. Prompt Optimizer · catcorner22 bundle
    Creates, optimizes, and iteratively refines agent prompts, system prompts, developer prompts, and reusable prompt templates. Use when asked to improve a prompt, optimize a system prompt, rewrite an agent prompt, tune prompt wording, make a prompt more reliable, port prompts between OpenAI, Claude, or Gemini, or build prompt evals. Scope boundary — this skill owns agent PROMPT authoring and optimization: the instruction text itself, its layering, its examples, and the evals that score it. Agent ARCHITECTURE and scaffolding belong elsewhere: generic "build/create/design/scaffold an agent" requests go to `build-agents`, and eve project structure, runtime, channels, and tooling go to `eve`. Do not claim a request just because it mentions an agent; claim it when the artifact under edit is a prompt.
    0 installs
  41. Academic Ecosystem Primer · catcorner22
    Router for college and academic work in this library: writing, citations, study planning, source attribution, lecture notes, and presentations. Use when the user is a student, mentions college/school/coursework, or asks how to approach an assignment, paper, exam prep, or lab. Scope boundary: CS/software implementation → `coding-ecosystem-primer`; AI/ML engineering → huggingface/langchain packs; GitHub PR workflow for group code projects → `cursor-team-kit`; general execution posture → `proactive-agency`.
    0 installs
  42. Appbuilder Action Scaffolder · catcorner22 bundle
    Create, implement, deploy, and debug Adobe Runtime actions with consistent layout, validation, and error handling. Use this skill whenever the user needs to add actions to an App Builder project, understand action structure (params, response format, web/raw actions), configure actions in the manifest, use App Builder SDKs (State, Files, Events, database), deploy and invoke actions via CLI, debug action issues, or implement patterns such as webhook receivers, custom event providers, journaling consumers, large payload redirects, action sequence pipelines, and Asset Compute workers. Also trigger when users mention serverless functions in Adobe context, action logging, IMS authentication for actions, or cron-style scheduled actions.
    0 installs
  43. AI Transfer Refinement · catcorner22
    Router for refinement AI-transfer techniques: three-axis grading, debate voting, model blending, faceting passes, localization QA. Use for final polish and multi-model fusion. Scope boundary: full catalog → `ai-transfer-ecosystem-primer`.
    0 installs
  44. Load Bearing Structure · catcorner22
    Mark load-bearing claims (therefore/must/key/critical) and forbid polish passes from deleting or softening them. Use before color-grading or faceting. Scope boundary — claim/evidence balance → `double-entry-claims`; robustness tests → `stress-test-robustness`.
    0 installs
  45. Localization QA Filter · catcorner22
    Pre-delivery scan for region mismatch: dates, currency, idioms, units, regulatory refs, cultural examples. Use when audience locale is known. Scope boundary: academic citation locales → `citation-literacy`.
    0 installs
  46. Orchard Graft Transfer · catcorner22
    Graft a specialist scion onto a safe rootstock output: keep the trusted base, attach expert additions at a marked join. Use when mixing a general answer with a domain specialist pass. Scope boundary — multi-model fusion → `wine-blending-fusion`; foreign genre skeleton → `cross-pollination-structure`.
    0 installs
  47. Stress Test Robustness · catcorner22
    Run contradiction, edge-case, adversarial, and scope tests on a draft before delivery. Use after generation and before polish. Scope boundary — escalating critique questions → `progressive-resistance-critique`; load-bearing tags → `load-bearing-structure`.
    0 installs
  48. Underwriting Risk Gate · catcorner22
    Score GREEN/YELLOW/RED risk before delivery for medical, legal, or financial-advice asks; hold RED for review. Use as a pre-delivery gate, not as advice. Scope boundary — does not give legal/medical advice; claim support → `double-entry-claims`; independent safety layers → `containment-safety-layers`.
    0 installs
  49. Wayfinding Restructure · catcorner22
    Instrument consumption behavior (scroll-back, re-prompt, abandon) to restructure future outputs. Use for productized AI interfaces with telemetry. Scope boundary: static layout → `stage-blocking-layout`.
