oimiragieo

@oimiragieo source repo

991 skills
0 followers
3 weeks ago last updated

▌
Mengto Optimize Threejs Games 3 · oimiragieo
Use when profiling, diagnosing, or improving Three.js or WebGL game performance without regressing gameplay—frame-time drops, CPU/GPU pressure, draw calls, texture/geometry budgets, animation loops, adaptive quality, mobile performance, and browser performance verification.

0 repo stars
▌
Mengto Shaders Cursor Ripples 2 · oimiragieo
Add cursor-following fluid WebGPU distortion over an existing image with the Shaders library's ImageTexture and CursorRipples components. Use when a hero, gallery, or media panel needs a water-ripple mouse effect; when replacing a drifting CSS spotlight or flashlight reveal; or when a prompt says to borrow only the shader interaction from a Shaders.com reference while preserving the current brand, image, copy, and layout.

0 repo stars
▌
Mengto Split Layout Technical 2 · oimiragieo
Use when designing a technical split-screen system with dual panels, fine frame lines, mono metadata, quiet editorial typography, and premium inset surfaces. Prefer this over mengto-bright-green-tech-system-webgl when dual-panel split framing leads without a bright-green WebGL viz mandate.

0 repo stars
▌
Mengto Webgl Landing Steering 2 · oimiragieo
Use when creating or refining WebGL-heavy landing pages and you need to steer toward a specific visual outcome (premium, technical, playful, cinematic) while balancing conversion clarity, performance, and implementation complexity.

0 repo stars
▌
Mengto Add Shader Cursor Trail 2 · oimiragieo
Add the Shaders WebGPU mouse effect used for the Tidal Commons hero: a white twinkling halftone cursor trail driven by ChromaFlow, masked through a DotGrid, finished with chromatic ripples and film grain, and protected by static, touch, accessibility, SSR, and performance fallbacks. Use when a user asks for this shader mouse effect, a halftone cursor trail, an interactive WebGPU hero/contact background, or a reusable cursor-following shader layer in React, Next.js, Vue, Svelte, Solid, or plain web projects.

0 repo stars
▌
Mengto Dark Glass Clean Layout 2 · oimiragieo
Use when building a dark glass multi-column workspace with frosted premium shells, floating data cards, and restrained atmospheric depth. Prefer this over mengto-glass-dark-mode-clock when workspace shells and columns matter, not circular clock dials; prefer over mengto-blue-laser-clean-glass-layout when there is no blue laser atmosphere; prefer over mengto-glass-dark-ui when full workspace layout matters more than gradient-border glass cards; prefer over mengto-framed-tech-dark-border-gradient when frosted glass shells lead, not border-gradient tech frames.

0 repo stars
▌
Mengto Image First Grid Layout 2 · oimiragieo
Use when building an image-led grid with full-bleed photography, structural guide lines, anchored content blocks, and restrained technical overlays. Prefer this over mengto-agency-grid-layout-minimal when photography is the primary plane, not typography-led editorial grids.

0 repo stars
▌
Mengto Nested Container Frames 2 · oimiragieo
Use when implementing a container-in-container layout with an outer centered frame (vertical boundary lines, corner markers) and inset inner containers with their own backgrounds and rounded frames. Prefer this over mengto-nested-container-clean-agency when the technique is structural nested frames, not a full agency visual system.

0 repo stars
▌
Mengto Optimize Web Animations 2 · oimiragieo
Profile, audit, and optimize frontend page performance with emphasis on animation work, memory-leak risks, long-session slowdowns, CSS animations, canvas/WebGL requestAnimationFrame loops, marquees, skeletons, GSAP/Three/Matter effects, timers, listeners, and observers. Use when the user asks to make animations performant, pause offscreen animations, look for memory leaks, profile pages that slow the computer over time, fix janky scrolling, reduce CPU/GPU use, or repeat the "only play in view" optimization on React/Vite/Next/frontend pages using Codex Browser.

0 repo stars
▌
Mengto Orange Clean Paper Saas 2 · oimiragieo
Use when designing a clean paper-toned SaaS system with warm neutrals, orange accent signals, rounded premium forms, and polished product illustration surfaces. Prefer this over mengto-clean-minimal-beige-light-mode when orange SaaS accents and product illustration lead.

0 repo stars
▌
Mengto Blue Cloudy Clean Modern 2 · oimiragieo
Use when designing a clean modern light UI with a luminous blue sky atmosphere, soft drifting cloud light, minimal white framing, and serene premium typography. Prefer this over mengto-clean-minimal-beige-light-mode when sky/cloud blue is the mood, not warm beige paper.

