Read project config from .agents.yml and .agents.local.yml with local overrides. Supports dot notation for nested fields. Invoke when agents/skills reference `config_read("field", "default")` pseudocode. Args format "FIELD DEFAULT".

Detect application-context mismatch after execution. Verifies applicability when correct output may not fit the actual context, producing contextualized execution. Type: (ApplicationDecontextualized, AI, CONTEXTUALIZE, Result) → ContextualizedExecution. Alias: Epharmoge(ἐφαρμογή).

Base rules for end users calling NVIDIA cuOpt (routing/LP/MILP/QP/install/server). Not for cuOpt internals — use cuopt-developer for those.

Create interactive Desmos graphs in Obsidian using desmos-graph code blocks. Use when visualizing functions, parametric curves, inequalities, or mathematical relationships with customizable styling and settings.

Formatting patterns for the Dinero.js money library. Use when displaying monetary values to users, formatting prices with currency symbols, handling locale-specific number formats, or working with non-decimal currencies. Triggers on toDecimal, toUnits, toSnapshot calls, or Intl.NumberFormat usage with Dinero objects.

Run a full discovery cycle from problem hypothesis to validated solution. Use when a team needs a structured path through framing, interviews, synthesis, and experiments.

# Dropbox Manager Skill

Resolve via Extended-Mind reverse induction. Reverse-traces decision coordinates from externalized substrate (codebase, rules, past sessions, user environment) and surfaces them through cycle-emergent dimension projections; user answers explicate the coordinates until intent crystallizes. Type: (AbstractAporia, Hybrid, REVERSE-INDUCE-CYCLE, IntentSeed × ExternalizedSubstrate) → ResolvedEndpoint. Directional dual to Periagoge. Alias: Euporia(εὐπορία).

Verify documentation coverage and generate missing docs interactively

Master error handling patterns across languages including exceptions, Result types, error propagation, and graceful degradation to build resilient applications. Use when implementing error handling, designing APIs, or improving application reliability.

Iterative refinement workflow for polishing code, documentation, or designs through systematic evaluation and improvement cycles. Use when refining drafts into production-grade quality.

Executes all tasks in a specific phase using wave-based parallel execution (max 4 agents per wave). Spawns small-coder and high-coder agents based on progress.json complexity. Updates progress.json after EACH wave so completed tasks immediately unblock dependents. Accepts phase number as argument (/execute-phase 3) or asks via AskUserQuestion. Triggers on: execute phase, run phase, build phase, develop phase, start phase.

Use this skill when users need to validate a launch plan, assess MVP scope, or determine if they're ready to execute. Activates for "validate my plan," "am I ready to launch," "is my scope too big," or when assessing action readiness.

Search and filter features by state, assignee, priority, epic, dependency, type, or category. Use when the user wants to find features matching criteria — "what's paused", "what's court working on", "what's in the auth-overhaul epic", "what depends on X".

# Feature Workflow Generation

Real-time market data feeds from 8 prediction market platforms

Fetch journal articles from Crossref published after a user-specified date and insert them into PostgreSQL `journals` with DOI deduplication. Use when incrementally ingesting journal metadata from `journals_issn` into `journals`.

Principal/Senior-level Flink playbook for stream processing architecture, stateful pipelines, event-time correctness, checkpointing, scaling, and operating low-latency data platforms. Use when: designing streaming systems, reviewing stateful Flink jobs, tuning event-time pipelines, or operating Flink in production.

Create structured build plans from feature requests or Flow IDs. Use when planning features or designing implementation. Triggers on /flow-next:plan with text descriptions or Flow IDs (fn-1, fn-1.2).

Génère une entité Doctrine avec repository selon principes Elegant Objects

Génère Story Foundry pour fixtures de tests

Génère classe Urls + Message CQRS + Handler

Designs engaging gameplay loops, economies, and progression systems, balancing challenge and reward for interactive experiences.

Use when working with Go formatting, line length, nesting, naked returns, semicolons, or core style principles. Also use when a style question isn't covered by a more specific skill, even if the user doesn't reference a specific style rule. Does not cover domain-specific patterns like error handling, naming, or testing (see specialized skills). Acts as fallback when no more specific style skill applies.

