oimiragieo

Agent frontmatter enhancements — disallowedTools, mcpServers scoping, fork_eligible field

Context management — pre-compact persistence, threshold alignment, microcompact/circuit breaker detection

Hook enhancements — updatedInput for bash safety prefixes, suppressOutput for verbose blocks, denial-based routing feedback

Hook system optimization — async conversion, consolidation, deduplication, new hook events

Memory index discipline — cap enforcement, pruning, archival, health reporting

Prompt assembler optimization — sorting, memoization, cache-break detection, integration tests

Compresses and merges CLAUDE.md and rules files to fit under the 40K character cap

Security hardening — path normalization, UNC blocking, pattern alignment with Claude Code

Use when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a frontend interface. Covers websites, landing pages, dashboards, product UI, app shells,…

Build scalable design systems with Tailwind CSS v4, design tokens, component libraries, and responsive patterns. Use when creating component libraries, implementing design systems, or standardizing UI patterns.

Expert guidance for integrating and building applications with shadcn/ui components, including component discovery, installation, customization, and best practices.

Brand voice, visual identity, messaging frameworks, asset management, brand consistency. Activate for branded content, tone of voice, marketing assets, brand compliance, style guides.

Token architecture, component specifications, and slide generation. Three-layer tokens (primitive→semantic→component), CSS variables, spacing/typography scales, component specs, strategic slide creation. Use for design tokens, systematic design,…

Create beautiful, accessible user interfaces with shadcn/ui components (built on Radix UI + Tailwind), Tailwind CSS utility-first styling, and canvas-based visual designs. Use when building user interfaces, implementing design systems, creating responsive…

Comprehensive design skill: brand identity, design tokens, UI styling, logo generation (55 styles, Gemini AI), corporate identity program (50 deliverables, CIP mockups), HTML presentations (Chart.js), banner design (22 styles, social/ads/web/print), icon…

UI/UX design intelligence for web and mobile. Searchable local database with 84 styles, 192 color palettes, 74 font pairings, 192 product types, 98 UX guidelines, 104 icon entries, 16 GSAP motion presets, and 25 chart types across 22 stacks (React, Next.js,…

Use when continuing work from a previous AI coding-agent session, handoff transcript, chat log, exported conversation, saved artifact set, or session summary.

Use when the user asks for a 'full' or 'end-to-end' release driven by an architecture document — typically a multi-track release landing a substantial product slice (new product line, multi-surface refactor, feature bundle). Triggers: 'design a doc for this…

Use when the user wants to clone or adapt a UI pattern from any website into your app, or asks to "build something like X", "make our nav look like Y", or "clone that component". Requires an aura.build Pro subscription. Aura's clone is now NATIVE — paste a…

Use when a task is too big for a handful of subagents or needs cross-verification — codebase audits, multi-file migrations, cross-checked research, plan-from-N-angles, multi-source sweeps. Codifies the built-in Workflow tool (dynamic workflows), the authoring…

Use when starting or restructuring any software project in ANY language — deciding folder/module layout, dependency direction, public API boundaries, where logic vs entrypoint lives, the testing tiers, smoke tests, or CI gates — when no language-specific…

Use when writing or auditing any blog post on your product's site (new post or existing). Enforces the BlogPostLayout container contract AND a Tier-1/Tier-2 anti-AI-slop checklist derived from 15-source Exa research (2026-05-14). Both checks are mandatory…

Use when an agent's response/formatting logic is (or will be) reachable from more than one delivery channel (chat, SMS, email, push, web). Triggers — before adding a second channel to a single-channel agent, before writing/editing a shared…

Use when the user asks "what did we decide about X", "find the session where we discussed Y", "when did we first hit Z bug", "what was the rationale behind W", or any question that needs answers retrieved from prior Claude Code sessions across all projects.…

Use before any reverse-engineering or malware-analysis work to confirm authorization and evidence rules. DO NOT USE as a pentest or hacking playbook.

Use when statically classifying an authorized malware-suspect PE without running it. DO NOT USE to write, spread, or execute malware.

Use when identify() kind is surprising and you need a magic-byte first-move. DO NOT USE to forge file formats or malware droppers.

Use when you need the cheapest static probes for an authorized binary before decompile. DO NOT USE for cracking or exploit recipes.

