Skill Claude CodeCodex
Use for closing test-coverage gaps incrementally — when a function in this repo's logic/library layer has zero test coverage and needs one focused unit test matching the repo's existing test runner, mock convention, and file-placement style. Covers a happy path and an edge/error path. Writes exactly one test per run.…
Plugin Claude Code
Plugin marketplace listing 1 plugin: robcsaszar-prose.
Plugin Claude Code
Draft and review skill for prose that detects AI writing patterns and rewrites in an authentic, channel-appropriate voice.
Instructions file CodexOpenCode
AGENTS.md instructions for robcsaszar/prose, covering agents.md, mission and judgment boundaries.
Skill Claude CodeCodex
Drafts, revises, and humanizes prose. Use when writing or revising anything human-facing — blog posts, articles, documentation, runbooks, specs, emails, social media posts, IM, marketing copy, or UI text, and for fiction, poetry, scripts, and memoir. Also use when a draft needs checking or fixing for AI writing…
Plugin Claude Code
Plugin marketplace listing 1 plugin: robcsaszar-delve.
Plugin Claude Code
A skill that activates a rigorous research collaborator mode: flags confidence levels, prevents hallucinations, cites sources, and surfaces assumptions.
Instructions file CodexOpenCode
AGENTS.md instructions for robcsaszar/delve, covering agents.md, mission and judgment boundary.
Skill Claude CodeCodex
Activates a rigorous research collaborator mode that flags confidence levels, prevents hallucinations, cites sources, and surfaces assumptions. Use when user asks to research a topic, investigate a claim, explore a technical concept, or provides multiple URLs or specs to research simultaneously. Not for quick factual…
Plugin Claude Code
Plugin marketplace listing 1 plugin: robcsaszar-scaffold.
Plugin Claude Code
Skills for creating and reviewing AGENTS.md, CONTEXT.md, and DESIGN.md files that give AI agents persistent, structured context about a codebase.
Instructions file CodexOpenCode
AGENTS.md instructions for robcsaszar/scaffold, covering agents.md, mission, layout convention, judgment boundaries and adding a skill.
Skill Claude CodeCodex
Creates, reviews, and improves AGENTS.md files for repositories. Review mode scores the file, then offers to apply the fixes to it. Use when user wants to generate agent documentation, scaffold AGENTS.md, review or improve an existing AGENTS.md, or make their repo agent-friendly. Don't use for documenting codebase…
Skill Claude CodeCodex
Create or review CONTEXT.md files — hierarchical, LLM-optimized repository documentation describing what a codebase IS (architecture, domain model, conventions). Dual mode — creates a new CONTEXT.md at a user-specified path, or reviews an existing file for completeness and anti-patterns and then offers to apply the…
Skill Claude CodeCodex
Create or extract a DESIGN.md file — a spec-compliant document combining YAML design tokens (name, colors, typography, spacing, rounded, components) with 8 ordered markdown sections (Overview through Do's & Don'ts) as persistent design-system context for AI agents. Use when adding design context to a project…
Plugin Claude Code
Plugin marketplace listing 1 plugin: robcsaszar-retrospective.
Plugin Claude Code
Reviews how a Claude Code session was conducted rather than what it shipped — classifies its shape, scores the run, flags where the context window went, and turns repeated hand-work into wire-ins for the skills the session used.
Instructions file CodexOpenCode
AGENTS.md instructions for robcsaszar/retrospective, covering agents.md, mission and judgment boundaries.
Skill Claude CodeCodex
Reviews how the current session was conducted — not what it produced. Classifies the session against a fixed taxonomy of shapes, scores how well it was run, names where the context window was spent badly with fixes actionable on the very next turn, and turns repeatable procedures it performed by hand into concrete…
Plugin Claude Code
Plugin marketplace listing 1 plugin: robcsaszar-ai-forge.
Plugin Claude Code
A workflow of skills for creating, updating, judging, reviewing, evaluating, and auditing AI skills and agent definitions.
Instructions file CodexOpenCode
AGENTS.md instructions for robcsaszar/ai-forge, covering agents.md, mission, layout convention, judgment boundaries and pre-publish checks.
Skill Claude CodeCodex
HITL (Human-In-The-Loop) application of a numbered list one item at a time — status board upfront, per-item approve/skip, approve-all mode, and one opt-in commit bundling all approved items after the loop. Use when stepping through ai-forge-judge findings or any numbered changes. Triggers are apply these, go through…
Skill Claude CodeCodex
Batch-evaluate all skills and agents in the repo with ai-forge-judge and render a single consolidated grade report sorted by grade (worst first) so effort is directed correctly. Use when reviewing overall skill/agent quality, finding where to invest improvement effort, or after bulk changes. Triggers are audit all…