    0 installs
  50. Walkthrough Artifacts · catcorner22
    Create walkthrough artifacts (screenshots and screen recordings) that prove code changes work. Use when finishing tested changes and uploading demo evidence for the user.
    0 installs
  51. M365 Ecosystem Primer · catcorner22
    Router for Microsoft 365 work in this library: Word documents, Excel workbooks, PowerPoint decks, Outlook email/calendar, Teams collaboration, and OneDrive organization. Use when the user mentions Microsoft 365, Office, Word, Excel, PowerPoint, Outlook, Teams, OneDrive, SharePoint, or Copilot in Office apps. Scope boundary: Google Workspace → not covered; general academic writing craft → `academic-writing`; slide narrative without Office still uses `powerpoint-decks` for structure; coding assignments → `coding-ecosystem-primer`.
    0 installs
  52. Onedrive Organization · catcorner22
    Organize files in Microsoft OneDrive and SharePoint: folder structure for semesters, sharing links, permissions, version history, and sync. Use when storing coursework, sharing group files, or recovering previous document versions. Scope boundary: in-app editing → word/excel/powerpoint skills; Google Drive → not this pack.
    0 installs
  53. Endgame Tablebase Cache · catcorner22
    Pre-compute and cache known-correct answers for recurring boundary conditions; check tablebase before reasoning. Use for boilerplate code, legal clauses, lookup math. Scope boundary: live reasoning → `proof-trees-reasoning`.
    0 installs
  54. Sterile Cockpit Context · catcorner22
    Phase-gated context: takeoff (parse inputs only), cruise (full history), landing (validation rules only). Strip distraction during critical phases. Use for high-stakes generation steps. Scope boundary: human prioritization → `ooda-lean-loop`.
    0 installs
  55. Fix Merge Conflicts · catcorner22
    Resolve merge conflicts non-interactively, validate build and tests, and finalize conflict resolution
    0 installs
  56. Huggingface LLM Trainer · catcorner22 bundle
    Train or fine-tune language and vision models using TRL (Transformer Reinforcement Learning) or Unsloth with Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training methods, plus GGUF conversion for local deployment. Includes guidance on the TRL Jobs package, UV scripts with PEP 723 format, dataset preparation and validation, hardware selection, cost estimation, Trackio monitoring, Hub authentication, model selection/leaderboards and model persistence. Use for tasks involving cloud GPU training, GGUF conversion, or when users mention training on Hugging Face Jobs without local GPU setup.
    0 installs
  57. Deep Agents Orchestration · catcorner22
    Subagent delegation, task planning, and approval gates inside the `deepagents` harness: SubAgentMiddleware and the `task` tool, TodoListMiddleware and `write_todos`, and HITL interrupts on subagent tool calls. Use when a Deep Agent must delegate to a named subagent, plan multi-step work, or gate a tool call on human approval. Scope boundary: this covers orchestration inside the `deepagents` harness only — harness setup and middleware selection belong to `deep-agents-core`, approval gates on a plain LangChain agent to `langchain-middleware`, `interrupt()` in a hand-written graph to `langgraph-human-in-the-loop`, and a multi-agent request that has not chosen a framework to `build-agents`/`eve`.
    0 installs
  58. Outlook Email Calendar · catcorner22
    Professional email and calendar in Microsoft Outlook: syllabus-to-calendar blocking, meeting invites, inbox triage, signatures, and student-professor communication tone. Use when managing Outlook mail, scheduling study blocks, or drafting academic/professional emails. Scope boundary: Teams chat/meetings → `teams-collaboration`; task lists in Planner/To Do → mention only; Gmail → not this pack.
    0 installs
  59. AI Transfer Architecture · catcorner22
    Router for architectural AI-transfer techniques: dual-axis reasoning, OODA context pipelines, proof DAGs, counterpoint, zoom levels, stage layout, warp/weft. Use when restructuring how AI reasons or formats output. Scope boundary: full catalog → `ai-transfer-ecosystem-primer`.
