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 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 system, then plan it, then ship it', 'ultrathink this through to ship', 'do all 10 phases', 'architecture refresh', 'convergence loop the doc, then implement, then push', or any prompt naming 4+ sequential phases ending in push/merge. Meta-skill bundling writing-plans, a peer-review council / codex peer-review, subagent-driven-development, verification-before-completion, gh-release-ship-loop, and blog-post-template.

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 URL or drag a screenshot into aura.build and it generates React/Tailwind directly; the Anima/Chrome-extension flow is only a fallback for login-gated pages Aura can't fetch.

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 API, quality patterns, the framework-decision rule, what to download, and this project's reusable templates + house constraints.

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 architecture skill applies. Language-agnostic parent of typescript-cli-architecture and rust-workspace-architecture. Triggers — "how should I structure this", "where does this file/module go", "feature vs layer", "set up tests and CI", "smoke test", "new package or module?", "structure my Go/Python project", "project layout for <language>".

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 before any blog post merges.

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 respond()/format_reply()/persona-selection helper, or when a multi-channel agent's voice output sounds like it was written for text (spelled digits, markdown symbols read aloud).

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. Also use proactively when the current session needs context that predates the loaded conversation thread — chat sessions are a queryable backup to long-term memory, and they hold reasoning traces (rejected alternatives, partial understandings, the why) that curated MEMORY.md / project_*.md entries don't capture. Searches the global ~/.claude/projects/*/*.jsonl archive via ripgrep + Python turn-pair extraction. NOT for current state queries (pod status, build status — read those directly), NOT for future plans (read paper §14 work queue or CLAUDE.md), NOT for questions already answered by MEMORY.md (check that first).

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.

Use when you need the domain theory behind tensor-grep's search/retrieval behavior, not just the command syntax — ripgrep exit codes (including the exit-2-but-kept partial-results contract)/PCRE2/binary-NUL-detection/-uuu/-- sentinels, ast-grep + tree-sitter routing, BM25 vs the flat no-IDF capsule scorer, PageRank vs in-degree centrality, the trigram index, PyO3 + the GIL, MCP argv surface, LSP 3.17 framing, and Model2Vec/potion-code (SHIPPED as `tg search --semantic`). Load before explaining WHY tg behaves a certain way, reasoning about the protocol/algorithm THEORY underneath a backend/router change (exit-code semantics, scoring math, wire framing), or writing docs that touch these subsystems — for the invariants a backend/router change must not break, use `tensor-grep-architecture-contract` instead (or in addition). Not a how-to-run or how-to-debug guide — see the sibling table below for those.

Use when you need the load-bearing design of tensor-grep and WHY it holds before touching cli/bootstrap.py, rust_core/src/main.rs, backends/, core/result.py, cli/main.py's native-delegation gate, routing, the agent capsule, or before reviewing/planning any change to the front door, command/flag registration, or backend contract. Explains the bootstrap intercept-before-Typer front door, native-vs-Python routing, the 4 command + 2 flag registration sites, the Backend Fail-Closed Contract, the native-delegation forward-or-refuse contract (`_can_delegate_to_native_tg_search` + its field-coverage ratchet), the partial-results `result_incomplete`/`incomplete_reason` envelope, `MatchLine`'s frozen-but-hashable dataclass contract, the ASCII-only CLI output rule, the agent-context moat, the invariants that must hold, and the known-weak points (flat no-IDF scorer, GPU not viable, rg parity gap, FFI not the dir-scan speed path). Read this to build the right mental model; use sibling skills for the how-to of changing, de

Use when asked to deep-dive, audit, fix, or drain tensor-grep backlog — OR investigate/rank next work and produce SPEC/TDD plans (docs/plans/requirements|design|tasks-*.md) without implementing. Triggers: "work the backlog", "what next", "investigate and plan", backlog-completion campaign. META-ORCHESTRATOR — 20-skill library. Semantic-search flagship: tensor-grep-semantic-search-campaign. Scale/hang campaign: tensor-grep-large-repo-scale-campaign. Load tensor-grep-change-control before edit.

Use when about to claim, review, or dispute a speedup/regression in tensor-grep (tg vs rg, hot-cache, AST, agent-workflow, or GPU changes) — which benchmark script to run, how to read check_regression.py, the noise-floor/absolute-jitter rule for sub-10ms rows, the fair-baseline rule (never compare tg against a strawman comparator), and the launcher-attribution rules (tg_launcher_mode, tg_launcher_command_kind, stale-binary refusal) that make a benchmark artifact claim-quality instead of noise.

Use when setting up the tensor-grep dev environment from a fresh clone, rebuilding the Rust/PyO3 extension or standalone `tg` binary after touching `rust_core/`, or debugging a build/toolchain problem — uv install, `maturin develop`, `cargo build`, the pinned 1.96.0 Rust toolchain, Python >=3.11 floor, a "hanging" cargo build, cargo/rustc missing from PATH, ruff CRLF false-alarms, or a dependency upper-cap silently downgrading tensor-grep on a newer Python. Gives exact copy-paste setup commands and the traps that have each cost a real cycle.

Use when about to change, review, merge, or release ANY code in tensor-grep — adding a tg command or search flag, touching a backend/router/pipeline, editing CI/release/docs contracts, merging a PR, or claiming a fix or speedup is done. Encodes the non-negotiable gates (draft-PR-only autonomy, never-trust-a-self-report, no-speed-claim-without-numbers, experimental-until-proven, TDD-first, smallest-change, benchmark-hot-paths, the 4 registration sites, one-merge-per-tick / the push-race, dogfood-the-real-binary, contract-changes-need-validator-tests) and the historical incident behind each.