Master Alex Hormozi's offer creation framework from "$100M Offers" (2021). Build irresistible offers using the Value Equation, stacking, guarantees, and scarcity. Use when: Creating new product or service offers; Restructuring existing offers for higher conversions; Pricing premium products and services; Building offer stacks with bonuses and guarantees; Choosing target markets for maximum leverage

Data validation using Great Expectations. Expectation suites, checkpoints, and data docs for pipeline monitoring.

Hardens CockroachDB user privileges by auditing and tightening role-based access control, reducing admin grants, restricting PUBLIC role permissions, and applying least-privilege principles. Use when reducing excessive privileges, cleaning up admin access, or implementing RBAC best practices.

Analyze hashtag performance and discover trending tags. Use when: researching hashtags for posts; finding related hashtags; analyzing hashtag reach; planning hashtag strategy; competitor hashtag research

Think like Intel's legendary CEO. Apply Andy Grove's management operating system to maximize your team's output through leverage, OKRs, and systematic decision-making. Use when: **Scaling a team** when individual contribution isn't enough; **Performance management** to measure and improve output; **Meeting optimization** to make meetings productive; **Decision-making** in management contexts; **New manager transition** from individual contributor

Find deepening opportunities in a codebase, informed by the domain language in CONTEXT.md and the decisions in docs/adr/. Use when the user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more testable and AI-navigable.

Principal/Senior-level Jaeger playbook for distributed tracing architecture, sampling, storage backends, operational workflows, and production trace platform governance. Use when: designing tracing systems, operating Jaeger deployments, reviewing sampling and storage tradeoffs, or debugging distributed trace reliability.

Maintain Clawdbot's compounding knowledge graph under life/areas/** by adding/superseding atomic facts (items.json), regenerating entity summaries (summary.md), and keeping IDs consistent. Use when you need deterministic updates to the knowledge graph rather than manual JSON edits.

When the user wants to plan a product launch, feature announcement, or release strategy. Also use when the user mentions 'launch,' 'Product Hunt,' 'feature release,' 'announcement,' 'go-to-market,' 'beta launch,' 'early access,' 'waitlist,' 'product update,' 'how do I launch this,' 'launch checklist,' 'GTM plan,' or 'we're about to ship.' Use this whenever someone is preparing to release something publicly. For ongoing marketing after launch, see marketing-ideas.

Analyze recent code changes via git history and extract software engineering lessons. Use when the user asks 'what is the lesson here?', 'what can I learn from this?', 'engineering takeaway', 'what did I just learn?', 'reflect on this code', or wants to extract principles from recent work.

Analyze recent code changes via git history and extract software engineering lessons. Use when the user asks 'what is the lesson here?', 'what can I learn from this?', 'engineering takeaway', 'what did I just learn?', 'reflect on this code', or wants to extract principles from recent work.

Upgrades Python pip/poetry/pipenv dependencies with breaking change handling. Use when updating Python dependencies.

When the user wants to apply psychological principles, mental models, or behavioral science to marketing. Also use when the user mentions 'psychology,' 'mental models,' 'cognitive bias,' 'persuasion,' 'behavioral science,' 'why people buy,' 'decision-making,' or 'consumer behavior.' This skill provides 70+ mental models organized for marketing application.

How to launch distributed Megatron-LM training jobs on a SLURM cluster. Covers a minimal sbatch skeleton, environment-variable setup for torch.distributed.run, CUDA_DEVICE_MAX_CONNECTIONS rules across hardware and parallelism modes, container conventions, monitoring, and per-rank failure diagnosis.

Convert meeting discussions into clear, actionable notes with tasks, decisions, and follow-ups fo...

Simulate a full interview round with timed questions, persona-consistent follow-ups, and end-of-round assessment

MSW DefaultPlayer (character) management. Use the msw-general ModelBuilder to inspect/patch DefaultPlayer.model and Player.model, add/remove components, configure movement speed / jump force / HP / camera, and per-map-mode movement components. Use for DefaultPlayer model, player components, movement speed, jump force, HP, camera, physics. Keywords: player, DefaultPlayer, speed, jump, HP, camera, gravity, revive, respawn, character.