    0 installs
  60. Emergency Triage Compute · catcorner22
    Classify tasks Immediate/Delayed/Minor/Deceased before processing; allocate reasoning budget by stakes. Use at router/orchestrator layer. Scope boundary: human prioritization → `ooda-lean-loop`.
    0 installs
  61. Journalistic Attribution · catcorner22
    Source-first generation: retrieve evidence per claim before prose, inline attribution, strip unattributable claims. Use for factual writing and RAG outputs. Scope boundary: bibliography formatting → `citation-literacy`; triple-path check → `survey-triangulation`.
    0 installs
  62. Huggingface Local Models · catcorner22 bundle
    Use to select models to run locally with llama.cpp and GGUF on CPU, Mac Metal, CUDA, or ROCm. Covers finding GGUFs, quant selection, running servers, exact GGUF file lookup, conversion, and OpenAI-compatible local serving.
    0 installs
  63. Huggingface Tool Builder · catcorner22 bundle
    Use this skill when the user wants to build tool/scripts or achieve a task where using data from the Hugging Face API would help. This is especially useful when chaining or combining API calls or the task will be repeated/automated. This Skill creates a reusable script to fetch, enrich or process data.
    0 installs
  64. Containment Safety Layers · catcorner22
    Require independent safety layers (pattern, keyword, policy) that can each fail closed. Use for high-stakes generation, not everyday chat. Scope boundary — this is layered containment, not a jailbreak keyword skill; phase gating → `sterile-cockpit-context`; risk color → `underwriting-risk-gate`.
    0 installs
  65. Counterpoint Perspectives · catcorner22
    Generate 2–3 independent analytical voices with own logic, then harmonize into interwoven output — not pros/cons list. Use for multi-stakeholder or multi-framework analysis. Scope boundary: debate scoring → `debate-adjudication-voting`.
    0 installs
  66. Glass Annealing Hardening · catcorner22
    Staged delivery: high temp (everything flexible) → medium (structure locked) → cool (typos only). Use for long documents and multi-pass review. Scope boundary: faceting angles → `gemstone-faceting-refinement`.
    0 installs
  67. Hf Cloud Python Env Setup · catcorner22 bundle
    Set up an isolated Python environment for SageMaker / AWS work, with the right Python version and current boto3. Use this skill whenever Python code will be executed for a SageMaker deployment, training job, or other AWS automation — including when about to run `pip install` or invoke `boto3` for AWS work, when creating or activating a virtualenv for it, or when the user asks to "set up the environment" for a SageMaker/AWS task. Never use system Python and never `pip install` into it. Always isolate. This skill prevents the most common failure modes: wrong Python version, dependency conflicts, and stale SDKs. Scope boundary — AWS/SageMaker work ONLY. Do not claim general Python work: Hugging Face Jobs, TRL, evaluation and vision-training environments are managed by `huggingface-llm-trainer`, `trl-training`, `huggingface-community-evals`, and `huggingface-vision-trainer`, which use their own uv / PEP-723 inline-dependency conventions.
    0 installs
  68. Langgraph Human In The Loop · catcorner22
    Pause a LangGraph graph for a human: `interrupt()`, `Command(resume=...)`, approval and validation workflows, resuming multiple concurrent interrupts by id, keeping pre-interrupt side effects idempotent, and the 4-tier error-handling strategy. Use when a LangGraph run must stop for human input or approval. Scope boundary: `HumanInTheLoopMiddleware` on a `create_agent` agent belongs to `langchain-middleware`, approval gates inside the `deepagents` harness to `deep-agents-orchestration`, and the checkpointer that makes a resume possible to `langgraph-persistence`.
    0 installs
  69. Debate Adjudication Voting · catcorner22
    Independent agents score rubric dimensions with written ballots; synthesis agent explains weighting. Use for high-stakes evaluation. Scope boundary: counterpoint generation → `counterpoint-perspectives`; wine blend → `wine-blending-fusion`.