0 repo stars
▌
Mengto Scroll Progress Timeline 2 · oimiragieo
Use when turning an ordered process into a data-driven vertical or horizontal scroll story with a base line, progress fill, active step states, responsive collapse, semantic fallback, and reduced-motion—onboarding, checkout, roadmaps, recipes, case studies, service processes, histories, or narratives paced by scroll.

0 repo stars
▌
Gotcontext Memory Hitl Honesty 2 · oimiragieo
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 parity claims.

0 repo stars
▌
Gotcontext Memory Streaming Digests 2 · oimiragieo
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 dream wiring in gotcontext-memory.

0 repo stars
▌
Ingest Docs 2 · oimiragieo
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.

0 repo stars
▌
Batch Compress 2 · oimiragieo
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.

0 repo stars
▌
Shrink For Claude 2 · oimiragieo bundle
Call this before reading any file path, URL, or document that could be large. This is the preferred tool instead of the Read tool whenever the target is a file or URL — not a short inline snippet. Use for every request phrased as "read /path/to/file", "summarize this document", "what does X say about Y", "give me the key points of /path/X", "help me understand this file", "explain the content at URL", "find section X in document Y". Compresses source by 60-90% via gotcontext.ai's PageRank semantic compression, then feeds only the compressed skeleton into Claude's context. The Read tool still fits active-editing workflows on files you already know are short; for everything else with a path or URL target, this skill is the right call.

0 repo stars
▌
Compress MCP Manifest 2 · oimiragieo
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.

0 repo stars
▌
Gotcontext Memory Claim Lifecycle 2 · oimiragieo
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.

0 repo stars
▌
Omega Codex CLI 2 · oimiragieo
Use when Codex should call a headless Codex CLI wrapper script for analysis, brainstorming, or machine-readable output.

0 repo stars
▌
Omega Codex CLI 3 · oimiragieo bundle
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".

0 repo stars
▌
Omega Opencode CLI 2 · oimiragieo
Use when OpenCode should call a headless OpenCode CLI wrapper for analysis, brainstorming, or machine-readable output.

0 repo stars
▌
Omega Opencode CLI 3 · oimiragieo bundle
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".

0 repo stars
▌
Omega Gemini CLI 2 · oimiragieo
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.

0 repo stars
▌
Omega Gemini CLI 3 · oimiragieo bundle
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".

0 repo stars
▌
Tensor Grep 2 · oimiragieo bundle
Use tensor-grep for repository code search, symbol lookup, blast-radius analysis, and edit planning when solving codebase tasks or preparing patches.

0 repo stars
▌
Tensor Grep 3 · oimiragieo bundle
Use tensor-grep for repository code search, symbol lookup, blast-radius analysis, and edit planning when solving codebase tasks or preparing patches.

0 repo stars
▌
Web Gsap · oimiragieo bundle
Use when you need to add or debug professional web animations with GSAP (timelines, ScrollTrigger, stagger, transforms) in HTML/CSS/JS/React. Includes patterns for smooth motion, performance, and common pitfalls.

0 repo stars
▌
Web Cobejs · oimiragieo bundle
Use when adding a lightweight interactive globe with cobe (canvas setup, markers, interaction, performance, integration with React/Next.js).

0 repo stars
▌
Web Threejs · oimiragieo bundle
Use when building or debugging interactive 3D scenes on the web with Three.js (scene/camera/renderer, lights/materials, GLTF loading, controls, performance). Helpful for designers shipping 3D UI moments.

0 repo stars
▌
Web Vantajs · oimiragieo bundle
Use when adding animated WebGL background effects with Vanta.js (setup, parameters, resizing, performance, integration in React/Next.js).

0 repo stars
▌
Web Globe Gl · oimiragieo
Use when implementing globe.gl (Globe.GL) for 3D globe data visualization with WebGL/ThreeJS, including setup, data layers (points, arcs, polygons, labels), and integration patterns in plain HTML or React.

0 repo stars
▌
Web Matterjs · oimiragieo
Use when implementing 2D physics interactions with Matter.js, including Engine/World setup, Render/Runner configuration, adding bodies and constraints, and scroll/interaction-friendly canvas scenes.

0 repo stars
▌
Web Tailwindcss · oimiragieo bundle
Use when designing/implementing UI with Tailwind CSS (layout, typography, responsive, theming, component patterns). Includes quick recipes and conventions for clean, consistent web design.

0 repo stars
▌
Web Landing Page · oimiragieo bundle
Use when designing or rewriting a high-converting landing page (single-offer page) for SaaS/apps/services. Covers structure, layout patterns, conversion strategies, copywriting, SEO/AEO, and common pitfalls.

