Skip to content
cccskills
FreePublished on GitHub

ralph-specum-prototype

This skill should be used only when the user explicitly invokes `$ralph-specum-prototype`, or explicitly asks Ralph Specum in Codex to run, resume, quick-run, or cancel an optional prototype.

The English summary is being prepared. Showing the original description.

tzachbon/smart-ralph
See how to install

Files included (2)

  • SKILL.md2.5 KB
  • agents/openai.yaml297 B

SKILL.md (original)

Review the instructions the agent will receive before you install.

Ralph Specum Prototype

Coordinate one optional prototype overlay. Delegate source work to a child agent and keep the main Ralph phase unchanged until the recorded handoff.

Load the contract

Derive RALPH_CODEX_PLUGIN_ROOT from this loaded skill: take the directory containing SKILL.md, then its parent skills directory, then the next parent. Never derive the plugin root from the project working directory.

Read ../../references/prototype-coordinator.md from this skill directory completely before any prototype mutation. Treat it as the source of truth for direct, suggested, resume, quick, cancel, isolation, review, publication, and handoff behavior.

Route the request

  1. Resolve an explicit path, exact spec name, or .current-spec with "$RALPH_CODEX_PLUGIN_ROOT/scripts/resolve_spec_paths.py". Use only the returned basePath, specRoot, settings, and warnings.
  2. Parse one mode: direct by default, suggested with a return phase, resume by ID, quick, or cancel by ID.
  3. Reconcile candidate and final records before reserving, resuming, reviewing, or publishing.
  4. Use only these mechanics:
    • "$RALPH_CODEX_PLUGIN_ROOT/scripts/locked_state.py" for activePrototypes and every state mutation
    • "$RALPH_CODEX_PLUGIN_ROOT/scripts/prototype_records.py" for exact candidate bytes, review receipts, immutable publication, reconciliation, and downstream selection
    • "$RALPH_CODEX_PLUGIN_ROOT/scripts/prototype_harness.py" for deterministic control outcomes and retry metadata
  5. Spawn internal builders with child-agent tools. Store only the returned agentId; wait with wait_agent and stop with interrupt_agent. Never use create_thread or a threadId for an internal builder.
  6. Keep normal capture, dirty-path transfer, verdict, handoff, deletion, and remote actions under explicit user control. Let quick mode own its bounded choices and continue to design after every terminal outcome.

Completion gate

Finish only after the coordinator contract verifies the immutable final bytes, removes the active entry through the locked helper, applies stale and handoff gates, and reports the local source disposition. Keep every remote pointer pending until the user authorizes that exact remote write.

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

Command Development

Free

This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.

The English summary is being prepared. Showing the original description.

tzachbon/smart-ralph559Updated Sep 16, 2026

communication-style

Free

Output rules for all agents - concise, scannable, actionable. Based on Matt Pocock's planning principles.

The English summary is being prepared. Showing the original description.

tzachbon/smart-ralph559Updated Sep 16, 2026

communication-style

Free

This skill should be used when generating spec artifacts (research.md, requirements.md, design.md, tasks.md), formatting agent output, structuring phase results, or when any Ralph agent needs guidance on concise, scannable output formatting. Applies to all Ralph spec phase agents.

The English summary is being prepared. Showing the original description.

tzachbon/smart-ralph559Updated Sep 16, 2026

delegation-principle

Free

Core principle that the main agent is a coordinator, not an implementer. All work must be delegated to subagents.

The English summary is being prepared. Showing the original description.

tzachbon/smart-ralph559Updated Sep 16, 2026

Hook Development

Free

This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.

The English summary is being prepared. Showing the original description.

tzachbon/smart-ralph559Updated Sep 16, 2026

interview-framework

Free

This skill should be used when a Ralph phase must identify critical user decisions, run a layered grill, persist partial answers, obtain explicit approval, or resume an interrupted phase interview before delegating artifact work.

The English summary is being prepared. Showing the original description.

tzachbon/smart-ralph559Updated Sep 16, 2026

See all skills by tzachbon

Report a problem with this skill