    0 installs
  70. Five Whys Failure Recovery · catcorner22
    On pipeline failure, drill five whys to root cause and log permanent system fixes — not prompt whack-a-mole. Use after hallucinations, format errors, or constraint misses. Scope boundary: human kaizen line → `ooda-lean-loop`; routing audit → `skill-library-audit`.
    0 installs
  71. Library Taxonomy Retrieval · catcorner22
    Dual retrieval: embedding similarity PLUS taxonomic adjacency in task ontology. Use when related concepts use different wording. Scope boundary: triangulation for facts → `survey-triangulation`.
    0 installs
  72. Wildlife Corridor Bridging · catcorner22
    Detect topic overlap across sessions; inject bridge summaries connecting isolated context islands. Use for long-term personal agents. Scope boundary: strata layers → `stratigraphy-memory`.
    0 installs
  73. Make Pr Easy To Review · catcorner22
    Prepare PRs for review by cleaning noisy history, improving PR descriptions, and adding reviewer guidance without changing code behavior. Use for "make this easy to review", "tidy this PR", "clean up commits", or "annotate the diff".
    0 installs
  74. Huggingface Vision Trainer · catcorner22 bundle
    Trains and fine-tunes vision models for object detection (D-FINE, RT-DETR v2, DETR, YOLOS), image classification (timm models — MobileNetV3, MobileViT, ResNet, ViT/DINOv3 — plus any Transformers classifier), and SAM/SAM2 segmentation using Hugging Face Transformers on Hugging Face Jobs cloud GPUs. Covers COCO-format dataset preparation, Albumentations augmentation, mAP/mAR evaluation, accuracy metrics, SAM segmentation with bbox/point prompts, DiceCE loss, hardware selection, cost estimation, Trackio monitoring, and Hub persistence. Use when users mention training object detection, image classification, SAM, SAM2, segmentation, image matting, DETR, D-FINE, RT-DETR, ViT, timm, MobileNet, ResNet, bounding box models, or fine-tuning vision models on Hugging Face Jobs.
    0 installs
  75. AI Transfer Quality Control · catcorner22
    Router for quality-control AI-transfer techniques: claim/evidence gates, preflight, critique loops, provenance, context gating, root cause, attribution, triangulation, proofreading marks. Use when verifying or hardening AI outputs. Scope boundary: full catalog → `ai-transfer-ecosystem-primer`.
    0 installs
  76. Chain Of Custody Provenance · catcorner22
    Token- or block-level provenance: which inputs, tools, prompt sections, and turns produced each output segment. Use when debugging AI failures or audit requirements. Scope boundary: claim-level sources → `journalistic-attribution`; orient logging → `ooda-adaptive-context`.
    0 installs
  77. Cross Pollination Structure · catcorner22
    Borrow a foreign genre skeleton (contract, tech spec) and plant the current content into it. Use when the native outline is weak. Scope boundary — graft a specialist passage → `orchard-graft-transfer`; multi-model blend → `wine-blending-fusion`.
    0 installs
  78. Just Intonation Calibration · catcorner22
    Calibrate generation parameters as just-intonation ratios by task type (factual, creative, code) instead of one global temperature. Use when the same model is too loose on facts or too stiff on drafts. Scope boundary — prompt wording itself → `prompt-optimizer`; compute budget class → `emergency-triage-compute`.
    0 installs
  79. Huggingface Community Evals · catcorner22 bundle
    Run evaluations for Hugging Face Hub models using inspect-ai and lighteval on local hardware. Use for backend selection, local GPU evals, and choosing between vLLM / Transformers / accelerate. Not for HF Jobs orchestration, model-card PRs, .eval_results publication, or community-evals automation.
    0 installs
  80. Huggingface Paper Publisher · catcorner22 bundle
    Publish and manage research papers on Hugging Face Hub. Use to create markdown research-article drafts, check or GET-index a paper page, link arXiv IDs into model/dataset/Space READMEs, and generate citations. Claim authorship, POST-index, and paper search belong in the huggingface-papers skill.
