Agent skill

Ralph Specum Triage

by tzachbon in tzachbon/smart-ralph

This skill should be used only when the user explicitly asks to use $ralph-specum-triage, or explicitly asks Ralph Specum in Codex to triage a large effort into multiple specs.

MITAuto-check passed

Install Ralph Specum Triage

skills CLI
$ npx skills add tzachbon/smart-ralph --skill ralph-specum-triage -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install tzachbon/smart-ralph ralph-specum-triage --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/tzachbon/smart-ralph.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/ralph-specum-codex/skills/ralph-specum-triage .claude/skills/ralph-specum-triage && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
ralph-specum-triage
GitHub stars
559
Token cost
~1.7k tokens
SKILL.md length
865 words
Files
2
Skills in repo
26
Repo updated
First seen
Licence
MIT

At a glance

This skill should be used only when the user explicitly asks to use $ralph-specum-triage, or explicitly asks Ralph Specum in Codex to triage a large effort into multiple specs.

  • Works in 12 steps: Parse exact --quick and exact… → Check specs/.current-epic. If an active… → Validate the resolved epic name against… → …
  • Explicitly asks to use $ralph-specum-triage
  • SKILL.md covers Contract, Action, Output Shape and Stop Behavior, plus 1 more section
  • Calls jq and go

What it does

Ralph Specum Triage is an agent skill from tzachbon/smart-ralph. This skill should be used only when the user explicitly asks to use $ralph-specum-triage, or explicitly asks Ralph Specum in Codex to triage a large effort into multiple specs.

Its SKILL.md is about 1.7k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).

The repository describes itself as: Spec-driven development with smart compaction. Claude Code plugin combining Ralph Wiggum loop with structured specification workflow. The licence is MIT.

When your agent uses it

  • Explicitly asks to use $ralph-specum-triage
  • Explicitly asks Ralph Specum in Codex to triage a large effort into multiple specs

Example prompts

  • “/ralph-specum-triage”

Workflow steps

12 steps, taken from the first numbered list in SKILL.md.

  1. Parse exact --quick and exact --interactive tokens before routing. Reject both together, -q, variants, and natural-language substitutes.
  2. Check specs/.current-epic. If an active epic exists, load its .epic-state.json as STATE and normalize mode before any possible question…
  3. Validate the resolved epic name against ^[a-z0-9]+(-[a-z0-9]+)*$ before constructing any path. Reject invalid names. If…
  4. Resolve or create only the epic directory, .progress.md, and .epic-state.json. Serialize the name and goal through a JSON encoder such as…
  5. For a new epic, run scripts/phase_gate.py mode STATE with the exact parsed mode flag, then register specs/.current-epic before discovery…
  6. Resolve the output destination from explicit input and configuration. In exact quick mode, use local Spec files as the deterministic…
  7. Ensure skill discovery pass 1 exists for the epic goal. Collect plugin, project .agents/skills, project .claude/skills, and current…
  8. Load skills/interview-framework-codex/SKILL.md, its required algorithm and domain-modeling references, and every selected domain contract…
  9. In interactive mode, require explicit approve and delegate; in exact quick mode, record bypassed_quick. In both modes, run phase_gate.py…
  10. Read-only exploration children may inspect seams, constraints, and existing boundaries, but they write no epic artifact.
  11. Keep the existing epic-state, read-only exploration, and multiwriter flow, plus each child packet, identity tuple, and receipt behavior…
  12. The coordinator does not assemble, format, or revise artifact content. Validate the gated writer outputs and persist .epic-state.json with…

What it can do on your machine

Read from SKILL.md and the folder at commit ac7251a. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • jq
    • go

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Ralph Specum Triage loads about 1.7k tokens when it runs. Until then it costs about 50 tokens; SKILL.md has 865 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~50
When it runs · the whole SKILL.md, loaded when a task matches
~1.7k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from tzachbon/smart-ralph at commit ac7251a, republished under its MIT licence (© tzachbon). 865 words, ~1,656 tokens.

Download SKILL.mdSave it as .claude/skills/ralph-specum-triage/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
ralph-specum-triage
description
This skill should be used only when the user explicitly asks to use `$ralph-specum-triage`, or explicitly asks Ralph Specum in Codex to triage a large effort into multiple specs.
metadata.surface
helper
metadata.action
triage

Ralph Specum Triage

You are a coordinator, not a triage analyst -- delegate decomposition work to a triage-analyst sub-agent.

