TIKAZI

35 mods across 2 repositories, 9 stars between them.

context-economy

01

TIKAZI/TIKAZ-AI-Skills

Skill Claude CodeCodex

Automatically prepare fidelity-first, bounded context when users paste text, attach files or folders, provide webpages or PDFs for Markdown conversion, continue long conversations, or supply documents containing images and complex tables. Route each input through Text, Hybrid, or Source; reduce exact or…

6 4d ago A 84 tokens original MIT

context-audit

02

TIKAZI/TIKAZ-AI-Skills

Skill Claude CodeCodex

Diagnose context relevance, redundancy, traceability, safety, cacheability, and recoverability. Use when files, prompts, rules, or context packs may contain duplication, conflicts, stale material, prompt injection, secret-shaped values, unstable prefixes, or weak evidence anchors.

6 4d ago A 58 tokens original MIT

context-benchmark

03

TIKAZI/TIKAZ-AI-Skills

Skill Claude CodeCodex

Measure context preparation across fixed cases. Use when token savings, hard-budget compliance, protected-fact recall, evidence anchors, determinism, runtime, or downstream answer quality must be demonstrated with reproducible evidence rather than marketing claims.

6 4d ago A 49 tokens original MIT

context-pack

04

TIKAZI/TIKAZ-AI-Skills

Skill Claude CodeCodex

Prepare files, folders, code, logs, and structured data as a bounded, traceable context pack for Codex. Use when source material must be converted, deduplicated, selected, budgeted, or handed off with exact evidence anchors.

6 4d ago A 52 tokens original MIT

TIKAZI/TIKAZ-AI-Skills

Skill Claude CodeCodex

Use when a long or repetitive conversation has no source file and must be converted into a recoverable task state before continuation, handoff, or compaction.

6 4d ago A 35 tokens original MIT

engineering

06

TIKAZI/TIKAZ-AI-Skills

Skill Claude CodeCodex

Orchestrate production software delivery through specification, repository intelligence, implementation, testing, security review, data operations, and release evidence. Use for substantial code changes that cross files, systems, or deployment boundaries.

6 4d ago A 43 tokens original MIT

code-intelligence

07

TIKAZI/TIKAZ-AI-Skills

Skill Claude CodeCodex

Understand repositories as systems: map code structure and semantic relationships, analyze change impact, review pull requests, and plan safe refactors. Use when a task involves unfamiliar codebases, dependency tracing, architecture mapping, PR review, or cross-file refactoring.

6 4d ago A 54 tokens original MIT

TIKAZI/TIKAZ-AI-Skills

Skill Claude CodeCodex

Run production software work from specification through planning, implementation, testing, review, and release. Use for substantial repository changes that require explicit acceptance criteria and verification evidence.

6 4d ago A 36 tokens original MIT

TIKAZI/TIKAZ-AI-Skills

Skill Claude CodeCodex

Statically inspect third-party agent skills before installation for prompt injection, destructive commands, credential access, dependency risk, hidden network behavior, and unsafe permissions. Use before installing or publishing an unfamiliar skill.

6 4d ago A 44 tokens original MIT

supabase-operations

10

TIKAZI/TIKAZ-AI-Skills

Skill Claude CodeCodex

Design, deploy, and operate Supabase projects with explicit schema, migration, security, backup, and observability checks. Use for Supabase architecture, Postgres changes, auth, storage, edge functions, or deployment operations.

6 4d ago A 50 tokens original MIT

video-workbench

11

TIKAZI/TIKAZ-AI-Skills

Skill Claude CodeCodex

Engineer repository-backed media processing workbenches across ingestion, job state, processing, review, export, frontend states, QA evidence, and deployment configuration. Use when building or changing a video or audio workflow application rather than analyzing media content.

6 4d ago A 51 tokens original MIT

frontend-design

12

TIKAZI/TIKAZ-AI-Skills

Skill Claude CodeCodex

Orchestrate product-aware frontend art direction, implementation, responsive QA, code impact analysis, and engineering handoff. Use for websites, landing pages, web apps, dashboards, mobile concepts, and desktop shells that need one coherent visual world and objective verification.