    0 installs
  81. Train Sentence Transformers · catcorner22 bundle
    Train or fine-tune sentence-transformers models across `SentenceTransformer` (bi-encoder; dense or static embedding model; for retrieval, similarity, clustering, classification, paraphrase mining, dedup, multimodal), `CrossEncoder` (reranker; pair scoring for two-stage retrieval / pair classification), and `SparseEncoder` (SPLADE, sparse embedding model; for learned-sparse retrieval). Covers loss selection, hard-negative mining, evaluators, distillation, LoRA, Matryoshka, and Hugging Face Hub publishing. Use for any sentence-transformers training task.
    0 installs
  82. Playwright Component Testing · catcorner22 bundle
    Set up component testing with Playwright using a story gallery — scaffold stories and a gallery dev page driven by the built-in mount fixture, no dedicated component-testing runtime. Use when asked to test React or Vue components in isolation with Playwright, or to migrate off @playwright/experimental-ct-react / -vue. Scope boundary — Playwright-based component testing only; for Jest + React Testing Library component tests in an Adobe App Builder project use `appbuilder-testing` instead.
    0 installs
  83. Building Pydantic AI Agents · catcorner22 bundle
    Build agents in Python with Pydantic AI — tools, capabilities (including on-demand loading), structured output, streaming, testing, and multi-agent patterns. Use when the user names Pydantic AI, when code imports `pydantic_ai` or uses its `Agent`/`RunContext`/`Tool` classes, or when a Python AI agent needs tools/capabilities, deferred capability loading, streamed output, YAML-defined agents, or agent tests. Scope boundary: this skill covers Pydantic AI in Python only — TypeScript/JavaScript agent work and framework-unspecified agent-building requests belong to `build-agents`/`eve`, and the `pydantic` validation library on its own is out of scope.
    0 installs
  84. AI Transfer Ecosystem Primer · catcorner22
    Router for the AI-transfer catalog (45 techniques, #1–50 with five merges) — gates, scaffolds, and pipeline stages. Use when hardening agents, RAG, multi-step chains, or when the user mentions transferable skills, discipline patterns, or AI quality plugins. Scope boundary: domain apps (college, M365) → those primers; human craft loops → `craft-systems-primer`.
    0 installs
  85. Gemstone Faceting Refinement · catcorner22
    Rotate refinement through clarity, precision, resonance, durability passes — flaws visible from new angles. Use instead of linear draft→revise→done. Scope boundary: annealing phases → `glass-annealing-hardening`.
    0 installs
  86. Differential Diagnosis Intent · catcorner22
    Rank 2–3 interpretations of the user query (literal, examples, comparison) with probabilities before answering. Use when the ask is ambiguous. Scope boundary — this is query triage, not medical advice (high-stakes domains → `underwriting-risk-gate`); OODA orient log → `ooda-adaptive-context`.
    0 installs
  87. Access Protected Vercel Deployment · catcorner22
    Access and test Vercel deployments protected by Vercel Authentication, SSO, or Deployment Protection. Use when curl, agent-browser, Playwright, or another automated request reaches a Vercel login or protection page; when a protected preview or production URL returns 401 or 403; when TRUSTED_SOURCES_ENVIRONMENT_MISMATCH appears; or when choosing between `vercel curl` and the `x-vercel-trusted-oidc-idp-token` header.
    0 installs
  88. Hf Cloud AWS Context Discovery · catcorner22
    Discover the user's local AWS context (active profile, region, account ID, caller identity) at the start of any AWS task. Use this skill before any other AWS work — deploying to SageMaker, creating resources, calling AWS APIs, or anything that touches an AWS account. Use it especially when the user has not specified a region or profile explicitly, when they say things like "use my AWS account", "deploy to AWS", "use my profile", or when about to make any AWS CLI or SDK call. Never guess the region or account ID — always use this skill to read it from the local configuration first.