Contract

  • Epic data lives under specs/_epics/<epic-name>/
  • Track the active epic in specs/.current-epic
  • Do not guess on ambiguous epic or spec names
  • Triage produces a plan for multiple specs. It does not implement them

Action

  1. Parse exact --quick and exact --interactive tokens before routing. Reject both together, -q, variants, and natural-language substitutes.
  2. Check specs/.current-epic. If an active epic exists, load its .epic-state.json as STATE and normalize mode before any possible question. With exact --quick, resume the matching active epic without prompting; an explicit different epic must include its goal. In interactive mode, summarize status and offer resume, details, or a new epic.
  3. Validate the resolved epic name against ^[a-z0-9]+(-[a-z0-9]+)*$ before constructing any path. Reject invalid names. If specs/_epics/<epic-name>/.epic-state.json already exists, reuse and resume it without replacing state or progress. If the directory exists without a valid state, stop and require a different name or an explicit user-authorized reset. Only a missing directory may be initialized.
  4. Resolve or create only the epic directory, .progress.md, and .epic-state.json. Serialize the name and goal through a JSON encoder such as jq --arg. Use .epic-state.json as STATE for every phase gate command with phase triage. Use .epic-state.json as STATE for every writer. After that, do not require .ralph-state.json. Create no research.md, epic.md, or generated plan.md before approval.
  5. For a new epic, run scripts/phase_gate.py mode STATE with the exact parsed mode flag, then register specs/.current-epic before discovery. Exact quick mode asks no setup question; missing required name or goal is an input error.
  6. Resolve the output destination from explicit input and configuration. In exact quick mode, use local Spec files as the deterministic default and ask nothing. Only interactive mode may ask one administrative destination question when the destination remains ambiguous; that answer never satisfies the interview gate.
  7. Ensure skill discovery pass 1 exists for the epic goal. Collect plugin, project .agents/skills, project .claude/skills, and current harness catalog entries. Select explicitly named skills and record shadowed duplicates.
  8. Load skills/interview-framework-codex/SKILL.md, its required algorithm and domain-modeling references, and every selected domain contract in both interactive and quick mode. In interactive mode, follow the algorithm for critical decomposition boundaries, stable cross-spec contracts, dependency choices, and sequencing risks. Ask no storage, naming, branch, or discoverable question.
  9. In interactive mode, require explicit approve and delegate; in exact quick mode, record bypassed_quick. In both modes, run phase_gate.py check-delegation with phase triage and the current loaded-manifest identity before every artifact-producing child. Apply the shared hard-transition invariant before every triage artifact writer. A failed check-delegation in either mode stops this invocation before phase transition, child dispatch, or target-artifact write; after a normal-mode failure, only the next explicit invocation creates a fresh manifest/interview identity. After an exact --quick delegation failure, the next explicit invocation reruns discovery, records a fresh phaseSkillLoad and interview identity, and does not reuse a terminal bypassed_quick interview or its discovery revision. Only a matching in-progress collecting or awaiting_confirmation interview is resumable. Exact --quick retains its existing question-and-approval bypass and discovery, manifest, delegation, and writer checks.
  10. Read-only exploration children may inspect seams, constraints, and existing boundaries, but they write no epic artifact.
  11. Keep the existing epic-state, read-only exploration, and multiwriter flow, plus each child packet, identity tuple, and receipt behavior, unchanged. Use separate unique gated writer dispatches as needed:
Show full SKILL.md (300 more words)Show less
  • a triage research writer for research.md
  • a triage plan writer for epic.md and generated spec plan.md files
  • a fresh revision writer for every artifact-review revision Pass the absolute gate helper path, epic state path, identity tuple, unique teammate dispatch identity, and verbatim phaseSkillLoad manifest to each writer. Each writer records its manifest loads and passes check-agent-write with its unique identity before its first filesystem artifact write.
  1. The coordinator does not assemble, format, or revise artifact content. Validate the gated writer outputs and persist .epic-state.json with each spec, its status, dependencies, and gate receipts.
  2. Keep specs/.current-epic set to the active epic name.
  3. Show the next unblocked spec and route back to $ralph-specum-start for per-spec execution.

Output Shape

The result should make it clear:

  • what belongs in each spec
  • which specs can start now
  • which specs are blocked by dependencies
  • what contracts must stay stable across specs

Stop Behavior

  • Without --quick: STOP HERE. Display the epic summary and approval prompt. Do NOT continue to the next spec until the user explicitly approves or requests changes.
  • With exact --quick: Record the quick bypass and continue directly to the first unblocked spec.

