Results for “pr”

Make a web app agent-ready — propose a WebMCP tool manifest, integrate, verify in a real browser, heal; unrelated code stays untouched. Use for "webmcpify", "add WebMCP", or "expose app actions to AI agents".

Research-driven strategist who produces content strategies, scripts, and copy. Use for competitor analysis, trend research, content planning, scripts, copywriting, or brief validation — or when the user asks for the Strategist.

Use `analysis-agent` to identify domain ownership, invariants, state transitions, and cross-context effects when rules change or ownership is unclear. Skip presentation-only or question-only work with no domain behavior.

Use `analysis-agent` to analyze permissions, secrets, sensitive data, trust boundaries, and injection; `task-agent` to implement controls; and `review-agent` to assess evidence. Skip self-review and no-trust-impact work.

Evaluate RAG pipelines with Ragas — measure faithfulness, answer relevancy, context precision/recall, and noise sensitivity using LLM-as-judge metrics; run automated test suite generation with TestsetGenerator; integrate with LangChain, LlamaIndex, and CI pipelines.

Develop native iOS applications with Swift/SwiftUI. Masters iOS 18, SwiftUI, UIKit integration, Core Data, networking, and App Store optimization. Use PROACTIVELY for iOS-specific features, App Store optimization, or native iOS development.

Moves issues and external PRs through a state machine of triage roles — categorise, verify, grill, and write agent-ready briefs. Use when the user says "triage this issue" or wants agent-ready issue briefs.

Master software architect specializing in modern architecture patterns, clean architecture, microservices, event-driven systems, and DDD. Reviews system designs and code changes for architectural integrity, scalability, and maintainability. Use PROACTIVELY for architectural decisions.

Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always

After the learner demonstrates understanding of a concept, present near-transfer and far-transfer challenges. Use to test whether learning is portable or task-specific — this is what separates understanding from familiarity.

Design a multi-round questioning sequence for interrogating AI chatbot answers, tracking how responses shift and distinguishing genuine updates from sycophantic capitulation. Use when teaching students to probe AI critically.

LLM-assisted human-in-the-loop review. Make sense of a change, focus attention where it matters, test. Use when the user says "checkpoint", "human review", or "walk me through this change".

Visualize whether skills, rules, and agent definitions are actually followed — auto-generates scenarios at 3 prompt strictness levels, runs agents, classifies behavioral sequences, and reports compliance rates with full tool call timelines

Framework for scaling Python applications from a laptop to a cluster. Includes Ray Core for distributed computing, Ray Serve for model serving, Ray Tune for hyperparameter optimization, and Ray Data for distributed data processing.

Find out why a coding-agent skill won't fire — grade each SKILL.md A–F on activation, simulate which skill a prompt triggers, and flag collisions where one silently shadows another.

Design authentication and authorization strategy for a product or MVP. Use when the team needs sign-in methods, session model, user/workspace membership, roles, tenant boundaries, invitation flows, or permission enforcement plans.

LLM-assisted human-in-the-loop review. Make sense of a change, focus attention where it matters, test. Use when the user says "checkpoint", "human review", or "walk me through this change".

Capture actionable learnings that emerge during conversation — when the agent or user discovers that a skill, a set of skills, or a process needs to be updated based on what's happening in the current chat. Sub-skill of the learn-from orchestrator. Load when the user says "we should update the skill for this", "this should be a skill rule", "add this as a gotcha", "the skill should know about this", "update the process for this", "remember this for next time", "this is important for the skill". Also triggers when the agent notices a skill's guidance was wrong or incomplete, a process step failed or was unnecessary, a new pattern emerged, a guardrail was missing, a workaround became a pattern, or a debugging session reveals a gap.

Curates clinical-specialty term lists, generates IPA-tagged synthetic audio via TTS, and produces NeMo-format manifests for ASR benchmark evaluation.

Convert human-written CLAUDE.md files into a structured label format that AI models follow more reliably using fewer tokens.

Analyzes production code to find gaps in existing tests by reasoning about hypothetical mutations and checking whether tests would catch them.

Create, synthesize, and iteratively improve agent skills following the Agent Skills specification. Handles source capture, precision passes, authoring, registration, and validation.

Interact with MCP servers from the command line to discover, inspect, and call tools for external systems like GitHub, filesystems, databases, and APIs.

Generates a Playwright test from a user-provided scenario by recording browser interactions via Playwright MCP, then saves and runs the test until it passes.

Creates a declarative agent for Microsoft 365 Copilot by integrating an MCP server with authentication, tool selection, and configuration.

Analyze existing code files to generate a project-specific coding standards document, with options for templates, README insertion, and inconsistency detection.

Automates hypothesis generation and testing on tabular datasets using LLMs, combining data-driven discovery with literature integration for scientific research.

Store and process large N-dimensional arrays with chunking, compression, and parallel I/O, integrating with NumPy, Dask, and Xarray for cloud-native scientific computing.

Generate original music from text prompts using ElevenLabs AI, with control over genre, mood, instruments, and duration up to 10 minutes.

Build evaluation frameworks for agent systems with deterministic checks, regression suites, multi-dimensional rubrics, quality gates, production monitoring, and outcome measurement.

Store and query embeddings with metadata filtering, vector search, and full-text search using an open-source database that scales from notebooks to production.

Extend context windows of transformer models using RoPE, YaRN, ALiBi, and position interpolation techniques for processing long documents and implementing efficient positional encodings.

Aggregate and rank signals from multiple edge-finding skills into a prioritized conviction dashboard with weighted scoring, deduplication, and contradiction detection.

Drafts structured goal-loop prompts for long-running agent work with verifiable stop conditions, validation commands, and documentation requirements.

Numerical computing with MATLAB and GNU Octave for matrix operations, data analysis, visualization, and scientific computing, including script execution and syntax guidance.

Pythonic wrapper around RDKit for cheminformatics, simplifying SMILES parsing, standardization, descriptors, fingerprints, clustering, 3D conformers, and parallel processing while returning native rdkit.Chem.Mol objects.