AI & ML

jscraik Bundle

Create, validate, install, fold, or troubleshoot Codex subagent role TOML, agents-table config, discoverability wiring, and duplicate-role merges. Use when a user asks for a Codex agent role, reviewer agent, role config, TOML role file, subagent setup, or overlapping agents to merge.

jscraik Bundle

Scaffold hook packs, validate hooks.json schema, verify hook script permissions, migrate hook configuration, and troubleshoot Codex hook execution errors. Use when creating, auditing, upgrading, or validating Codex hook packs, hooks.json files, hook scripts, SubagentStart/SubagentStop lifecycle hooks, PreToolUse/PostToolUse/PreCompact hooks, Stop claim checks, or repo-local/user-level .codex hook installs.

dykyi-roman Skill

Maps domain model components — Entities, Value Objects, Aggregates, Services, Events, Repositories. Builds Ubiquitous Language glossary connecting code names to business terminology.

jscraik Bundle

Builds a project glossary that maps everyday wording to canonical terms, repository actions, and reusable engineering rules. Use when a user asks "what does X mean here?", "define our terms", "standardize this naming", "turn this phrase into a repo action", "grill the domain language", or whether a local correction should apply to similar code.

jscraik Bundle

Create, review, and validate an alignment checkpoint. Use when a request is ambiguous, high-stakes, multi-step, or requires explicit approval before tool use.

jscraik Bundle

Check if a repository or agent-facing product surface is ready for AI coding agents. Use when you need to audit repo agent compatibility, review AGENTS.md, find missing test/build commands, evaluate docs quality, assess tool/action parity, or produce a file-evidence scorecard with specific fixes.

jscraik Bundle

Plan, execute, and validate production deployments when rollout safety, health checks, observability, rollback, or production-parity verification is required.

jscraik Bundle

Analyze, compare, and recommend a Codex build primitive. Use when the user is packaging or automating a workflow and the right primitive is unclear.

jscraik Bundle

Create, review, and maintain gold-standard Skills SDK eval scenarios before internal evals, dry Tessl staging, or live private Tessl scoring. Use when creating or updating a skill, writing skill tests, adding eval cases, importing KnowledgeOS or Tessl suggestions, checking scenario drift, or hardening evals that are too easy.

jscraik Bundle

Analyze recent Codex session evidence for repeated manual workflows and route them to skills, subagents, validators, or no artifact when Jamie asks what he keeps doing manually.

jscraik Bundle

Create, repair, and validate uv Python project setup. Use when initializing Python apps or libraries, managing uv dependencies, virtual environments, or CI-ready uv workflows.

jscraik Bundle

Use when a project or Codex runtime needs environment TOML created, triaged, or updated with safe setup, actions, exec-server providers, and validation evidence.

jscraik Bundle

Use when designing, reviewing, or updating Codex app automations, cron jobs, scheduled tasks, recurring runs, or heartbeat follow-ups.

jscraik Bundle

Create evidence-backed HE reframe migration programs. Use when structural drift, routing ambiguity, or source-prompt gaps need phased rollback-safe execution.

jscraik Bundle

Compress HE cognition artifacts into evidence-backed strategy. Use when intent, review, triage, ADR, core, or source-prompt comparison evidence needs durable direction.

jscraik Bundle

Review code architecture, code quality, dependency graphs, coupling, technical debt, modularization, ownership, and test seams. Use when refactors, restructuring, tightly coupled code, or architecture decisions need proof-backed options.

jscraik Bundle

Review and validate completion claims. Use when you are about to say work is complete, fixed, passing, pushed, or ready for review.

dykyi-roman Skill

Analyzes PHP code for access control issues. Detects inline role checks, hardcoded permissions, mixed ACL/RBAC models, missing Voter/Policy pattern, and authorization logic in controllers.

jscraik Bundle

Defensive review of AI-agent skills, plugins, and tools using Liran Tal's security principles. Use when assessing provenance, permissions, data exposure, sandboxing, or approval boundaries before adoption.

jscraik Bundle

Generate closure-grade HE eval and drift proof for one execution slice. Use when Linear, milestone, or source-prompt closure needs validation evidence.

jscraik Bundle

Convert approved HE cognition into small live-ready Linear execution tracking. Use when strategy, reframe, plan, bug, or source-prompt evidence needs scoped issue, milestone, or project routing with explicit confirmation before any live mutation.

jscraik Bundle

Explains the Product Brain talk and helps design curated product-memory systems for AI-assisted product work: knowledge structure, provenance, synthesis cadence, ownership, and agent-ready context packets. Use when the user asks about product context for AI, product knowledge management, product documentation for LLMs, or building a maintained product brain.