0 repo stars
▌
Web Pricing Page · oimiragieo bundle
Use when designing or rewriting a high-converting SaaS pricing page (structure, plan design, copywriting, SEO/AEO, FAQs, layout patterns, experiments). Includes checklists, templates, and common pitfalls.

0 repo stars
▌
Web Unicorn Studio · oimiragieo bundle
Use when embedding and customizing Unicorn Studio interactive animations on the web (embed, responsive sizing, performance, layering with UI, fallbacks).

0 repo stars
▌
Web Progressive Blur · oimiragieo
Create a layered CSS progressive blur (top or bottom) using multiple backdrop-filter masks for depth and softness. Use when asked for “progressive blur”, “gradient blur overlay”, or stepped blur masks that fade from an edge of the viewport.

0 repo stars
▌
Web Animation Systems · oimiragieo
Use when designing or implementing product-grade web motion like Stripe, Linear, Apple, and Vercel. Covers motion principles, easing/duration defaults, choreography patterns, scroll/hover interactions, performance, accessibility (reduced motion), and implementation guidance.

0 repo stars
▌
Web Aura Asset Images · oimiragieo
Use when you need high-quality stock-style images from Aura Assets (aura.build/assets) similar to Unsplash for design mockups and marketing: backgrounds, abstract wallpapers, architecture, portraits, and headshots. Includes a workflow for searching by tag on aura.build/assets and returns 5 real image URLs per category plus practical guidance for using different resolutions and aspect ratios.

0 repo stars
▌
Web CSS Alpha Masking · oimiragieo
Apply CSS alpha masking with linear-gradient for horizontal or vertical edge fades (mask-image and -webkit-mask-image). Use when asked for alpha masks, fade edges, or CSS mask gradients.

0 repo stars
▌
Web Animation On Scroll · oimiragieo
Create an on-scroll animation trigger using IntersectionObserver with Tailwind-friendly animation classes and keyframes. Use when asked for scroll-reveal, animate-on-scroll, or sequencing element animations when they enter the viewport.

0 repo stars
▌
Web Unsplash Asset Images · oimiragieo
Use when you need to pick high-quality Unsplash images for product/design assets (avatars, headshots, portraits, large website backgrounds, and abstract wallpapers) and output real Unsplash URLs plus practical instructions for producing the right resolutions and aspect ratios (1:1, 4:5, 3:4, 16:9, 9:16).

0 repo stars
▌
Omega Opencode CLI · oimiragieo
Use when the user wants OpenCode headless analysis via ask-opencode.mjs.

0 repo stars
▌
Gotcontext Memory Hitl Honesty · oimiragieo
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 parity claims.

0 repo stars
▌
Gotcontext Memory Claim Lifecycle · oimiragieo
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.

0 repo stars
▌
Gotcontext Memory Streaming Digests · oimiragieo
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 dream wiring in gotcontext-memory.

0 repo stars
▌
Omega Feedback Test · oimiragieo
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.

0 repo stars
▌
Quick Start · oimiragieo
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".

0 repo stars
▌
Pre Flight · oimiragieo
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".

0 repo stars
▌
Ingest Docs · oimiragieo
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.

0 repo stars
▌
Batch Compress · oimiragieo
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.

0 repo stars
▌
Review Pr Diff · oimiragieo bundle
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.

0 repo stars
▌
Session Summary · oimiragieo
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".

0 repo stars
▌
Shrink For Claude · oimiragieo bundle
Call this before reading any file path, URL, or document that could be large. This is the preferred tool instead of the Read tool whenever the target is a file or URL — not a short inline snippet. Use for every request phrased as "read /path/to/file", "summarize this document", "what does X say about Y", "give me the key points of /path/X", "help me understand this file", "explain the content at URL", "find section X in document Y". Compresses source by 60-90% via gotcontext.ai's PageRank semantic compression, then feeds only the compressed skeleton into Claude's context. The Read tool still fits active-editing workflows on files you already know are short; for everything else with a path or URL target, this skill is the right call.

0 repo stars
▌
Extract API Surface · oimiragieo bundle
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.

0 repo stars
▌
Compress MCP Manifest · oimiragieo
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.

0 repo stars
▌
Codebase Cleaner · oimiragieo
Cleanup worker for deleting AI slop, consolidating duplicates, and fixing imports. Never breaks tests.

0 repo stars
▌
Python Developer · oimiragieo
Core Python developer for the REVENG RE platform mission.

0 repo stars
▌
Reveng Sol Frozen Tip · oimiragieo bundle
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 Sol to a parent SHA while HEAD moved.

0 repo stars
▌
Reveng Release Honesty · oimiragieo
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, managed recompile, JS behavior grades, native fixtures / analyze probes, Sol/Fable plan-validate loops, backlog clearance waves, JS recovery Option C metrics, or writing CEO/release status.