    0 installs
  89. Huggingface Lora Space Builder · catcorner22 bundle
    Build and publish a Gradio demo on Hugging Face Spaces for a user-provided LoRA. Use when someone asks to create, generate, ship, or publish a Space, demo, Gradio app, or playground for a LoRA — including LoRAs for Qwen-Image, Qwen-Image-Edit, LTX-Video, Wan, FLUX, SDXL, or other diffusion base models. Also triggers when someone describes a LoRA they trained or hosts on the Hub and wants to share it. Covers picking the right base pipeline and `diffusers` inference recipe, designing a UI tailored to the LoRA's task and inputs (Union/multi-task control, edit, video, image, etc.), respecting model-card recommendations (trigger words, steps, guidance, LoRA scale, example inputs), and shipping to ZeroGPU hardware as a private Space by default.
    0 installs
  90. Progressive Resistance Critique · catcorner22
    Escalating self-critique passes: warm-up consistency, moderate alignment, working robustness, max falsifiability. Use instead of single shallow 'review your answer'. Scope boundary: post-delivery debrief → `after-action-review`; proof DAG → `proof-trees-reasoning`.
    0 installs
  91. Langsmith Online Eval Engineering · catcorner22 bundle
    Create LangSmith online evaluators one at a time: inspect recent traces in a tracing project, interview the user, propose grounded criteria, then build, test, attach via a run rule, and verify a single LLM-as-judge or code evaluator per pass. Use for evaluation attached to live LangSmith traces. Scope boundary: offline model benchmarking and leaderboards belong to `huggingface-community-evals`.
    0 installs
  92. Workfront Actions · catcorner22 bundle
    Use when writing or fixing the server-side code of a Workfront App Builder extension — the Adobe I/O Runtime action the React SPA calls to do work the browser can't. Reach for this whenever the user is: structuring or editing action code; deciding what shape an action returns so the frontend can tell success from failure (the {data,error} body); passing the IMS token through and calling an external API from the backend so credentials never reach the browser; calling Workfront's own Public API v21 (search/count, bulk PUT with the updates param, custom DE: field filters); calling Workfront Planning or another Adobe service; or troubleshooting why a deployed action can't read secrets (process.env is empty once deployed — inputs flow .env → config inputs → params). Also covers CommonJS-only structure, require-adobe-auth, and registering actions in app.config.yaml / ext.config.yaml. For generic non-Workfront action templates and SDKs see appbuilder-action-scaffolder.
    0 installs
  93. Hf Cloud Sagemaker Iam Preflight · catcorner22 bundle
    Ensure a usable SageMaker execution role exists before deploying or training. Use this skill whenever about to create a SageMaker endpoint, model, training job, or any resource that requires an execution role. Use it especially when the user has not provided a role ARN explicitly, when scripts are about to call `iam:CreateRole`, or when an AccessDenied error mentions an IAM action. Never blindly call `iam:CreateRole` — always check for existing roles first. This skill prevents the most common SageMaker deployment failure: trying to create IAM resources from an SSO principal that has no IAM write permissions.
    0 installs
  94. Hf Cloud Serving Image Selection · catcorner22 bundle
    Pick the right serving container for a SageMaker model deployment and find its current image URI. Use this skill whenever about to deploy a model to a SageMaker endpoint and an image URI needs to be chosen — including when the user says "deploy this LLM", "host this HuggingFace model", "serve this fine-tuned model", "deploy this embedding model", "host a reranker", "serve a sentence-transformers model", or when about to hardcode any container URI in deployment code. HuggingFace-curated Deep Learning Containers are ALWAYS preferred: HuggingFace vLLM (LLMs and generative rerankers), HuggingFace vLLM-Omni (multimodal), TEI (embeddings/cross-encoder rerankers), HF Inference Toolkit (other transformers). Generic images (AWS vLLM, DJL-LMI, SGLang) are used only when no HuggingFace image is compatible — never merely because they carry a newer version. Never hardcode a container URI from memory and never default to TGI. Prevents stale-image failures and wrong-region URIs.