jacob-balslev Skill

Use when auditing for recurring issues, clustering errors, detecting drift from conventions, or when an agent keeps fixing symptoms instead of root causes. Covers the Observe -> Cluster -> Name -> Codify -> Detect -> Prevent loop, grep-based audits, normalize-then-hash error clustering, board-health patterns, design-token and heading drift, domain-encoding patterns, eval-as-pattern-tests, 5 Whys, pattern lifecycle states, and drift traps. Do NOT use for one-off bug localization without recurrence, or for designing the classification system itself; this skill detects violations of conventions that already exist. Do NOT use for review this code for semantic correctness. Do NOT use for find where the user-auth helper is defined. Do NOT use for design a MECE classification taxonomy for our error catalogue. Do NOT use for investigate why this single failing test is breaking. Do NOT use for trigger an alert when CPU exceeds 80% for 5 minutes. Do NOT use for rewrite this function to be cleaner.

jacob-balslev Skill

Use when deciding WHICH free or cheap agent model to route a piece of work to (e.g. MiniMax M3 Free, NVIDIA Nemotron, GLM, GPT-5 Nano, or another OpenCode Zen free-tier model), what each is good at, where its quality ceiling sits, and when to escalate the same work to a frontier model instead. Covers cost-routing: matching deterministic/mechanical/high-volume work to the cheapest model that clears its bar, and the hard rule that quality-creating and quality-judging work never goes to a free/cheap model. Do NOT use for choosing or operating the OpenCode runtime itself (use `opencode`), for authoring the agent loop (use `autonomous-loop-patterns`), or for GitHub Copilot premium-request budgeting (use `github-copilot`). Do NOT use for how do I invoke opencode from a script? Do NOT use for how do I write the retry loop for my agent? Do NOT use for how many Copilot premium requests will this cost?

jacob-balslev Skill

Use when designing how a database keeps multiple copies of its data in agreement across nodes for availability, read scaling, and disaster recovery: the three foundational topologies (single-leader / primary-replica, multi-leader / multi-primary, leaderless / quorum), synchronous vs asynchronous replication and the replication-lag trade-off, log shipping vs statement replication vs trigger-based replication, the read-after-write consistency problem and its mitigations (sticky session, read-from-leader, monotonic reads), the failover model and split-brain risk, and the relationship to the CAP/PACELC choices the topology realizes. Do NOT use for horizontal partitioning across nodes (use sharding-strategy), the CAP theoretical frame itself (use cap-theorem-tradeoffs), single-node transactional guarantees (use transaction-isolation), or query tuning (use query-optimization).

jacob-balslev Skill

Use when designing or auditing deterministic health tooling for a skill library: schema/source validation, manifest/protocol parity, relation integrity, routing health, drift/export checks, supply-chain scanning, and eval-verdict evidence honesty. Covers checker ownership, the library-as-database model, release gates, and maintenance workflows after batch skill changes. Do NOT use for authoring one SKILL.md (use `skill-scaffold`), repo conformance audits (use `graph-audit`), generic lint rules (use `lint-overlay`), or reviewing checker code (use `code-review`). Do NOT use for scaffold a new SKILL.md for our team''s deploy procedure. Do NOT use for audit this Skill Graph repo for schema conformance and dangling relation targets. Do NOT use for the manifest sample drifted from the generator — find the mismatch. Do NOT use for improve this prompt''s wording to get better outputs. Do NOT use for review this AI-generated PR for correctness. Do NOT use for review this PR that changes scripts/skill-lint.js.

jscraik Bundle

Answers questions about, retrieves safe excerpts from, explains concepts from, and summarizes key arguments in Birgitta Böckeler's talk "State of Play: AI Coding Assistants" (AI Native Dev conference, 2026). Use when the user asks about the last 12 months in AI coding assistants, model-task fit, LLM statelessness, context window and attention trade-offs, coding harnesses, harness engineering/context engineering, skills/MCP/sub-agents/plugins/hooks, guide-and-sensor feedback loops, background agents and swarms, review bottlenecks, AI coding costs, cognitive surrender, or risk-based supervision of coding agents.

jacob-balslev Skill

Use when reasoning about agent autonomy levels, designing auto-improve loops, evaluating AI-generated code quality, or measuring agent productivity in an LLM-assisted codebase. Covers Karpathy's three eras of software (1.0 explicit / 2.0 learned / 3.0 natural-language), the vibe-coding-vs-agentic-engineering distinction, the 0–5 autonomy slider with task-type recommendations, the one-asset / one-metric / one-time-box AutoResearch loop, Software 3.0 productivity metrics, and the documented quality regressions of ungated AI-generated code (the 'vibe hangover'). Do NOT use for choosing a specific autonomy-loop topology (use `agent-engineering`), for the per-prompt authoring discipline (use `prompt-craft`), or for reviewing the AI-generated code that comes out of a Software 3.0 workflow (use `code-review`). Do NOT use for improve this specific prompt for the grader. Do NOT use for review this AI-generated PR for correctness. Do NOT use for design the checkpoint state machine for our loop.