0 repo stars
▌
Reveng Worktree Hygiene · oimiragieo bundle
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 foreign worktrees/PRs wholesale, or when disposing session temp thinktank/Sol artifacts on Windows.

0 repo stars
▌
Reveng JS Recovery Climb · oimiragieo bundle
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 + unique-token tombstones), running scripts/js_recovery_toolkit.py, writing test_wave8_* / test_wave85_* / test_wave9* / test_wave10_*, or reporting oracle_coverage vs survivor/unlockable ship-bar metrics. Enforces Option C honesty (100% unlockable ship bar; oracle aspirational; report BOTH) and refuses GA / R-RALPH-2 / exe-decode overclaims.

0 repo stars
▌
Reveng Named Path Commit · oimiragieo bundle
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 Windows Git Bash hooks need /c/Users/... Python via pwsh.exe.

0 repo stars
▌
Reveng MCP Annotation Honesty · oimiragieo bundle
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 annotations as enforcement or auto-map every high risk tool.

0 repo stars
▌
Tensor Grep Enterprise Agent · oimiragieo
Use when designing or evaluating tensor-grep as an enterprise agentic code-intelligence tool — tg prepare one-call edit readiness, PATH narrowing, agent --deadline, find/route-test/ledger, install-dense, EvidenceReceipts, review-bundle, GPU honesty, world-class readiness gaps.

0 repo stars
▌
Tensor Grep Research Frontier · oimiragieo
tensor-grep research frontier

0 repo stars
▌
Tensor Grep Workspace Dogfood · oimiragieo
Use when stress-testing tensor-grep against a multi-project workspace — orientation, scoped search, tg find, prepare, route-test, ledger, install-dense, symbol graphs, GPU, evidence, sessions, readiness gates. Not the PyPI release dogfood harness.

0 repo stars
▌
Tensor Grep Debugging Playbook · oimiragieo bundle
Use when a tensor-grep (tg) run fails, hangs, returns wrong/empty/silently-degraded results, a CI check goes red, a release doesn't publish, a worktree agent's PR reports "No commits between main and <branch>" after a reported commit, or a wall-clock/timing-ratio test flakes on a loaded CI runner. Symptom-to-triage table, each row giving a discriminating experiment and a fix pointer, for CI red, release not published (push-race), search hangs/slow, silent-empty result (fail-closed contract), argv/flag injection, mock-green-but-real-dead FFI, dependency-cap silent downgrade, ranking flip, a `CliRunner`/`capfd` test that goes green-on-PR-red-on-main after a delegation/routing change, a latency fix/regression report that needs profiling-at-scale instead of a code-reading guess, a detached-HEAD worktree push that pushes a stale branch ref instead of the real commit, a timing-ratio test flake caused by a degenerate baseline below clock resolution, a diagnostic control that checked the wrong symbol or only proved a

0 repo stars
▌
Tensor Grep Worldclass Roadmap · oimiragieo
Use when planning, building, reviewing, or prioritizing any slice of the world-class roadmap — the agentic EDIT-CONTROL PLANE thesis (not faster grep); the S1 fail-closed edit tickets + verify-edit with ESCROWED CI-held-key evidence; S2 registration-aware impact-diff; S3 next_action protocol; S4 warm-session resume; S5 head-bound escrowed evidence chain; S6 semantic default + why_ranked; S7 federated workspace object; or the H1 unknown-command/PATH-honesty prerequisite. Triggers: "edit-control plane", "world-class", "verify-edit", "escrowed evidence", "S1..S7", "edit tickets", "CI-held signing key", "semantic blast radius", "impact diff", "next_action protocol", "federated workspace", "why_ranked". Covers the council-amended spine (design + prioritization contracts), the banked-vs-new status of each item, the both-front-door + 4-site registration obligations, and the gate sequence (change-control → thinktank design council → TDD) every slice must pass. NOT a build plan — build routing happens through tensor-g

0 repo stars
▌
Tensor Grep Failure Archaeology · oimiragieo bundle
Use when about to "fix" or "optimize" something in tensor-grep that feels novel — before proposing PyO3/FFI for directory walking, re-enabling free-threading, adding a --json self-test, tightening a dependency upper-cap, blaming an IDF/ranking flip, trusting a green mock/FFI test, diagnosing a release that "didn't publish", chasing a reported latency "regression" without profiling at scale, shipping a doc-drift/precision heuristic off green fixtures alone, adding a "differs-from-default" native-delegation gate, reading a `capfd`-based CliRunner test result, micro-optimizing a hot loop without checking who actually consumes the value, re-proposing cAST structural chunking as the default, re-proposing dense int8/binary/PCA embedding compression, proposing a warm-session/daemon search-index shortcut, proposing GPU-for-search or re-litigating the PFAC-vs-brute-force kernel claim, hitting the many-pattern Aho-Corasick dedup bug, trusting an unverified "cheap win" from a paper/research steal-list, cloning a "mirror

