Instructions file CodexOpenCode
Instructions for cskwork/oh-my-symphony, covering agents.md: codex cli entry point, source of truth: skills/symphony-skill, available skill (operator-facing), symphony-skill and worker-side guidance.
Instructions file Gemini CLI
Instructions for cskwork/oh-my-symphony, covering gemini.md: gemini cli entry point, skill activation, available skill (operator-facing), symphony-skill and worker-side guidance.
Skill Claude CodeCodex
Single Symphony operator router for Kanban tickets, service/TUI runs, WORKFLOW.md and prompt config, lane customization, delegation, production-ready app delivery planning, OneShot runs, repo and monorepo bootstrap, and worker failure triage.
Instructions file
Claude Code instructions for cskwork/pptx-to-html-updated, covering claude.md, project overview, essential commands, installation & setup and install dependencies (required first time).
Skill Claude CodeCodex
Convert PowerPoint (.pptx) presentations to standalone HTML format with FULL style, position, and formatting preservation. Accurately replicates slides with exact fonts, colors, shapes, backgrounds, layouts, hyperlinks, videos, audio, and tables. Use for web-friendly presentations that maintain visual fidelity and…
Plugin Claude Code
Objective-driven dev router. Use for "fix bug", "add feature", "prototype", "QA/verify", or "code review".
Plugin Claude Code
Objective-driven dev router. Use for "fix bug", "add feature", "prototype", "QA/verify", or "code review".
Skill Claude CodeCodexCursor
Objective-driven dev router. Use for "fix bug", "add feature", "build a new app", "prototype", "QA/verify", "code review", "teach/explain", "map this codebase", "break this into tickets", "improve the architecture", "draw a diagram", "measure skill lift", or "turn this into a skill".
Instructions file Gemini CLI
Instructions for cskwork/supergoal-skill, a project described as: One objective in, a verified result out. An agent skill that runs a full, gated dev process with expert subagents and refuses to declare done until a machine-checkable gate passes. Bilingual (EN/한국어) onboarding & live walkthrough.
Agent
Pre-planning analyst — turns a raw objective into a machine-checkable brief, and (GREENFIELD) validates real demand before any build opens.
Agent
Plan-phase architect — freezes a surgical, grounded implementation plan with contracts; pressure-tests it against the project's own docs before it freezes.
Agent
Adversarial Reviewer — independent reviewer for the conditional pre-Build plan attack (named escalation trigger required) and for REVIEW-ONLY mode. Re-reads request/docs and tries to disprove the plan or diff. Never edits src; never writes or weakens tests.
Agent
Read-only, DB-independent data reader for supergoal evidence - fetches test auth, source-of-truth expected values, schema metadata, and dataset/environment diffs over MySQL/PostgreSQL/SQLite. Returns small named values + diffs, never raw rows or secrets. Issues SELECT-class statements only; never writes.
Agent
DEBUG-mode root-cause analyst — reproduces the failure, runs hypothesis-driven diagnosis to one confirmed cause, and writes a minimal-fix plan. Alt persona for deep causal tracing — tracer.
Agent
UI/UX Designer-Developer for user-facing surfaces — implements to the Expressive baseline (taste-skill-v2, always) plus the Functional functional-ui density overlay when the conductor names it, and dial values. Used only on UI/UX jobs; never self-approves.
Agent
Builder — implements every planned criterion of the approved plan with the smallest correct change, or an R-LOOP re-entry fix. Never approves its own work.
Agent
Codebase mapping specialist — maps the code a change touches with file:line evidence. Read-only; never edits source.
Agent
Independent final verifier — consumes tester evidence for browser/CLI work, reruns REAL tests, and owns the final verdict, GOAL ticks, and R-LOOP. Never drives the app, queries the DB, or edits product code.
Agent
Evidence-only black-box tester — drives browser/CLI scenarios, captures reproducible proof, and returns it to qa-auditor. Never owns the final verdict, GOAL ticks, or R-LOOP.
Agent
Verify-phase security reviewer — OWASP, secrets, injection, SSRF, unsafe crypto. Findings only; never edits source.
Agent
Skill-authoring specialist — turns one approved pattern into a cross-agent-portable SKILL.md within the agentskills.io limits. Writes only the skill directory.
Agent
History-mining specialist — runs the mechanical miner, clusters intents, and returns 3-5 ranked skill candidates with recurrence evidence. Read-only; never edits source or creates skills.
Skill Claude CodeCodex
Create architecture, workflow, sequence, data-flow, and lifecycle/state diagrams as self-contained HTML with inline SVG, dark/light themes, and PNG/JPEG/WebP/SVG export.
Instructions file CodexOpenCode
Instructions for cskwork/coding-agent-rules, covering ten commandments for coding agents, response & documentation style and repository rules.