    0 installs
  95. Workfront UI Extension · catcorner22 bundle
    Use when building or editing the React/Spectrum front-end SPA of a Workfront App Builder extension. Reach for this whenever the user is: registering or changing extension points in `ExtensionRegistration` — a Main Menu button, a left-panel (`secondaryNav`) item for a specific Workfront object type (Project, Task, Issue, Portfolio, Program), or a custom-form widget with specific height and width; adding a new route in `App.js` to match an extension point URL; reading the Workfront shared context to get the current user, `objCode`, `objID`, or `hostname`; calling a Runtime action from the SPA via `actionWebInvoke`; or debugging a widget or route that renders blank after being registered. Never call Workfront or Adobe APIs directly from the SPA — all API calls belong in a Runtime action (see `workfront-actions`).
    0 installs
  96. Hf Cloud Sagemaker Deployment Planner · catcorner22
    Plan and coordinate the deployment of a model to Amazon SageMaker AI. Use this skill whenever the user wants to deploy, host, serve, or expose a model on SageMaker or AWS — including phrases like "deploy a model", "host this LLM on AWS", "serve this embedding model", "deploy a reranker", "deploy a text-to-image / diffusion model", "host this for async inference", "create an endpoint", "serve my fine-tuned model", or any request that involves making a model available for inference on AWS. Use this even when the user is vague (e.g. "I just want to get this running on AWS, you figure it out"). Works for text-generation LLMs, embedding models, rerankers, classifiers, text-to-image / diffusion models — picks the right serving stack and chooses between real-time and async inference. This is the entry-point skill for SageMaker deployment work — it asks clarifying questions, picks a deployment pathway, and coordinates the other deployment skills.
    0 installs
  97. Workfront Local Testing · catcorner22 bundle
    Use when making Workfront load your locally running App Builder extension, or when a local extension that worked before has stopped appearing. Reach for this whenever the user is: trying to preview their local build inside Workfront before deploying; setting `extensionOverride` in localStorage but Workfront still shows the published version; seeing buttons, widgets, or left-panel items not appear in Workfront even though `aio app dev` is running; hitting a cert warning on localhost that blocks Workfront from loading the extension; seeing a local extension silently break after a Chrome update (Chrome 142+ blocks localhost connections); asking what value to set `extensionOverride` to and exactly where to set it in the browser; asking whether a custom-form widget should appear in the field picker; or wondering if Workfront admin rights are needed to see locally-loaded extension points. Separate from `appbuilder-workfront` (the umbrella) and `appbuilder-project-init` (scaffolding / dev server).
    0 installs
  98. Hf Cloud Sagemaker Production Defaults · catcorner22 bundle
    Create a SageMaker endpoint (real-time, real-time scale-to-zero, or async) with autoscaling, CloudWatch alarms, and tagging enabled by default. Use this skill whenever about to create a SageMaker endpoint, write deployment code that calls `create_endpoint`, or finalize a deployment after the image URI and IAM role are known. Provides deploy.py for real-time endpoints, deploy_ic.py for real-time endpoints that scale to zero instances via inference components, and deploy_async.py for async endpoints (also scale-to-zero). This is the last step in the SageMaker deployment workflow. Never generate a bare `create_endpoint` call without these defaults — endpoints without autoscaling or alarms are demos, not deployments.
    0 installs
  99. Eve · catcorner22 bundle
    eve framework guidance for durable AI agents and agent-powered applications. Use when creating, editing, or debugging an eve project, when the user explicitly asks for eve, or when the build-agents skill has selected eve as the default framework. Covers eve's filesystem-first runtime, durable sessions, tools, skills, connections, channels, sandboxes, subagents, schedules, evals, frontend clients, and Agent Runs observability. Do not use for incidental agent mentions, generic agent-building prompts, or established non-eve stacks unless the user asks for comparison or migration.
    0 installs
  100. Auth · catcorner22
    Authentication integration guidance — Clerk (native Vercel Marketplace, recommended for greenfield), Descope, Auth0, and Auth.js (NextAuth v5) for Next.js. Covers middleware/proxy auth patterns, sign-in flows, and Marketplace provisioning.
    0 installs