0 repo stars
▌
Tensor Grep Release Drift Check · oimiragieo
Run a mechanical post-release governance sweep of the in-repo skills and docs after a release lands — version stamps that fall below the current tag, derived counts (language tier via _symbol_navigation_descriptor, skill count, tree-sitter package count) that no longer match the code, and known-state facts (merged PRs, doctor schema fields) that went stale. Use when a release just merged (e.g. "we hit v1.110.x, are the skills/docs current?"), when auditing the in-repo skill library for drift, when a skill still claims a tier/count a newer skill or this session's changes superseded, or before writing new skills that would inherit a stale stamp. NOT a pytest (numbers drift; a hard gate would red every PR) — a maintenance sweep like .claude/skill_anchor_audit.py. Sibling of tensor-grep-docs-and-writing (the docs governance) and tensor-grep-release-and-positioning (the release mechanics themselves); this one is the bookkeeping that keeps the library current after the release.

0 repo stars
▌
Tensor Grep Multi Project Search · oimiragieo
Use when searching across a multi-project workspace root (many sibling repos) with tensor-grep — bare unscoped search is refused; scope with --glob/--type/--max-depth or opt in with --allow-broad-generated-scan; prefer per-repo paths for agent/symbol/find work; pass explicit --deadline on whole-repo agent; narrow mega-repo PATH when result_incomplete.

0 repo stars
▌
Tensor Grep Research Methodology · oimiragieo
Use when you have a hunch, a candidate optimization, a novel technique, or an "I think X is faster/better/possible" idea for tensor-grep and must turn it into an ACCEPTED result or a DOCUMENTED RETIREMENT — the research discipline. Covers the evidence bar (one mechanism must explain every observation INCLUDING the negatives, and survive an assigned adversarial refutation whose every claim cites file:line), predicting the number + noise band BEFORE you run, the idea lifecycle (experimental default-OFF -> dogfood/benchmark -> council-verify -> conscious flag-flip to adopted OR retirement recorded in docs/PAPER.md so it is never retried), verifying an AI-drafted plan against real code, and where good ideas actually come from. The scientific-method META sibling to change-control (gates) and research-frontier (targets).

0 repo stars
▌
Tensor Grep Architecture Contract · oimiragieo
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 plus the MCP contract-version site, 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 sk

0 repo stars
▌
Tensor Grep Codex Gated Audit Loop · oimiragieo
Use when shipping an AUDIT-FIX PR for a verified H/M finding, running or resuming the codex-gated adversarial audit loop for a fix (behavioral RED -> minimal fix -> independent codex gate -> verify every finding with your OWN probes -> re-audit until SHIP), writing a gated test that must pass identically on the dev desktop AND the CI pytest env, or any security-surface change that needs an adversarial gate before merge (A3). Also when a prior fix to the same finding already shipped wrong (the twin law). Triggers: "codex-gated", "audit loop", "FIX-FIRST", "SHIP", "audit-fix PR", "adversarial gate", "try to BREAK it". Distinct from the pre-build plan council (tensor-grep-backlog-campaign) and the change gates (tensor-grep-change-control): this is the per-item fix loop itself. Not for first-pass feature planning or merge/release administration.

0 repo stars
▌
Tensor Grep Hermetic Hostile Tests · oimiragieo
Use when writing a gated test that must pass identically on the dev desktop AND the CI pytest env (which lacks optional engines), constructing a HOSTILE fixture (permission denial, junction/symlink swap, network partition, disk-full, killed process, corrupted file, missing binary) and proving it actually BITES before the probe runs, forcing a deterministic injectable seam instead of env-detecting, mutation-asserting that a red-arm control really applied, or adding a positive control so a zero cannot read as "clean". Triggers: "hermetic test", "hostile fixture", "fixture-BITES precheck", "STILL VACUOUS", "env-independent", "setup-not-assertion", "the fixture never applied", "mutation asserted-applied", "positive control", "Event-gated parent swap", "RED reason class", "platform arms". Sibling of tensor-grep-codex-gated-audit-loop (the loop) and tensor-grep-validation-and-qa (what counts as proof); this one is the CONSTRUCTION discipline for hermetic + hostile tests. Not for deciding what to test or for merge g

0 repo stars
▌
Code Search And Retrieval Reference · oimiragieo
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, the multi-language symbol-graph registry's fail-closed grammar-missing contract, 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.

