Instructions file CodexOpenCode
Instructions for jakkaj/tools.
Instructions file CodexOpenCode
Instructions for jakkaj/tools.
Instructions file
Instructions for jakkaj/tools, covering claude.md — contributor / dev guide, platform support & quick setup, what this repo is, layout and adding or editing a skill.
Skill Claude CodeCodex
FlowSpace-first codebase research agent for parallel subagent exploration with structured output for parent orchestrator synthesis. Domain-aware v2.
Skill Claude CodeCodex
Deep shopping research skill for finding products similar to a reference link or image, benchmarking global pricing, comparing quality/provenance, and creating a reusable buying dossier with links, per-item prices, shipping notes, and value-focused recommendations.
Skill Claude CodeCodex
Craft structured, domain-aware research prompts to leverage deep research agents for solving coding challenges. V2 with domain boundary awareness.
Skill Claude CodeCodex
Universal clarity utility - deep think 5 critical insights and discuss conversationally to build shared understanding. Run after any spec/plan/tasks/code. Domain-aware v2.
Skill Claude CodeCodex
Convert any content (markdown, specs, plans, findings) into a polished, self-contained static HTML document with a modern light/muted design. V2 standalone.
Skill Claude CodeCodex
Establish or refresh the project constitution and align the supporting norms documents before any planning phases begin. Re-entrant command that preserves user customizations during updates. Domain-aware v2.
Skill Claude CodeCodex
Generate terse, industry-standard issue text from specs and plans for Azure DevOps, GitHub Issues, or any tracker. Domain-aware v2.
Skill Claude CodeCodex
Collaboratively identify and formalize an existing codebase concept as a named domain. No files are moved — this is about communication and traceability, not refactoring.
Skill Claude CodeCodex
The single front door to the SDD pipeline (docs/plans/): research → plan → workshop → ADR → phase tasks → implement → progress → review → ship. Use when the user wants to plan, research, explore, specify or architect (now one atomic 'plan' step → one document: business spec + implementation plan), clarify, workshop…
Skill Claude CodeCodex
Brief pre-work alignment for any stage. Use before planning, coding, editing, reviewing, or delegating when the user asks you to understand the thesis, vibe, intent, current position, or direction of a request or existing thing. Returns 2–4 bold-labelled one-sentence observations and one short synthesis, then stops.
Skill Claude CodeCodex
Generate a domain-aware handover document for LLM agent continuity. V2 standalone rewrite.
Skill Claude CodeCodex
Adaptive, high-signal post-action validation for whatever was just produced — unified plan, tasks, code change, workshop, legacy spec, or any artifact. Proves the claims that matter, reports only findings likely to change action, and adds independent critics only when risk or uncertainty earns them. Thesis- and…
Skill Claude CodeCodex
Pre-task token discipline. Use before any task when every read, tool call, line of reasoning, and output token must materially advance the stated goal or thesis, without weakening correctness or safety.
Skill Claude CodeCodex
Relentlessly interview the user about any plan, design, decision, proposal, codebase, architecture, strategy, document, workflow, or subject until there is shared understanding. Use when the user wants to stress-test an idea, be challenged on a design, prepare for review, uncover hidden assumptions, or says “grill me”.
Skill Claude CodeCodex
Run long, deep web research via the Perplexity API directly (bypassing the perplexity MCP server, which times out at 5 minutes). Use this when a research question needs the slow sonar-deep-research model — multi-source investigation, literature sweeps, "find everything about X" — or any Perplexity call you expect to…