Use when adding, changing, or auditing a tg environment variable, CLI flag, or provider mode (native/lsp/hybrid); when a search flag silently leaks to ripgrep or a command misroutes; when deciding whether a config axis (GPU, LSP, classify, semantic) is production or EXPERIMENTAL default-OFF; when adding a new `SearchConfig` field and needing to know whether it must be forwarded/refused/KNOWN_GAP'd for native delegation; or before registering a new `tg search --flag` or `tg COMMAND` (including `tg inventory`'s `--max-repo-files`). Catalogs the load-bearing TG_*/TENSOR_GREP_* env vars (routing, timeouts, GPU, classify, session, MCP security, LSP) with their default and guard, the 2-front-door / 4-site registration checklist, and the native-delegation field-coverage ratchet.

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 phrases include "compress all these files", "pre-process this corpus", "shrink everything in /path", "bulk-compress for Q&A", or when onboarding Claude to a large project that needs a lot of ingested context. Submits an async job to gotcontext's batch queue and returns a job id; the job processes in the background with per-item error reporting so one bad file doesn't block the batch. Pro, Team, or Enterprise plan required.

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 package at the overview level. Trigger phrases include "help me understand this codebase", "what does this library do", "what's the API of X", "how is this project structured", "give me an overview of Y", "explain this repo". Calls gotcontext's AST-aware skeleton extraction so you read the shape of the code, not the implementation bodies.

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 these docs", "what does the Y docs say about Z", "search the Stripe/AWS/Anthropic docs for", "summarize this reference", "check the docs for". Passes the user's question as a query parameter so gotcontext weights relevant sections heavier and compresses off-topic sections more aggressively — keeps answers grounded without loading every page.

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 skill whenever an agent is about to submit a prompt above ~1000 tokens or when context fill is unknown. Trigger phrases include "estimate cost before sending", "should I compress this prompt", "am I about to run out of context", "preview compression savings".

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 expensive context ops), gc_search_docs + gc_read_doc (answer gotcontext product/API questions from live docs), and gc_submit_benchmark (publish an inference-benchmark run to the public leaderboard). Trigger phrases include "set up gotcontext", "how do I use the gotcontext plugin", "which gotcontext tool should I use", "getting started with gotcontext".

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 recent commits. Trigger phrases include "review this PR", "what changed", "explain this diff", "summarize the changes", "look at my diff", "check this branch against main". Uses gotcontext's code-aware compression at fidelity=detailed — detailed because a character dropped in a security fix matters more than a character dropped in prose.

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 because gotcontext runs the summarization on its own infra. Trigger phrases include "summarize this session", "I need to clear context but keep what we built", "compact failed help me recover", "save this conversation before reset".

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", "sandbox", "brainstorm with Gemini".

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", "sandbox", "brainstorm with Gemini". Do not use for general code edits that do not require Gemini; use for tasks that benefit from Gemini's context or a second model.

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 Gemini".

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.

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 skill whenever an agent is about to submit a prompt above ~1000 tokens or when context fill is unknown. Trigger phrases include "estimate cost before sending", "should I compress this prompt", "am I about to run out of context", "preview compression savings".

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 recent commits. Trigger phrases include "review this PR", "what changed", "explain this diff", "summarize the changes", "look at my diff", "check this branch against main". Uses gotcontext's code-aware compression at fidelity=detailed — detailed because a character dropped in a security fix matters more than a character dropped in prose.

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 because gotcontext runs the summarization on its own infra. Trigger phrases include "summarize this session", "I need to clear context but keep what we built", "compact failed help me recover", "save this conversation before reset".

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 package at the overview level. Trigger phrases include "help me understand this codebase", "what does this library do", "what's the API of X", "how is this project structured", "give me an overview of Y", "explain this repo". Calls gotcontext's AST-aware skeleton extraction so you read the shape of the code, not the implementation bodies.

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 for general code edits that do not require Claude; use for tasks that benefit from Claude's context or a second model.

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 asks to run Codex CLI headless from an agent workflow (analysis, brainstorming, second opinion, scripted CLI output). Trigger on requests like "ask codex", "run codex headless", "analyze with codex", or "brainstorm with codex".

Use when Antigravity should run Codex CLI headless for analysis or brainstorming tasks.

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

Use when the user asks to run Cursor Agent CLI headless from an agent workflow (analysis, brainstorming, second opinion, scripted CLI output). Trigger on requests like "ask cursor", "run cursor headless", "analyze with cursor", or "brainstorm with cursor".

Use when Antigravity should run Cursor Agent CLI headless for analysis or brainstorming tasks.

Use when a Codex/Codex-like agent should call a headless Cursor Agent CLI wrapper script for analysis, brainstorming, or machine-readable output.

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 building a scroll-driven cinematic 3D landing experience for any brand: AI-generated photoreal frames displaced into real 3D by depth maps, a scroll-scrubbed camera fly-through with weighted-leg pacing and per-leg camera moves, mouse parallax, explode-on-scroll shatter transitions, an ember particle field, warp streaks, a live in-scene terminal that runs a REAL product demo, a branded preloader, an exit handoff into the page below, a self-hosted display typeface, phone gyro parallax, and opt-in synthesized ambient sound. Covers 2K image generation via OpenRouter, depth maps, the WebGL engine, chrome (nav/consent) integration, the observe-first verify loop, and the flag-off ship posture.

Use when generating or editing an enterprise deck, reconstructing approved visual regions, debugging Google Slides publication, or deciding between native Google Slides and PowerPoint .pptx output.