6 4d ago A 54 tokens original MIT

TIKAZI/TIKAZ-AI-Skills

Skill Claude CodeCodex

Direct, design, implement, animate, critique, audit, polish, and deploy distinctive production frontend interfaces for websites, landing pages, web apps, dashboards, mobile concepts, and desktop shells. Use for new frontend builds, redesigns, bland or visually generic UI, messy interfaces, design systems, Vue Bits or…

6 4d ago A 126 tokens original MIT

knowledge-research

14

TIKAZI/TIKAZ-AI-Skills

Skill Claude CodeCodex

Orchestrate source ingestion, academic research, product decisions, personal knowledge retrieval, and evidence-backed memory feedback. Use when a task requires traceable research, document normalization, reusable knowledge, or a decision under uncertainty.

6 4d ago A 47 tokens original MIT

academic-research

15

TIKAZI/TIKAZ-AI-Skills

Skill Claude CodeCodex

Plan literature reviews, search and evaluate sources, synthesize evidence, draft research writing, and perform peer-review-style critique. Use for academic research, papers, systematic comparisons, citation-backed reports, or methodological review.

6 4d ago A 46 tokens original MIT

TIKAZI/TIKAZ-AI-Skills

Skill Claude CodeCodex

Convert PDF, Office, HTML, images, and audio into structured Markdown while preserving headings, tables, links, and provenance where possible. Use when source documents need extraction or normalization before research and knowledge capture.

6 4d ago A 46 tokens original MIT

TIKAZI/TIKAZ-AI-Skills

Skill Claude CodeCodex

Retrieve relevant personal project decisions, playbooks, knowledge, skills, and verified outcomes before important work, then record only knowledge that materially affected the result. Use for reusable personal workflows backed by a user-controlled knowledge base.

6 4d ago A 48 tokens original MIT

product-strategy

18

TIKAZI/TIKAZ-AI-Skills

Skill Claude CodeCodex

Support product discovery, market research, positioning, prioritization, execution planning, go-to-market, and product analytics. Use when a product decision requires evidence, alternatives, tradeoffs, and measurable outcomes.

6 4d ago A 44 tokens original MIT

TIKAZI/TIKAZ-AI-Skills

Skill Claude CodeCodex

Plan and operate a one-person business across product, content, finance, operations, legal coordination, customer support, and engineering. Use for cross-functional solo-business decisions and execution systems.

6 4d ago A 41 tokens original MIT

presentation

20

TIKAZI/TIKAZ-AI-Skills

Skill Claude CodeCodex

Route and govern presentation creation across browser-editable HTML decks, native editable PowerPoint, and magazine-style web decks. Use when a presentation request needs narrative planning, format selection, source tracking, rendering QA, and verified delivery.

6 4d ago A 47 tokens original MIT

html-deck-builder

21

TIKAZI/TIKAZ-AI-Skills

Skill Claude CodeCodex

Plan and build browser-editable HTML presentations with narrative contracts, responsive slide layouts, keyboard navigation, offline-safe assets, and render verification. Use when the final presentation should be an HTML file or browser-based deck rather than a native PPTX.

6 4d ago A 53 tokens original MIT

magazine-web-deck

22

TIKAZI/TIKAZ-AI-Skills

Skill Claude CodeCodex

Create editorial or Swiss-inspired single-file web presentations with strong typographic hierarchy, horizontal navigation, responsive composition, and restrained motion. Use for keynote-like web decks, editorial stories, launches, and visually distinctive browser presentations.

6 4d ago A 49 tokens original MIT

TIKAZI/TIKAZ-AI-Skills

Skill Claude CodeCodex

Plan, create, revise, and verify native editable PowerPoint presentations with source-aware content, reusable layouts, speaker notes, and rendered visual QA. Use when the deliverable must be an editable .pptx or must reuse an existing PowerPoint template.

6 4d ago A 56 tokens original MIT

video-intelligence

24

TIKAZI/TIKAZ-AI-Skills

Skill Claude CodeCodex

Orchestrate evidence-based video research across platforms, transcripts, Whisper fallback, keyframes, source verification, and cross-video synthesis. Use for one or many videos when the result must be traceable, comparable, and reusable rather than a generic summary.

6 4d ago A 54 tokens original MIT