Use when inventorying cryptographic libraries and APIs in an authorized binary. DO NOT USE to crack, forge, or weaken cryptography.

Use when auditing an operator-owned shipped binary for bugs via static inventory. DO NOT USE on third-party products or to weaponize findings.

Use when deciding how to reverse an authorized binary without wasting decompiler time. DO NOT USE for cracking, DRM bypass, or exploit development.

Use when explaining a Windows PE file layout from a reveng-debug inventory. DO NOT USE for patching binaries or forging signatures.

Bulk compression of a file corpus — up to 50 documents per call — for later queries rather than one-off reads. Use this skill whenever the user wants to pre-process a directory, a support-ticket dump, meeting notes, or any sizable corpus before Q&A. Trigger…

Compress an MCP tools/list manifest so downstream agents see shorter tool descriptions without losing inputSchema semantics. Use before forwarding a large tools/list to a secondary agent or storing it in context.

Extracts the public API of a codebase — class names, function signatures, exported types, module docstrings — without loading every file. Use this skill whenever the user asks to understand, explore, navigate, or describe a codebase, library, repository, or…

Query-guided compression of a documentation site, docs folder, README, wiki, or specification for Q&A. Use this skill whenever the user points you at multi-page reference material and wants to find something in it. Trigger phrases include "help me find X in…

Pre-flight check before sending an expensive LLM prompt. Returns a verdict (send_as_is, send_compressed, warn_context_limit, clear_first), the compressed prompt body inline, a cost preview against on-demand list pricing, and a cache hit likelihood. Use this…

Orientation for the gotcontext MCP plugin — the few tools worth reaching for first. Use this skill when setting up the plugin, when unsure which gotcontext tool fits, or right after install. Covers gc_pre_flight (decide ingest/search/summarize/clear before…

Compresses a git diff before review so noise (lockfile bumps, generated files, whitespace churn) doesn't crowd out the actual logic changes. Use this skill whenever the user asks you to review a pull request, explain a diff, summarize changes, or comment on…

Compress a session's conversation history into a portable summary that can be re-injected after /clear. Use this skill when context is filling up and the agent needs to recover state after clearing. Works even when Claude Code's own auto-compact has failed…

Use when climbing JS recovery / unlockable coverage on Claude SEA or similar minified bundles, editing js_recovery_toolkit (Waves 7–10: ensemble, structural / Bun map, defrag / word_map, normalize / semantic / LLM, webcrack + tag-boost, Hungarian soft_assign…

Enforces named-path git staging on REVENG WSL/DrvFS dirty trees (L38/L49). Use when committing on reveng-main with other agents’ dirty files present, when tempted to git add -A / git add . / git stash across worktrees, when git status hangs on DrvFS, or when…

REVENG GA/release honesty rules from Scope C 2026-08 (Waves 0–2 honesty closeout merged; Waves 3–10 JS recovery climb in progress; R-RALPH-2 open). Use when verifying GA readiness, editing verify_ga_readiness, support matrix claims, capability reports,…

Prunes REVENG merged/prunable git worktrees and local feature branches without blind-merging unfinished work to main (L51/L52 companion). Use when cleaning .worktrees/, after Wave closeout, when git worktree list shows prunable tips, when tempted to merge…

Runs the Sol/Codex frozen-tip audit protocol for REVENG Wave closeout and honesty PRs (L47). Use when Sol or Codex must audit a closeout PR before merge, when writing or pinning a Sol verdict file, or when tempted to merge on self-PASS / amend after Sol / pin…

States REVENG Wave 2 MCP tool-annotation honesty for denylist dual-labels and actlint expectations (L45). Use when editing MCP tool annotations, risk_level hints, generate_exploit / recompile_binary labels, denylist policy, or when tempted to treat…

Cleanup worker for deleting AI slop, consolidating duplicates, and fixing imports. Never breaks tests.

Core Python developer for the REVENG RE platform mission.

Use when searching code, logs, or repositories with tensor-grep; validating rg or AST parity; using tg MCP tools; checking GPU/search routing; or producing agent-friendly context, source, refs, or blast-radius output.

Understand tensor-grep routing, shared services, local state, and compatibility boundaries before changing behavior.

Search a repository, inspect symbols and callers, and prepare a bounded edit investigation with tensor-grep.

