Results for “pas”

Build and maintain a persistent markdown wiki that an LLM updates on the user's behalf, usually inside an Obsidian vault or git-tracked notes repo. Use when raw sources such as web articles, papers, meeting notes, transcripts, screenshots, or past analyses need to be turned into an interlinked knowledge base with immutable source files, LLM-written wiki pages, `index.md`, `log.md`, schema rules in `AGENTS.md` or `CLAUDE.md`, source summaries, query notes, and recurring lint passes. Triggers on: llm-wiki, personal wiki, obsidian wiki, research vault, knowledge base, source ingest, persistent notes, wiki maintenance, source summaries, query filing.

Automates X (Twitter) DM workflows: scan inbox, read conversations, generate persona-based replies, and send messages. Also supports searching users and starting new conversations with rate control and E2E passcode unlock.

Evaluates image captions by converting them into scene graphs and computing an F-score over semantic propositions, measuring how well a generated caption captures the meaning of an image compared to human references.

Set up the Discord channel — save the bot token and review access policy. Use when the user pastes a Discord bot token, asks to configure Discord, asks "how do I set this up" or "who can reach me," or wants to check channel status.

Use when a reference list needs APA 7 cleanup, when DOIs must be confirmed real against Crossref or PubMed, when the user asks whether AI-suggested citations actually exist, or when a manuscript needs a citation hygiene pass before submission or defense.

Apply-now consolidation of a drifted design system into one token/component SSOT. Use after an approved plan-uiux-unification pass, or when "clean up the design system now", "migrate to one button", or "resolve token conflicts". Plan-only burndown → plan-uiux-unification.

Evaluates code generation models across HumanEval, MBPP, MultiPL-E, and 15+ benchmarks with pass@k metrics. Use when benchmarking code models, comparing coding abilities, testing multi-language support, or measuring code generation quality. Industry standard from BigCode Project used by HuggingFace leaderboards.

Evaluates code generation models across HumanEval, MBPP, MultiPL-E, and 15+ benchmarks with pass@k metrics. Use when benchmarking code models, comparing coding abilities, testing multi-language support, or measuring code generation quality. Industry standard from BigCode Project used by HuggingFace leaderboards.

Set up the Discord channel — save the bot token and review access policy. Use when the user pastes a Discord bot token, asks to configure Discord, asks "how do I set this up" or "who can reach me," or wants to check channel status.

Analyze datasets to answer defined questions through statistical methods, trend identification, hypothesis testing, and correlation analysis. Use when the user needs evidence-backed findings or decisions from data; use exploratory-data-analysis instead for open-ended first-pass profiling before questions are defined.

Autonomously runs iterative experiment loops to optimize code against a measurable metric. Use when the user wants to improve execution time, memory usage, test pass rate, or any numeric performance goal across repeated experiments — NOT for one-shot bug fixes or simple code review.

Create library-grade Vue composables that accept maybe-reactive inputs (MaybeRef/MaybeRefOrGetter) so callers can pass plain values, refs, or getters. Normalize inputs with toValue()/toRef() inside reactive effects for predictable behavior.

Bypass Web Application Firewall protections using encoding techniques, HTTP method manipulation, parameter pollution, and payload obfuscation to deliver SQL injection, XSS, and other attack payloads past WAF detection rules.

Run customer interviews that uncover real problems using Mom Test rules: ask about their life, not your idea; focus on past specifics; and secure commitments instead of collecting compliments.

Performs a meticulous final pass on frontend work, checking visual alignment, typography, color contrast, interaction states, micro-interactions, content, icons, forms, edge cases, responsiveness, performance, and code quality to elevate work from shipped to polished.

Single source of truth for all contacts, PAs, and WhatsApp groups. Use when: looking up a phone number, email, address, PA, group JID, adding/updating a contact, or before sending any WhatsApp message. Reads and writes contact-list.md in the workspace root.

Integrates Mem0 Platform SDK for persistent memory in AI applications. Use when building agents or chatbots that need to remember user preferences, past interactions, or personalized context across sessions. Covers Python and TypeScript SDKs, plus LangChain, CrewAI, OpenAI Agents, LlamaIndex, AutoGen, and LangGraph integrations.

Perform an exhaustive, multi-pass proofread and copy-edit of an applied-microeconomics manuscript to top-economics-journal standards (AER, QJE, Econometrica, ReStud), checking prose, equations, table notes, footnotes, and citations for avoidable errors. Use before submitting or circulating an empirical economics paper.

