Automate SEO analysis with SEMrush -- research keywords, analyze domain organic rankings, audit backlinks, assess keyword difficulty, and discover related terms through the Composio SEMrush integration.

Automate Spotify workflows including playlist management, music search, playback control, and user profile access via Composio

Create strategic HTML presentations with Chart.js, design tokens, responsive layouts, copywriting formulas, and contextual slide strategies.

Systems engineering covering requirements management, the V-model lifecycle, integration planning, verification and validation (V&V), interface control, trade studies, and the NASA Systems Engineering Handbook. Spans the full lifecycle from concept through operations and disposal. Includes requirements decomposition, traceability matrices, configuration management, and technical performance measures. Use when managing complex system development, writing requirements, planning integration, or conducting V&V activities.

Meta-cognitive and practical strategies for learning any language -- learner autonomy, goal setting, strategy taxonomy (Oxford's SILL framework), memory strategies, cognitive strategies (note-taking, summarizing, analyzing, reasoning), compensation strategies, metacognitive strategies (planning, monitoring, evaluating), affective strategies (managing anxiety, self-encouragement), social strategies (collaboration, questioning, empathy), immersion design, study habit optimization, plateau diagnosis, and motivation maintenance. Use when designing a language learning plan, diagnosing a learner's stuck points, selecting study methods, or building self-directed learning skills.

Pragmatics and communicative competence across languages -- speech acts (Austin/Searle), Grice's conversational maxims and implicature, politeness theory (Brown & Levinson), face-threatening acts, discourse structure, turn-taking, repair strategies, register and formality, cross-cultural communication, communicative strategies (circumlocution, approximation, appeal for assistance), and the gap between grammatical competence and communicative performance. Use when teaching communication skills, analyzing cross-cultural misunderstandings, building conversational fluency, or understanding why grammatically correct sentences can be pragmatically inappropriate.

PMU observation pattern for agent health monitoring. Runs patrol loops, detects stalled agents, sends nudges, and escalates persistent failures to the mayor. Never modifies agent work or resolves conflicts.

Classical mechanics from kinematics through rotational dynamics and oscillations. Covers 1D/2D/3D motion, Newton's three laws, free-body diagrams, friction, projectile motion, circular motion, rotational mechanics, gravitation and orbits, work-energy theorem, conservation of momentum, collisions, and simple harmonic motion. Use when analyzing forces, trajectories, orbital mechanics, or any problem where objects move under deterministic forces at non-relativistic speeds.

Electromagnetism from Coulomb's law through Maxwell's equations and optics. Covers electric fields, Gauss's law, electric potential, capacitance, DC circuits (Ohm's law, Kirchhoff's laws), magnetic fields and forces, Biot-Savart law, Ampere's law, Faraday's law of induction, Lenz's law, Maxwell's equations in integral and differential forms, electromagnetic waves, the speed of light derivation, and optics (reflection, refraction, lenses, interference, diffraction). Use when analyzing electric or magnetic phenomena, circuit design, wave propagation, or optical systems.

Biological foundations of behavior and mental processes. Covers brain structure and function (cerebral cortex, limbic system, brainstem, cerebellum, lateralization), neurotransmitter systems (dopamine, serotonin, norepinephrine, GABA, glutamate, acetylcholine), neural plasticity (synaptic plasticity, neurogenesis, critical periods, experience-dependent change), and psychopharmacology (drug mechanisms, tolerance, dependence, major drug classes). Use when analyzing brain-behavior relationships, neurotransmitter function, neural development and plasticity, or pharmacological effects on cognition and behavior.

"The root cause was human error" is almost never a useful investigation finding. It stops the inquiry exactly where it should begin. This skill teaches the frameworks that treat human performance as a

FS-UAE emulator configuration and launch: hardware profiles, ROM management, WHDLoad integration, config generation, and state snapshots. Use when configuring emulation, managing ROMs, or launching Amiga software.

REST API design best practices. Use when designing APIs, choosing status codes, or creating endpoints.

Interrupt controller converting polled to proactive agent execution. Per-runtime strategies, configurable thresholds, Deacon heartbeat supervision. Fights LLM passivity bias.