0 repo stars
▌
Tensor Grep Demand Gate Measurement · oimiragieo bundle
Use when a DEMAND_GATED board row must be measured before it may reopen: running a bounded, plan-frozen measurement that decides whether the row's reopen condition (its Trigger text, re-derived verbatim from origin/main) is satisfied. Covers frozen thresholds (client count, duration, request shape, and control expectation all fixed BEFORE the run, never chosen from the result), the positive-control law (a control arm must hit the frozen threshold VERBATIM or the arm is CANNOT_MEASURE - add a single-shot arm that reports the exact number instead of recharacterizing the frozen value as illustrative, A112), discriminated failure classes (claim only what the raw JSON classifies; split connect vs response timeouts so each classifies separately; unrecorded environment readings are observations, not data, A113), CANNOT_MEASURE as a first-class outcome, honest soft-severity reporting, and per-row receipt discipline with the board update in-body per A71. Proven on DD-006 (2026-08-14). NOT for building the fix - this s

0 repo stars
▌
Tensor Grep Diagnostics And Tooling · oimiragieo bundle
Use when you need to MEASURE tensor-grep's health instead of eyeballing it -- interpreting a `tg doctor --json` field, reading a PASS/FAIL/SKIP from `tg dogfood` or `scripts/agent_readiness.py`, or explaining what a diagnostic field actually proves (and does not prove). Not for CLI syntax (tensor-grep-run-and-operate), fixing a found bug (tensor-grep-debugging-playbook), or deciding which `benchmarks/*.py` script to run / constructing a claim-quality benchmark artifact (tensor-grep-benchmark-and-proof-toolkit).

0 repo stars
▌
Tensor Grep Local CI Parity Harness · oimiragieo
Use when you need to run a CI lane locally that this repo's shared-box rules forbid (cargo test, tests/e2e/test_routing_parity.py, a full pytest matrix), when building or debugging scripts/ci-local/, when a local container run and the GitHub run disagree, or when deciding between nektos/act and a hand-written harness. Covers the twelve measured container-vs-runner divergences, the CPU-cap discipline that makes local lanes acceptable on a shared machine, and the anti-drift gate that keeps a second CI definition honest. DO NOT USE for diagnosing a genuinely red CI job (tensor-grep-debugging-playbook), for deciding what counts as proof a change works (tensor-grep-validation-and-qa), or for release/publish mechanics (tensor-grep-release-and-positioning).

0 repo stars
▌
Tensor Grep Release And Positioning · oimiragieo
tensor-grep: Release Mechanics and Public Positioning

0 repo stars
▌
Tensor Grep Enterprise Review Bundle · oimiragieo
Use when packaging tensor-grep outputs for enterprise change review — review-bundle create/verify requires a rewrite audit --manifest (not a capsule); optionally attach scan JSON and checkpoint IDs; pair with evidence emit and audit-history.

0 repo stars
▌
Tensor Grep Semantic Search Campaign · oimiragieo
Use when building, extending, or reviewing tensor-grep's APPROVED local hybrid semantic search — BM25 + CPU dense embeddings fused with Reciprocal Rank Fusion (RRF), no API key, no GPU (roadmap item #1). Load before adding a dense/embedding leg, RRF fusion, a `tg index` command, or changing `tg search --rank` / `--bm25`. Covers the decision-gated build phases with exact commands + expected gate numbers, the ranked solution menu (Semble / ripvec / BM25-only) with derivation obligations, the retrieval-quality + editor-plane + token-economy promotion gates, the Backend Fail-Closed Contract for the dense leg, fenced-off wrong paths (no API-key embeddings, no GPU dependency, do not break `--format rg` / `--json` / `--ndjson` semantics), and routing promotion through change-control. STATUS as of 2026-07-08, v1.49.3: the dense leg + RRF fusion described here as the target architecture (Candidate 1 / the Semble pattern) SHIPPED as `tg search --semantic` (`retrieval_dense.py` + `retrieval_fusion.py`, default-OFF, gate

0 repo stars
▌
Tensor Grep Large Repo Scale Campaign · oimiragieo
Use when tg hangs, stalls, or runs for minutes on a large/unscoped repo; when `--deadline` "seems ignored" and a symbol query still overruns its budget; when working task #52 (CLOSED, end-to-end deadline ineffective on a ~1800-file TS repo) or #390 (CLOSED, the daemon-path deadline gap) for historical context, caller-scan / build_repo_map latency, the unscoped-`tg search` hang, the generic >1500-file implicit-root fast-refuse (A9/#702), or the exit-2 partial-result semantics. The decision-gated campaign to finish agent-native SCALE HONESTY: tg must never hang and never silently lie (return an empty/partial result as if it were complete) on a customer-scale repo. Gives the reproduce -> phase-instrument (cProfile) -> ranked solution menu -> fail-closed build -> change-control promotion runbook with exact commands, expected numbers, and branch-on-mismatch forks. Verified against v1.110.14 (2026-08-11) on 2026-07-24 (#400/#413/#428/#702 fully shipped; #52 and #390 both CLOSED; the exit-code contract is exit-2-reg