Detects anomalous authentication patterns using UEBA analytics, statistical baselines, and machine learning to identify impossible travel, credential stuffing, brute force, password spraying, and compromised account behaviors across authentication logs.

Use to convert references to PNAS's numbered citation style — cited in order of appearance, a numbered reference list, full author lists, abbreviated journal titles. Provides formats for article/book/chapter/dataset/preprint and an author-date → PNAS conversion table. Late-stage style pass.

Consolidates project memory across harness and .memory/ with theme clustering, practical-expiry prune, ground-truth verify, and an adversarial second pass. Use when the user runs /memory:consolidate, asks to tidy/dedupe/prune memory, or reports redundant or stale memories. Also covers active writing during work.

User-story-driven test coverage audit and plan — no test writing in this pass. Use when "test coverage plan", "coverage audit", "traceability matrix", "fake-green tests", "uncovered user stories", "plan tests for critical flows", or "whats not tested". Mutation score / assertion theater → test-mutation.

Search X/Twitter profiles, tweets, trends, lists, communities, and Spaces through the AISA relay, then publish approved posts with OAuth. Use when: the user asks for Twitter/X research, monitoring, or posting without sharing passwords. Supports read APIs, authorization links, and media-aware posting.

Create a structured customer interview script with JTBD probing questions, warm-up, core exploration, and wrap-up sections. Follows The Mom Test principles — no leading questions, no pitching, focus on past behavior. Use when preparing for user interviews, creating interview guides, or planning discovery research.

Deploys and configures Zeek network security monitor to passively analyze traffic, generate structured logs, detect anomalous behavior, and create custom detection scripts for threat hunting and incident response.

Diagnose Sentry issues without copy-pasting stack traces. Uses the Composio CLI to pull issue details, events, breadcrumbs, and suspect commits, then maps the frames to local source so the agent can propose a fix directly.

Use when planning a COLT (Conference on Learning Theory) submission calendar backward from the single AoE paper deadline — proof-completion and verification milestones, writing and appendix-assembly passes, CMT logistics, the rebuttal window, decision aftermath, and PMLR camera-ready with conference presentation in early summer.

Search X/Twitter profiles, tweets, trends, and approved engagement actions through the AISA relay. Use when: the user asks for Twitter/X research, posting, likes, follows, or related workflows without sharing passwords. Supports read APIs, OAuth-gated posting, and follow or like operations.

Use when a paper is complete or near-complete and a holistic pre-submission audit is needed. Cross-cuts text, code, tables, figures, results, citations, and reproducibility in a single pass and produces a persistent audit report. Works standalone on papers written outside the plugin.

Analyze Base EVM tokens via the deluagent oracle. Pass a contract address or cashtag to receive a flat decision header (action, conviction, entry/stop/size, read) and a full cognition report. Tiered x402 pricing with sequential calls required.

Detects credential stuffing attacks by analyzing authentication logs for login velocity anomalies, ASN diversity, password spray patterns, and geographic distribution of failed logins using statistical analysis on Splunk or raw log data.

Reuse a running Chrome session for browser automation via Playwriter CLI + MCP. Use when the task depends on the browser the user already has open — existing logins, cookies, extensions, passkey-friendly flows, or live-tab continuity. Route repeatable fresh-browser or CI-style checks to `browser-harness` instead.

Manage project learnings. Review, search, prune, and export what gstack has learned across sessions. Use when asked to "what have we learned", "show learnings", "prune stale learnings", or "export learnings". Proactively suggest when the user asks about past patterns or wonders "didn't we fix this before?"

Searches and reads X (Twitter): profiles, timelines, mentions, followers, tweet search, trends, lists, communities, and Spaces. Publishes posts after the user completes OAuth in the browser. Use when the user asks about Twitter/X data, social listening, or posting without sharing account passwords.

Comprehensive expertise in cross-chain infrastructure, including LayerZero, Wormhole, Axelar, and custom bridge implementations. Covers omnichain token standards, message passing, bridge security, and cross-chain application architecture. Use when "cross-chain, bridge, LayerZero, Wormhole, Axelar, omnichain, multi-chain, chain abstraction, cross-chain messaging, token bridge, " mentioned.

Technical writing proficiency covering clarity principles, audience analysis, information structure, editing techniques, and style enforcement. Use when writing or improving any technical content — docs, specs, guides, or explanations. Also trigger for 'technical writing', 'write clearly', 'simplify this', 'rewrite for clarity', 'plain language', 'writing style', or 'editing pass'.