OpenStack monitoring operations skill for deploying, configuring, and operating the cloud health monitoring stack. Covers Prometheus metric collection and scrape targets, Grafana dashboard provisioning and visualization, Alertmanager notification channels and routing, alerting rules for service health and resource exhaustion, service endpoint health checks, log aggregation strategies, SLA tracking with availability and response time percentiles, and capacity trend analysis from historical metrics. Use when deploying monitoring via Kolla-Ansible, configuring alert thresholds, troubleshooting blank dashboards, tuning noisy alerts, or analyzing cloud performance trends.

Triggers when: user mentions Minecraft server, block editing, world building, video display in Minecraft, image-to-blocks, SocketEdit, or bulk block placement.

Thermal engineering for infrastructure: heat transfer (conduction, convection, radiation), cooling load analysis for data centers, heat exchanger sizing via LMTD and e-NTU, PUE/TUE/WUE efficiency metrics, and airflow management patterns. Activates for thermal analysis, data center cooling design, heat exchanger sizing, efficiency calculations, and airflow management.

Detect and reap zombie processes using `/bin/ps`.

- **Team:** Growth team, weekly release cadence

**Role:** Founding Engineer (Full-Stack: React + Python)

- **Conversation type:** Performance feedback / behavior change

- **Role**: Senior Engineer (previously a top performer as recently as 6 months ago)

Produce a Managing Up Pack (manager profile, comms cadence, escalation plan, exec-ready memo).

Measure PMF: Sean Ellis survey, retention evidence, reference-customer signals, action plan. See also: retention-engagement (optimize post-PMF).

- **Objective:** Identify and fix the primary driver(s) of low trial-to-paid conversion (currently 4% vs. industry benchmark of 8-12%) through hypothesis-driven experimentation, then commit to a remed

- **Current metric**: 4% trial-to-paid conversion

Produce a Platform & Infrastructure Pack (capabilities plan, scaling triggers, execution roadmap).

**Company Profile:** B2B SaaS targeting operations teams at companies with 50-500 employees

Premier setup d'un nouvel utilisateur BOS. Déclenché automatiquement quand `Core/Profile.md` est vide ou n'existe pas.

Use when brainstorming a product or feature where multiple valid technology choices exist and the wrong one is costly, when the user asks for 'objectively best' or 'highest quality', or when the domain has tools/frameworks where marketing or popularity biases could mislead research agents. Also use when starting architecture decisions, evaluating tech stacks, or when the user mentions bias, vendor lock-in, hallucinated benchmarks, or wants research-backed decisions rather than default recommendations.

Comprehensive crypto project analysis from website, docs, and social media with investment profile.

>-

>

>

>

>

>

You have access to browser39, a headless web browser that fetches pages and returns token-optimized Markdown. Use it to browse the web, fill forms, manage cookies and localStorage, and query the DOM.

Token-optimized CLI proxy for developer operations (60-90% savings)

Self-learning SEO content pipeline: dashboard, multi-agent queue, token budgets, research → write → audit → publish. StoryBrand/Cialdini/JTBD-style frameworks; config-driven. Use for content factory, batch articles, or scaled publishing.

Working memory protocol — maintains context across sessions via CONTINUITY.md. Inspired by Loki Mode. Read at turn start, update at turn end. Captures mistakes and learnings to prevent repeating errors.

Optional power-up — detects oversized codebases/docs and suggests tobi/qmd for local semantic search. Bridges cm-continuity (working memory) with long-term document retrieval. Zero-config detection, non-intrusive suggestion.

Use when executing implementation plans — choose mode: batch execution with checkpoints, subagent-per-task, or parallel dispatch for independent problems.

Sync high-value dev knowledge (skills, decisions, lessons) into Google NotebookLM for cloud recall, podcasts, and flashcards. Pairs with Dockit/deep-search. Use for NotebookLM, nlm, knowledge base, skill sync, or cross-machine AI memory.

Progressive Disclosure skill index — efficient skill loading in 3 layers. Layer 1 (index, ~100 tokens) always loaded. Layer 2 (summary, ~300 tokens) loaded on context need. Layer 3 (full SKILL.md) loaded on execution only.

Find the best CodyMaster skill using the shipped indexes, profiles, docs, and contextual suggestions.

Refresh the current session's LOG with a fresh extraction. Use as the last step of /wrap, or any time the session has continued and you want the capture current. Idempotent — safe to invoke multiple times.

> This file defines how the agent behaves. Load it at session start.

Dashboard design system — colors, typography, spacing, components, and visual patterns for the session dashboard UI.

>-