0 repo stars
▌
Tensor Grep Benchmark And Proof Toolkit · oimiragieo
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 warm-vs-cold measurement trap (a warm dogfood run can hide a real cold-path win), the byte-identical output-proof obligation before trusting any merge/skip/reorder speedup, 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.

0 repo stars
▌
Tensor Grep Design Authorization Ladder · oimiragieo bundle
Use when demand is SATISFIED but product code is not yet authorized: writing or auditing docs/requirements+design+decisions packets, recording skip-Fable waivers, splitting PERF vs HONESTY sub-dispositions, or resisting "design on main = shipped" (A117/A122). Covers the authorization ladder (measure → design packet → Sol exact-commit → optional Fable waiver → deliberate build go → TDD+A3), measurement-envelope timeouts (A120), backlog+R7 pairing when raising request_queue_size under ThreadingMixIn (A121), and Sol audits that hash exact commit bytes. NOT for demand measurement itself (tensor-grep-demand-gate-measurement) or unconstrained product builds without a recorded go.

0 repo stars
▌
Tensor Grep Index Fingerprint Freshness · oimiragieo
Use when working on index/reuse staleness detection — the Rust `.tg_index` reuse path, a cached parse/symbol/semantic index that is served on a LATER query, `staleness_reason` / `compute_tree_fingerprint` / mtime-size identity, or a "reused index must not serve the wrong tree" guard (M17). Covers identity-anchor-first (canonical root, not a raw path string), the alias/swap RED shape that a naive wrong-root comparison cannot reach, the fingerprint ladder (mtime+size → ctime → content-checksum → whole-tree), and bounded sampling with NAMED boundaries so the honest cap is a reopen trigger, not a silent hole. Triggers: "index reuse", "staleness", "fingerprint", "wrong tree", "stored root", "canonical_root_of", "mtime size", "ctime", "sampling cap", "M17", "swap". Sibling of tensor-grep-cross-platform-path-confinement (the alias swap is a junction there) and tensor-grep-hermetic-hostile-tests (the fixture must BITE); this one is the identity/freshness discipline for CACHED INDEX REUSE.

0 repo stars
▌
Tensor Grep Cross Platform Path Confinement · oimiragieo
Use when writing or reviewing any code that confines filesystem access to a root (checkpoint snapshot/undo, LSP documentChanges, index reuse, install/upgrade, scan-writer paths) and must behave CORRECTLY on BOTH Windows and POSIX — especially junctions vs symlinks vs hardlinks, the drive-absolute `/C:/...` escape that only exists on Windows, canonicalize-or-fail-closed, handle-anchored identity versus resolve-then-act (TOCTOU/A38/A48), or a path-shape transform that is platform-meaningful (A84). Triggers: "junction", "symlink", "drive-absolute", "reparse point", "path confinement", "within_root", "TOCTOU", "canonicalize", "opened identity", "CWE-59", "CWE-1386", "mklink /J", "out-of-root". Sibling of tensor-grep-hermetic-hostile-tests (the fixture that must BITE) and tensor-grep-index-fingerprint-freshness (identity of the tree being served); this one is the cross-platform path-security discipline itself.

0 repo stars
▌
Tensor Grep Argv Normalization And Shadowing · oimiragieo
Use when modifying, auditing, or testing an argv normalizer or a CLI front door that REWRITES one invocation shape into another (bootstrap `_normalize_search_invocation` / `main_entry`, `SEARCH_OPTION_FIRST_FLAGS`→`tg search ...` in rust_core), adding or auditing a `--` end-of-options sentinel on a builder that appends a caller-influenced positional, auditing root-option shadowing (an option parsed as a subcommand/positional and vice versa), enumerating the doors a rewritten argv can reach (A83), or adding a flag to a SHARED argv builder and needing to know which consumers parse vs stream the output. Triggers: "argv rewrite", "normalizer", "option-first", "flag shadowing", "CWE-88", "end-of-options", "`--` sentinel", "shape-monotonic", "the front door rewrote my invocation". Sibling of tensor-grep-change-control (the four registration sites) and tensor-grep-config-and-flags (the search-flag allowlists); this one is the normalizer/argv-shape discipline itself.