Use tensor-grep for repository code search, symbol lookup, blast-radius analysis, and edit planning when solving codebase tasks or preparing patches.

Add or extend a language extractor and register its symbol, import, reference, and caller capabilities.

Set up the development environment and verify Python and Rust artifact locations before testing tensor-grep changes.

Write public tensor-grep documentation with verified commands, clear explanations, and accurate feature claims.

Select focused checks, verify installed entry points, and report tensor-grep validation against the exact artifact tested.

Use when the user wants to use Google Gemini for analysis, large files or codebases, sandbox execution, or brainstorming. Runs headless Gemini CLI via a Node script (no MCP). Triggers on "use Gemini", "ask Gemini", "analyze with Gemini", "large file",…

Use when the user wants to use Google Gemini for analysis, large files or codebases, sandbox execution, or brainstorming. Runs headless Gemini CLI via a Node script (no MCP). Triggers on "use Gemini", "ask Gemini", "analyze with Gemini", "large file",…

Use when the user wants to use Google Gemini for analysis, large files or codebases, sandbox execution, or brainstorming. Uses headless Gemini CLI scripts (no MCP). Triggers on "use Gemini", "analyze with Gemini", "large file", "sandbox", "brainstorm with…

Use when the user asks for feedback on code, a self-review, testing suggestions, or a sanity check. Provides structured feedback, test ideas, or a short review checklist so the user can validate their work.

Use when fixing proposal resurrection, rejected/accepted claim reappearance, cross-session prevalence spam, maxProposals ordering, preference false positives, or claimKey / --max-sessions behavior in gotcontext-memory dreaming.

Use when working on gotcontext-memory (markdown HITL dream, MemoryStore CAS, MCP tools, doctor caps, preference extraction) or when comparing it to omega transcript_dream / memory_dream. Enforces HITL honesty, lock/index rules, inert-test traps, and no false…

Use when dreaming over multi-GB transcript corpora, fixing OOM / heap pressure, implementing or auditing SessionDigest streaming, stratified max-sessions windows, concurrent digestion, distinguishing truncated from malformed reads, or Cursor .vscdb vs *.jsonl…

Use when fixing proposal resurrection, rejected/accepted claim reappearance, cross-session prevalence spam, maxProposals ordering, preference false positives, or claimKey / --max-sessions behavior in gotcontext-memory dreaming.

Pre-flight check before sending an expensive LLM prompt. Returns a verdict (send_as_is, send_compressed, warn_context_limit, clear_first), the compressed prompt body inline, a cost preview against on-demand list pricing, and a cache hit likelihood. Use this…

Compresses a git diff before review so noise (lockfile bumps, generated files, whitespace churn) doesn't crowd out the actual logic changes. Use this skill whenever the user asks you to review a pull request, explain a diff, summarize changes, or comment on…

Compress a session's conversation history into a portable summary that can be re-injected after /clear. Use this skill when context is filling up and the agent needs to recover state after clearing. Works even when Claude Code's own auto-compact has failed…

Extracts the public API of a codebase — class names, function signatures, exported types, module docstrings — without loading every file. Use this skill whenever the user asks to understand, explore, navigate, or describe a codebase, library, repository, or…

Use when the user wants to use Claude (Claude Code CLI) for analysis, codebases, or brainstorming from another agent. Uses headless Claude Code CLI scripts (no MCP). Triggers on "use Claude", "analyze with Claude", "ask Claude", "brainstorm with Claude".

Use when the user wants to use Claude (Claude Code CLI) for analysis or brainstorming. Triggers on "use Claude", "ask Claude", "analyze with Claude", "brainstorm with Claude".

Use when the user wants to use Claude (Claude Code CLI) for analysis, codebases, or brainstorming. Runs headless Claude Code CLI via a Node script (no MCP). Triggers on "use Claude", "ask Claude", "analyze with Claude", "brainstorm with Claude". Do not use…

Use when the user wants OpenCode headless analysis via ask-opencode.mjs.

Use when OpenCode should call a headless OpenCode CLI wrapper for analysis, brainstorming, or machine-readable output.

Use when the user wants to use OpenCode (opencode CLI) for analysis, codebases, or brainstorming from another agent. Uses headless `opencode run` scripts (no MCP). Triggers on "use OpenCode", "ask OpenCode", "analyze with OpenCode", "brainstorm with OpenCode".