Show and toggle Navigator features. Auto-invoke when user says "show features", "enable/disable feature", "my navigator settings", or "configure navigator".

DigitalOcean networking patterns - VPCs, firewalls, load balancers, DNS

NMEA 0183 changes since training cutoff (latest: v4.30) — RTK quality values, FAA mode indicators, multi-GNSS extensions (GSA/GSV/RMC), satellite ID ranges. Load before working with NMEA 0183.

npm registry ops: login, whoami, names, publish; 1Password tmux.

Build an Opportunity Solution Tree from outcomes to opportunities, solutions, and tests. Use when a stakeholder request needs problem framing before you decide what to build.

# OrcaFlex Specialist Skill

Use when investigating slowness with baselines, profiler evidence, and ranked bottlenecks. Triggers:

Validate environment before any PM skill runs. Checks sqlite3, database, schema. Hard stop on failure — no fallbacks.

Podman changes since training cutoff (latest: 5.8.0) — Quadlet CLI management, OCI artifacts, multi-file install, BoltDB→SQLite migration, TLS remote. Load before working with Podman.

Building standalone interactive calculators and dashboards that embed in policyengine.org

Create product positioning and messaging frameworks with validation and iteration guidance.

Generate an executable PRD (Product Requirements Document) for Ralph from an idea file or description. Creates .ralph/prd.json with stories for autonomous development. Use when creating PRDs, generating user stories, planning features for Ralph, or converting ideas to executable specifications. Triggers: PRD, product requirements, Ralph stories, idea to spec, feature planning.

Shopping price comparison using Bright Data's web scraping infrastructure. Finds where a product is sold, for how much, and whether it's in stock — across Amazon, Walmart, eBay, Best Buy, Google Shopping, and any retailer URL — then ranks the offers into a single buy-recommendation table. Use this skill when the user wants to compare prices, find the cheapest place to buy something, do a price check, see "how much does X cost on Amazon vs Walmart", track an item's price, or decide where to buy a product. Handles product names, ASINs, and direct URLs, and is region-aware (country affects price, availability, and which retailers apply). This is consumer purchase-decision research — for analyzing a competitor's pricing *strategy*, use competitive-intel instead.

This skill should be used when the user asks to "configure prisma", "prisma config", "set up prisma", "prisma orm", "work with prisma", or mentions general Prisma ORM questions. For specific topics, focused skills may be more appropriate.

Progressive Web Apps - service workers, caching strategies, offline, Workbox

Create distributable Python packages with proper project structure, setup.py/pyproject.toml, and publishing to PyPI. Use when packaging Python libraries, creating CLI tools, or distributing Python code.

Use when creating Python projects, managing dependencies with uv, configuring pyproject.toml, building packages, or publishing to PyPI - covers project initialization, dependency management, and distribution; NOT for testing or performance (plugin:python@dot-claude)

Using lib-observability v1.0.0, Lerian's OpenTelemetry foundation (lib-commons, lib-systemplane, lib-streaming depend on it), in two modes. Sweep Mode detects DIY zap/slog logging, raw OTel metrics, hand-rolled redaction, and hard-coded attribute strings. Reference Mode catalogs the log, metrics, zap, redaction, and constants packages. Go-only. Skip for non-Go or assert/runtime/tracing.

Plan a strategic roadmap across prioritization, epic definition, stakeholder alignment, and sequencing. Use when turning strategy into a release plan that teams can execute.

# Ruby Pattern Detector Skill

Research ideation partner. Generate hypotheses, explore interdisciplinary connections, challenge assumptions, develop methodologies, identify research gaps, for creative scientific problem-solving.

Research ideation partner. Generate hypotheses, explore interdisciplinary connections, challenge assumptions, develop methodologies, identify research gaps, for creative scientific problem-solving.

Principal/Senior-level ScyllaDB playbook for shard-aware data modeling, consistency, compaction, topology, performance tuning, and operating high-throughput distributed wide-column systems. Use when: designing ScyllaDB schemas, tuning low-latency clusters, reviewing topology and repair posture, or operating ScyllaDB in production.

