247 skills · sorted by relevance
Guides users through removing a stored fact with Codewhale’s Context Lens memory controls. It identifies the intended fact, explains the forget action, and distinguishes confirmed deletion from an action that has not yet completed.
Use SAELens to train and analyze sparse autoencoders, which break model activations into a small set of interpretable features. Explore pretrained features, evaluate reconstruction quality, troubleshoot training, and test how individual features influence generated text.
Use SAELens to train and analyze sparse autoencoders, which separate neural network activity into features that may represent recognizable concepts. Explore pretrained features, evaluate reconstruction quality, and investigate how individual features influence language model outputs.
Investigate how transformer language models produce predictions with TransformerLens. This skill guides inspection of intermediate values and attention patterns, plus experiments that replace internal values to test their effects and identify components involved in model behavior.
Investigate how transformer language models produce predictions with TransformerLens. This skill guides inspection of intermediate values and attention patterns, plus experiments that replace internal values to test their effects and identify components involved in model behavior.
Explore concepts learned by language models using sparse autoencoders, which separate internal activity into a small set of features. Analyze pretrained models, train custom autoencoders, assess reconstruction quality, and experiment with feature based output adjustments.
Plug-in vision for text-only models. Hard rule: when a file path or URL with an image extension (.png, .jpg, .jpeg, .webp, .gif, .heic, .heif) appears anywhere in the conversation (typed by the user, injected as a `[Image: source: <path>]` line, or inside a tag) and you cannot see that image's content, run this skill on it before any other approach: no self-built OCR, no PIL, no tesseract. Also triggers on pasted-image placeholders such as `[Image #1]` and `[Unsupported Image]`. If you can actually see the image, do not use this skill. When unsure, run `modlens guard` before the first read of a session: a deny verdict means the active model has native vision and must read the image itself. Runs the modlens CLI to convert the image into structured JSON evidence: every word transcribed, layout regions, semantics, visual clues. Also use when the user asks how to install, configure, or switch modlens providers (Gemini API key, OpenAI-compatible endpoints, Claude API or Claude Code CLI).
The English summary is being prepared. Showing the original description.
Run a structural-review debate between two lenses — lowy (volatility-based decomposition) and hickey (structural simplicity) — on the current diff. Each reviews independently, then they cross-examine every finding until they agree per-finding, and the agreed fixes are applied. Use when the user types `/lens-debate`, or asks to "have lowy and hickey review this", "run the lens debate", "debate this diff structurally", or "argue the structure of this PR until the lenses agree".
The English summary is being prepared. Showing the original description.
Audit Snapchat Ads measurement, mobile and app campaigns, creative, AR and catalog formats, audiences, and budgets. Produce prioritized recommendations with supporting evidence, missing inputs, and brand safety concerns clearly identified.
Turn code changes and system structure into animated SVG diagrams. The skill maps changed components, surrounding context, and ordered data flows, then helps prepare diagrams for sharing in pull requests or through an optional published link.
Apply 12 structured investing frameworks to evidence already collected. Each framework orders the questions to ask, defines reasons to reject a case, and identifies its limitations, helping explain why different approaches reach different conclusions.
Provides guidance for mechanistic interpretability research using TransformerLens to inspect and manipulate transformer internals via HookPoints and activation caching. Use when reverse-engineering model algorithms, studying attention patterns, or performing activation patching experiments.
The English summary is being prepared. Showing the original description.
Queries S3 object metadata, tracks bucket activity, audits object changes, searches annotations, and analyzes storage metrics using S3 Metadata system tables (journal, inventory, annotation) and S3 Storage Lens tables via Athena SQL. Applies when counting objects, finding recent uploads or deletions, identifying who wrote to a prefix, breaking down storage classes, finding objects by tag, searching annotation content, analyzing storage lens metrics, or enabling S3 Metadata tracking. Prefers system tables over raw S3 APIs (list-objects-v2, head-object) at scale. Trigger phrases: bucket activity, object count, who uploaded, track deletions, storage class breakdown, find by tag, search annotations, storage lens metrics, audit bucket changes.
The English summary is being prepared. Showing the original description.
WHAT: Draws a code change or part of a codebase as an animated architecture or data-flow diagram, on its own or in a pull request. WHEN: asked to diagram, visualise or explain a change or a system, or when a pull request should carry a diagram. KEYWORDS: PR Lens, diagram, architecture, data flow, visualise, visualize, pull request
The English summary is being prepared. Showing the original description.