jacob-balslev Bundle

Sweller's Cognitive Load Theory (CLT) for agents reviewing skill bodies, prompts, docs, dashboards, and agent outputs for avoidable cognitive burden. Working memory holds ~4 chunks; CLT splits load into intrinsic (irreducible difficulty), extraneous (avoidable load from poor presentation — ELIMINATE), and germane (the schema-building work applied to intrinsic load — PROTECT). Use when writing a SKILL.md body, designing prompts (am I asking the model to hold too much at once?), building dashboards (per-screen cognitive budget), authoring docs (is intrinsic load segmented?), or checking whether modern features (long context, structured outputs, prompt caching, subagents) actually reduce load or just move it. Do NOT use for retrieval/session working-set design (use context-management), token budget and compaction timing (use context-window), prompt engineering tactics (use prompt-craft), or token-efficient representation (use compression).

jacob-balslev Skill

Use when reasoning about baseline application-security properties: threat modeling, trust boundaries, Saltzer and Schroeder design principles, input validation, authentication vs authorization, secrets handling, secure-by-default choices, least privilege, defense in depth, and OWASP vulnerability classes as recurring failure modes. Covers cross-cutting decisions about what is trusted, where validation belongs, where authn/authz checks live, and how to bound blast radius. Do NOT use for LLM-specific prompt injection or agent-tool authority (use prompt-injection-defense), OWASP-category deep code review (use owasp-security), vendor webhook mechanics (use webhook-integration), cryptographic primitive implementation or key-management mechanics (use vendor/KMS/library docs), compliance/legal artifacts, or the social/organizational side of security. Do NOT use for configure a specific SAST or dependency scanner (use the scanner docs, then owasp-security for review).

jacob-balslev Skill

Use when reasoning about tests that specify universal properties of code rather than specific input-output pairs: the forall(input) → property quantification, the generator/shrinker primitives that produce inputs and minimize failing cases, the four-rules-of-simple-design analog (commutativity, associativity, idempotence, round-trip, oracle, invariant), the difference between example-based tests (one input, one assertion) and property-based tests (many generated inputs, one universal claim), why property tests find bugs example tests don't, the shrinking discipline that produces minimal failing cases, and the trade-off between generator complexity and bug-finding capacity. Do NOT use for specifying one concrete behavior with one input (use example-based tests under testing-strategy), for fuzz-testing focused on crashes (use fuzz-testing), for mutation testing as a test-suite quality signal (use mutation-testing), or for model-based testing of state machines (use state-machine-modeling).

coderabbitai Bundle

Vercel AI SDK expert guidance. Use when building AI-powered features — chat interfaces, text generation, structured output, tool calling, agents, MCP integration, streaming, embeddings, reranking, image generation, or working with any LLM provider.

jscraik Bundle

Use when the user asks about Steve Ruiz's AI Native DevCon talk on tldraw, Make Real, annotations as prompt input, canvas workflows, tldraw computer, and agents collaborating on an infinite canvas.

jscraik Bundle

Use when the user asks about Ian Thomas's talk "AI Native Engineering" (Meta / Reality Labs / Horizon Experiences) — including questions about Meta's AI4P (AI For Productivity) programme, the 6-dimension / 5-level AI maturity model and self-assessment workshop, how Horizon rolled out AI tooling across 500+ engineers, engineering excellence as an adoption vehicle, anti-test-slop, autonomous code mods, the DRS risk-scoring tool, the Horizon MCP server, vanity metrics vs real productivity, or applying Thomas's ground-up-plus-top-down adoption playbook to their own org.

jscraik Bundle

Explains Kevin Groetzinger's Skills Everywhere talk and helps teams operationalize reusable skills: trigger design, ownership, discoverability, maintenance, quality review, and adoption loops. Use when the user asks about skill design, skill rollout, skill sprawl, shared agent instructions, or making skills reliable across a team.

jscraik Bundle

Answers questions about, summarises key insights from, and applies the security guidance of Joseph Katsioloudes's talk 'Code Security Reinvented: Navigating the era of AI'. Use when the user asks about AI-assisted secure coding, MCP servers, skills, agentic workflows, the 1-to-100 security-to-developer gap, start left vs shift left, task flows, LLM-as-judge, supply-chain decisions, AI-assisted fuzzing, hallucinations and non-determinism in AI security review, GitHub Security Lab resources, or applying the talk's security framework to AI-assisted development.