Seven Advisors decision council - structured multi-perspective deliberation for important decisions. Use when facing complex choices, strategic decisions, or when you need to think through a problem from multiple angles.

Seven Advisors decision council - structured multi-perspective deliberation for important decisions. Use when facing complex choices, strategic decisions, or when you need to think through a problem from multiple angles.

Signed Distance Functions (SDFs) in GLSL—2D/3D shape primitives, boolean operations (union, intersection, subtraction), smooth blending, repetition, and raymarching fundamentals. Use when creating procedural shapes, text effects, smooth morphing, or raymarched 3D scenes.

Escape the build trap and endless backlogs. Use Basecamp's methodology to ship meaningful work in 6-week cycles with fixed time, variable scope. Use when: **Product planning** to replace endless backlogs; **Feature development** with clear time boundaries; **Team autonomy** when you want self-directed teams; **Scope management** when projects tend to balloon; **Startup development** with limited resources

Apply Edward de Bono's parallel thinking framework (1985) to make better decisions by examining ideas from six distinct perspectives systematically. Use when: **Making complex decisions** that require multiple perspectives; **Evaluating new products, offers, or strategies** before launch; **Breaking out of analysis paralysis** with structured thinking; **Running productive meetings** where everyone thinks in the same direction; **Balancing optimism with caution** in strategic planning

Decompose large tasks across parallel agents — use for migrations, multi-file refactors, or batch work

Generate Peninsula School District Standard Operating Procedures using the official PSD SOP template and conventions. Conducts a structured interview to gather all required information before drafting. Use when creating new SOPs, updating existing procedures, or drafting operational documentation for any district department. Triggers on requests to create SOPs, standard operating procedures, operational procedures, process documentation, or procedural guides for PSD.

Principal/Senior-level Spark playbook for batch and streaming architecture, data layout, shuffle control, cost-efficient compute, reliability, and operating large-scale data processing platforms. Use when: designing Spark workloads, tuning jobs, optimizing cluster economics, or operating Spark platforms in production.

SQLite changes since training cutoff (latest: 3.51) — json_pretty, unistr, jsonb_each/jsonb_tree, percentile aggregates, multi-arg iif, numeric underscores, sqlite3_setlk_timeout. Load before working with SQLite.

Stacking lottery pots on stackspot.app — pool STX into pots that get stacked via PoX, VRF picks a random winner for sBTC rewards, and all participants get their STX back. Mainnet-only.

This skill should be used when working with Steam on Linux - managing non-Steam game shortcuts, configuring Proton/Wine compatibility, parsing VDF files, or finding Steam paths and prefixes. MUST BE USED when user mentions Steam launch options, modifying shortcuts.vdf, Proton environment variables (PROTON_*, WINE*), Battle.net/Blizzard games on Linux, or RTX 4000+ performance fixes. ALSO USE when troubleshooting Proton/Wine game issues (black screen, game won't launch, launcher issues, CEF/Chromium rendering problems).

# Structural Analysis Skill

Use when implementing gesture composition (simultaneous, sequenced, exclusive), adaptive layouts (ViewThatFits, AnyLayout, size classes), or choosing architecture patterns (MVVM vs TCA vs vanilla, State-as-Bridge). Covers advanced SwiftUI patterns beyond basic views.

SWOT strategic analysis examining Strengths, Weaknesses, Opportunities, and Threats. Use for strategic planning, competitive analysis, career decisions, or evaluating opportunities.

Principal/Senior-level Tempo playbook for trace architecture, storage strategy, sampling-aware operations, tenant governance, and operating large-scale trace backends. Use when: designing trace storage, correlating observability workflows, tuning Tempo, or operating trace platforms in production.

Terragrunt-specific orchestration patterns — CLI redesign migration (run/run --all, --terragrunt-* flag removal, TG_* env vars, strict controls), config composition (include, locals, inputs deep-merge, generate blocks), dependency wiring (mock_outputs semantics), run --all safety, hooks, and the new terragrunt.stack.hcl. Use when working with Terragrunt, `terragrunt.hcl`, `terragrunt.stack.hcl`, the deprecated `run-all`, `--terragrunt-*` flags, `TERRAGRUNT_*` env vars, `include` blocks, `dependency` blocks, or `terragrunt run --all`.