WHAT: Explains a codebase, a folder, a feature, a command or a pull request to someone who knows nothing about it, as a PR Lens canvas whose walkthrough builds the picture one part at a time. WHEN: /eli5 <thing>, or asked to explain code simply, for a beginner, a new hire, a non-engineer, or 'like I'm five'. KEYWORDS: eli5, explain like I'm five, explain simply, beginner, onboarding, walkthrough, diagram, PR Lens
The English summary is being prepared. Showing the original description.
Your board of directors. Puts a business idea in front of a three-member board, each a sub-agent reading the idea through one published framework: the Offers lens (from Alex Hormozi's $100M Offers), the Monopoly lens (from Peter Thiel's Zero to One) and the Product lens (from Walter Isaacson's biography of Steve Jobs). Each member scores the idea, names the risks that would kill it and votes fund, fund with conditions, or pass. Use when the user says "test my business idea", "would this work", "pressure-test this", "what would a board say", "is this a good business", or starts the founder pack on a new idea.
The English summary is being prepared. Showing the original description.
Lens — Add a cognitive lens to any problem. It accepts a task description and produces an enhanced description that surfaces hidden dimensions, prerequisites, and lines of inquiry—the things you do not know you do not know. Use when the user asks to brainstorm, analyze, generate a skill, distill, or fuse, or when the input is too simple and needs to be expanded.
The English summary is being prepared. Showing the original description.
Use when a task needs the judgment of a camera-equipment repairer — diagnosing sensor dust vs. lens contamination, deciding whether a shutter is nearing end-of-life and should be replaced vs. repaired, calibrating autofocus and lens collimation, isolating image-stabilization mechanism faults, or sourcing parts for a discontinued body/lens.
The English summary is being prepared. Showing the original description.
Use when creating or configuring a CRM Analytics (Einstein Analytics) app — including app containers, lenses, datasets, data source connections, app sharing, and the row-level security that gates whether users see any data. NOT for choosing Reports vs CRM Analytics vs Tableau — use admin/einstein-analytics-basics. NOT for security predicate syntax, sharing inheritance or Analytics license assignment — use admin/analytics-permission-and-sharing.
The English summary is being prepared. Showing the original description.
Prospective failure imagination for a plan, decision, or running system. Operates in two modes — **plan mode** (a plan has not yet been committed to; imagine its catastrophic failure broadly) and **scenario mode** (a specific catastrophic scenario is posed against an existing system; investigate causes against the actual code and architecture). Spawns parallel pre-mortemers in isolation across three categories of lens: standard failure classes (technical, operational, estimation, scope, adoption, dependency, team, incentive, detection, reversibility, adversarial), 0-3 ad-hoc target-specific lenses the orchestrator names when warranted, and a first-principles lens that always runs to catch what the prescribed taxonomy misses. Synthesizes into a prioritized risk register with early-warning signals. Produces feedback only — no code, no tickets, no artifacts.
The English summary is being prepared. Showing the original description.
Fornece orientação para pesquisa de interpretabilidade mecanística usando TransformerLens para inspecionar e manipular internals de transformers via HookPoints e caching de ativações. Use ao fazer engenharia reversa de algoritmos de modelos, estudar padrões de atenção ou realizar experimentos de activation patching.
The English summary is being prepared. Showing the original description.
Use immediately after RBR confirms a root cause, or after any confirmed finding from security-audit-lens, legacy-investigation-lens, a scan skill, or a Critical/Required code-review finding, before considering the finding complete. Checks whether the confirmed defect is one instance of a structurally identical pattern elsewhere in the same file family, workflow, or business-domain area, and folds in or explicitly defers every other instance found. Mandatory for Architect — not an optional lens the agent judges when to apply.
The English summary is being prepared. Showing the original description.
Provides guidance for mechanistic interpretability research using TransformerLens to inspect and manipulate transformer internals via HookPoints and activation caching. Use when reverse-engineering model algorithms, studying attention patterns, or performing activation patching experiments.
The English summary is being prepared. Showing the original description.
Review code changes or documents through configured review lenses, each representing a different perspective. Findings identify the location, triggering condition, suggested fix, and potential consequence, with reports available as JSON, Markdown, or both.