Sssemil Skills

Compact the current conversation into a handoff document for another agent to pick up.

Co-operative workflow with OpenAI Codex CLI for plan review and pre-commit code review. Use this skill whenever Claude is about to present a plan to the user, propose an implementation approach, or commit code changes. Also triggers when the user mentions "codex", "co-op", "second opinion", "review with codex", or asks Claude to validate plans or changes before proceeding. This skill should fire before ANY plan is shown to the user and before ANY git commit — even if the user doesn't explicitly ask for Codex review.

Orchestrate repo-grounded grilling, specification review, cohesive ticket design, and work-store publication. Use when planning a feature, refactor, migration, or system change into a decision-complete parent plan and executable tasks through BRUTAL.md integrations.

Synthesize repo evidence and resolved requirements into a reviewed, decision-complete implementation specification. Use after requirements grilling, when converting a planning conversation or completed investigation map into the parent specification for a Brutal plan.

Shape output for a reader with ADHD: lead with the next action, number multi-step work, restate state across turns, suppress tangents, give specific time estimates, make wins visible. Invoke with /i-have-adhd; stays on until "stop adhd mode".

Repo-grounded requirements interrogation that resolves related planning decisions in batched rounds. Use when a feature, refactor, or system change still has material product or engineering choices, or when another Brutal planning skill needs a decision-complete requirements brief.

Drain a BRUTAL.md task graph through parallel isolated workers and stacked pull requests. Managed workers use append-only phases with fresh execution context.

Apply the Factory.ai visual design system to any UI. Use whenever the user asks for Factory-style, "factory.ai look", agent-native developer tooling aesthetics, or is building landing pages, dashboards, marketing sections, CLI install boxes, terminal mockups, or developer-tool UIs that should feel like Factory.ai / Vercel / Linear-adjacent dev brands. Triggers on phrases like "factory design", "factory style", "droid look", "make it look like factory.ai", or any task in a project using the color tokens `--color-accent-100`, `--color-base-*`, Geist Mono + orange `#ef6f2e`. Produces exact class strings, CSS variables, component shapes, motion, and enforcement rules — never guesses values.

Review a Rust PR, branch, or local diff against main. Focus on correctness, smaller code, idiomatic Rust, ownership, error handling, unnecessary clones, needless allocation, async safety, tests, and maintainability.

Perform a ruthless, multi-perspective code review of jj change `@-` or git `HEAD`.

Own one exact BRUTAL.md task or review finding through claim, isolated implementation, verification, stacked pull request publication, and an uncapped material-correctness review/fix loop. Managed workers execute one phase at a time with fresh context.

Stress-test business ideas against the "Reality's Moat" scar tissue framework. Use when a user describes a startup idea, product concept, or business model and wants honest evaluation of its defensibility in a world where AI makes building software free. Also use when comparing multiple ideas, evaluating pivots, or deciding build-vs-buy. Triggers include phrases like "is this idea defensible", "will this get commoditized", "stress test this", "what's the moat", "brutal honesty", or any request to evaluate a business idea's durability.

Decompose an approved specification into the smallest useful dependency graph of cohesive, decision-complete implementation scopes. Use when another Brutal planning skill needs executable tasks, or when the user wants an approved plan split into implementation tickets without publishing them yet.

Delegate coding work to OpenCode through safe-opencode. Use when Codex should plan, route the job to a suitable DeepSeek model, review git diff, and validate instead of writing the main code itself.

Comprehensive IDEA evaluation combining Reality's Moat scar tissue framework, Revenue Reality Check, VC Power-Law filter, and structured deep research pipeline. Point it at an IDEA.md for end-to-end analysis: defensibility ratio, revenue viability, VC scalability, validated research, and synthesized verdict with pivot recommendations.

Review an open pull request with Brutal multi-perspective scrutiny, snapshot-safe BRUTAL.md context, and provider-native findings. Supports normal, strict all-findings, and material-convergence passes.

Map and resolve planning work whose route is still hidden by research, prototypes, access, or decisions spanning multiple sessions. Use for large or foggy efforts that cannot yet produce a decision-complete Brutal specification and implementation tickets.

Design, review, prototype, and evaluate JEPA models, joint-embedding predictive architectures, V-JEPA/I-JEPA-style representation learners, action-conditioned world models, and JEPA-inspired models for time series or trading research. Use when the user asks for JEPA architecture design, masking/target choices, collapse prevention, latent probes, toy JEPA experiments, market-data JEPA research, world-model planning, or critique of a JEPA paper/model/implementation.

Write, rewrite, and audit technical procedures and descriptions with ASD-STE100 Simplified Technical English. Use for maintenance, operating, installation, inspection, troubleshooting, safety, software, API, specification, terminology, controlled-language, translation-source, vocabulary, and STE compliance-review tasks. Supports baseline, hybrid, and strict review modes; formal compliance requires the applicable official ASD-STE100 issue, official dictionary, project termbase, publication rules, and technical review.

Run a bounded provider-neutral pull-request review and finding-fix loop for up to three passes. Use when the user wants the existing safety-capped Brutal PR cleanup behavior.

Use when the user wants Rust duplicate-function detection and cleanup with funcvec, especially crate-by-crate scans, duplicate triage, boilerplate refactors, or safe dedupe fixes across a Rust workspace.

Structured deep research pipeline with confirmation gates and resume support. Generates outline, launches parallel research agents, produces validated JSON results and markdown report.

Review and fix an open pull request without a pass limit until a fresh review has no CRITICAL or MAJOR findings. When material findings exist, drain every severity opportunistically; a final MINOR/NIT-only pass is materially clean and may stop.

Maps public-company supply chains to uncover connected investment opportunities, risk exposures, and competitive landscapes. Use when analyzing a stock ticker or company name for supply-chain relationships, supplier/customer dependencies, cascading risk, competitors, adjacent industries, catalysts, or stock-market intelligence. Always uses current web research and primary financial sources where available.

Systematically review a project subsystem-by-subsystem with resumable state tracking. Creates CRITICAL/MAJOR finding tasks through the work store resolved from BRUTAL.md.

Review Rust codebase architecture and recommend improvements. Use when the user asks to assess Rust crate or module structure, public surfaces, trait/interface depth, coupling, testability, ownership leaks, async boundaries, unsafe isolation, or refactoring opportunities that make Rust code easier to reason about and verify.

Fix generated pull-request finding occurrences through the BRUTAL.md code-host adapter, one focused change at a time, with complete queue scans for material-convergence passes.

Create one-page high-level design diagrams in the soft rounded architecture style shown by the reference: pale blueprint background, mono text, blue-gray cards, arrows, data stores, stream bus, small vector icons, and side labels.

Reference for writing and editing skills well — the vocabulary and principles that make a skill predictable.

Create fixed-layout institutional brief PDFs with cream page fields, black/blue typography, Roman-numeral side rails, alternating footers, and dense linework diagrams calibrated to the supplied reference.