0 repo stars
▌
Tensor Grep · oimiragieo bundle
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.

0 repo stars
▌
Tensor Grep Gpu · oimiragieo
Use when exercising tensor-grep experimental GPU paths — devices/doctor probes, --gpu-device-ids search, agent GPU evidence, calibrate crossover. Distinguishes inventory detection from actual NativeGpuBackend promotion proof; CPU auto-fallback is not a GPU win.

0 repo stars
▌
Tensor Grep Ledger · oimiragieo
Use when coordinating multiple agents on the same repo with tg ledger — advisory claim/release/list (Slice 1) and content-addressed finding record/find reuse (Slice 2). Never blocks edits; overlaps are informational. Distinct from tg evidence emit (produces receipts) and from docs/BACKLOG.md (product backlog, not this CLI).

0 repo stars
▌
Tensor Grep Prepare · oimiragieo
Use when an agent needs one-call edit readiness before changing code — tg prepare returns primary target, confidence, callers/blast-radius floor, validation commands, and claim/evidence coordination hooks. Prefer over the multi-step orient→search→agent→route-test→callers→evidence→ledger loop for routine edits. Pair with tg install-dense once for semantic find quality.

0 repo stars
▌
Tensor Grep Add Language · oimiragieo
Use when adding a new language to tensor-grep's tree-sitter symbol graph (defs/refs/callers/blast-radius, `tg source`, `tg imports`) — registering a `LanguageSpec` in `lang_registry.py`, writing a new `src/tensor_grep/cli/lang_<x>.py` extractor module, debugging a C/C++ declarator-walker mis-kind, or verifying a banked "the fix is obviously X" hypothesis against a live parse tree before writing declarator-shape logic. Triggers and keywords include add a language, add <language> to tensor-grep, new grammar, tree-sitter grammar, lang_registry, register_language, new lang_<x>.py module, symbol-graph language, onboard a language, "tg doesn't find symbols in <language>", `_target_language_for_path`, grammar-missing provenance, C/C++ symbol graph, function-pointer variable mis-kinded as function, declarator shape.

0 repo stars
▌
Tensor Grep Build And Env · oimiragieo
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, a dependency upper-cap silently downgrading tensor-grep on a newer Python, a flaky/un-retried rustup pinned-toolchain fetch, the CPU-SAFE scope of local Rust compiles on the shared desktop, the A60 WSL-venv destruction trap, the uv.lock hand-splice discipline, or a broken-WSL-stdlib verify-before-trust probe. Gives exact copy-paste setup commands and the traps that have each cost a real cycle.

0 repo stars
▌
Tensor Grep Change Control · oimiragieo bundle
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, claiming a fix or speedup is done, or deciding whether a follow-up commit is truly "docs-only"/"comment-only". 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, a test proving nothing until seen fail on the pre-fix baseline, gating comments/docstrings with the same rigor as code, diff-review-is-not-measurement-review, and the `ast.dump()` behavior-neutral proof technique) and the historical incident behind each.

0 repo stars
▌
Tensor Grep Find And Route · oimiragieo
Use when vocabulary-mismatched queries need whole-repo hybrid search via tg find (BM25 + optional dense RRF, no regex pre-filter), or when verifying context-render vs edit-plan target agreement with tg route-test before trusting an edit plan. Distinct from tg search --rank/--semantic (those re-rank an existing regex match set).

0 repo stars
▌
Tensor Grep Run And Operate · oimiragieo
Use when running the `tg` CLI day-to-day — exact syntax for orient, search --rank, defs/refs/callers/blast-radius, agent, docs-coverage, context, session open/refresh/serve/daemon, checkpoint, scan --ruleset, run, mcp, doctor, dogfood, upgrade; the symbol-command 0/1/2 exit-code contract and what an agent should branch on; bounding a scan with `--deadline` and reading `partial`/`result_incomplete`/`deadline_limit` truncation flags; excluding vendor/skill trees with `--ignore` on orient/agent/docs-coverage; `tg context --max-tokens` budgets (default 16000, 0=opt-out); where JSON artifacts and cache state land on disk; starting the MCP server; or a whole-repo `tg search` that hangs. The OPERATOR runbook (how to invoke), not theory or audit workflow.

0 repo stars
▌
Tensor Grep Backlog Campaign · oimiragieo
Use when asked to deep-dive, audit, fix, or drain the tensor-grep backlog, or to investigate and rank next work and produce SPEC/TDD plans without implementing. Triggers include "work the backlog", "what next", "investigate and plan", and backlog-completion campaigns. This is the meta-orchestrator for the repo skill library; load tensor-grep-change-control before editing.

0 repo stars

991 published skills · page 3 of 10