Control tmux sessions/panes for interactive CLIs: list, capture output, send keys, paste text, monitor prompts.

Use this skill when creating, managing, or working with Conductor tracks - the logical work units for features, bugs, and refactors. Applies to spec.md, plan.md, and track lifecycle operations.

Find and validate startup ideas by mining user complaints, crafting premises, and navigating the idea maze. Use when discovering product opportunities, validating ideas, shaping solutions, researching user pain points, or exploring what to build.

Windows local privilege escalation playbook. Use when you have low-privilege shell access on Windows and need to escalate via token abuse, Potato exploits, service misconfigurations, DLL hijacking, UAC bypass, or registry autoruns.

Systematic performance analysis and optimization. Use when things are slow, need optimization, or preparing for scale.

Create a compelling startup pitch deck that follows the structure proven to raise billions from top investors. Master the YC and Sequoia formats that get founders funded. Use when: **Fundraising** to create investor pitch decks; **YC application** to structure your narrative; **Demo Day prep** to craft your 2-minute pitch; **Angel investors** to communicate your opportunity; **Partnership pitches** to structure compelling asks

Use when a YouTube playlist is involved: pasted playlist links or IDs, requests to list playlist videos, browse playlist contents, or work through a playlist for transcripts or research. Also use when the user wants all videos from a series, course, or collection. Not for creating playlists or account management.

Automatically manage focus sessions, breaks, and hyperfocus protection. Uses ADHD-optimized Pomodoro technique with flexible timers, health reminders, and gentle interruptions. Protects against hyperfocus burnout while maximizing productive time.

Manage the PAI Knowledge Archive — a curated, typed graph of notes across four entity domains: People, Companies, Ideas, and Research. Operations: search (3-pass: lexical + frontmatter + wikilink), add (creates note with mandatory typed cross-links), harvest (KnowledgeHarvester pulls from PAI sources), develop (surfaces seedling notes for enrichment), ingest (fetch URL or file, create primary note, ripple updates to related notes), contradictions (find conflicting claims via tag-overlap pairs), graph (stats or 2-hop traversal via KnowledgeGraph.ts), retrieve (BM25-lite compressed context via MemoryRetriever.ts), mine (SessionHarvester extracts memory candidates from recent conversations). Every note ships with typed related: frontmatter links (8 relationship types: supports, contradicts, extends, part-of, instance-of, caused-by, preceded-by, related). USE WHEN knowledge, knowledge base, search knowledge, what do we know about, archive, harvest, knowledge status, develop note, add to knowledge, ingest, contradictions, knowledge graph, graph, retrieve, mine conversations. NOT FOR session/ISA context recovery (use ContextSearch).

Implement signal-based reactive state management in Angular v20+. Use for creating reactive state with signal(), derived state with computed(), dependent state with linkedSignal(), and side effects with effect(). Triggers on state management questions, converting from BehaviorSubject/Observable patterns to signals, or implementing reactive data flows.

Tools for reading and analyzing Arduino serial monitor output for enhanced debugging. Provides real-time monitoring, data logging, filtering, and pattern matching to help troubleshoot Arduino sketches using arduino-cli or Arduino IDE.

Understand authentication and authorization defects in AI-generated code including insecure password storage, broken session management, and access control bypasses. Use this skill when you need to learn about auth vulnerabilities in AI code, understand why AI suggests MD5/plaintext passwords, recognize broken session patterns, or identify access control gaps. Triggers include "auth vulnerabilities AI", "password storage AI", "session management", "broken access control", "authentication defects", "MD5 passwords", "session hijacking", "authorization bypass".

Manage significant changes during sprint execution. Use when the user says "correct course" or "propose sprint change"

Autonomous bounty hunting — scan open bounties, match to your skills, claim and track work

Use when user requests creative work - creating features, building components, adding functionality, or modifying behavior. Activates BEFORE APEX Analyze phase to refine requirements through structured questioning.

# Brainstorming Coach Protocol