Response Handoff

  • After writing epic.md, name epic.md and summarize the epic plan briefly.
  • When normalized quickMode is false, end with exactly one explicit choice prompt:
    • approve current artifact
    • request changes
    • continue to the next spec
  • Treat continue to the next spec as approval of epic.md.
  • With exact --quick, do not show this prompt; continue directly to the first unblocked spec after the gates succeed.
  • During artifact review, apply the changes immediately delegates already-recorded feedback through a fresh unique gated revision writer, redisplays the artifacts, and stays at this approval gate. Ask one focused change question only when no feedback is pending. Control-only continue, proceed, and go ahead approve nothing.

© tzachbon, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in plugins/ralph-specum-codex/skills/ralph-specum-triage of tzachbon/smart-ralph.

  • SKILL.md
  • agents/openai.yaml

Open the folder on GitHubat commit ac7251a

Compare with similar skills

Ralph Specum Triage next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Ralph Specum Triage compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Ralph Specum Triage this skilltzachbon/smart-ralph559—~1.7kAutomated safety check: PassMIT
Triaging Issuespytorch/pytorch104k—~4.2kAutomated safety check: PassCustom licence
Issue Triagepaperclipai/paperclip100k—~1kAutomated safety check: PassMIT
Triagepnpm/pnpm37k—~2.9kAutomated safety check: PassMIT
Herdr Issue Triageherdrdev/herdr43k—~517Automated safety check: PassApache-2.0
RalphYeachan-Heo/oh-my-claudecode40k—~7.5kAutomated safety check: PassMIT

Similar skills

  • Triaging Issues

    pytorch/pytorch

    Triages GitHub issues by routing to oncall teams, applying labels, and closing questions.

    104k GitHub stars~4.2k tokensUpdated today
    AI & LLM EngineeringAuto-check passed
  • Issue Triage

    paperclipai/paperclip

    Triage Paperclip inbox issues that are stale, blocked, in-review, or assigned-but-not-progressing, and decide a single next action per issue (resume, reassign, unblock, escalate, or close).

    100k GitHub stars~1k tokensUpdated today
    DevelopmentAuto-check passed
  • Triage

    pnpm/pnpm

    Triage an incoming GitHub issue against the pnpm codebase and related open issues, then apply exactly one implementation-readiness label using pnpm's state: taxonomy.

    37k GitHub stars~2.9k tokensUpdated today
    DevelopmentAuto-check passed
  • Herdr Issue Triage

    herdrdev/herdr

    Triages open herdr GitHub issues into a short decision-first Markdown table with a priority light, recommendation, age, reactions and a reason for each.

    43k GitHub stars~517 tokensUpdated 2 days ago
    DevelopmentAuto-check passed
  • Ralph

    Yeachan-Heo/oh-my-claudecode

    Self-referential loop until task completion with configurable verification reviewer

    40k GitHub stars~7.5k tokensUpdated 3 days ago
    Product & Project ManagementAuto-check passed
  • Runs issue triage and PR triage in parallel, then cross-analyzes the results to flag duplicate coverage, security gaps, P0 issues with no PR, and PR conflicts.

    83k GitHub stars~1.6k tokensUpdated yesterday
    DevelopmentAuto-check: notes

More from tzachbon/smart-ralph

All 26 skills in this repo
  • Communication Style

    tzachbon/smart-ralph

    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…

    559 GitHub stars~551 tokensUpdated 24 days ago
    Auto-check passed
  • Interview Framework

    tzachbon/smart-ralph

    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…

    559 GitHub stars~2.2k tokensUpdated 24 days ago
    Auto-check passed
  • Reality Verification

    tzachbon/smart-ralph

    This skill should be used when the user asks to "verify a fix", "reproduce failure", "diagnose issue", "check BEFORE/AFTER state", "VF task", "reality check", "check test quality", "mock-only…

    559 GitHub stars~877 tokensUpdated 24 days ago
    Auto-check passed
  • Spec Workflow

    tzachbon/smart-ralph

    This skill should be used when the user asks to "build a feature", "create a spec", "start spec-driven development", "run research phase", "generate requirements", "create design", "plan tasks"…

    559 GitHub stars~1.1k tokensUpdated 24 days ago
    Auto-check passed
  • Ralph Specum Design

    tzachbon/smart-ralph

    This skill should be used only when the user explicitly asks to use $ralph-specum-design, or explicitly asks Ralph Specum in Codex to run the design phase.

    559 GitHub stars~1.5k tokensUpdated 24 days ago
    Auto-check passed
  • Ralph Specum Tasks

    tzachbon/smart-ralph

    This skill should be used only when the user explicitly asks to use $ralph-specum-tasks, or explicitly asks Ralph Specum in Codex to run the tasks phase.

    559 GitHub stars~1.6k tokensUpdated 24 days ago
    Auto-check passed

Questions about Ralph Specum Triage

What does Ralph Specum Triage do?

This skill should be used only when the user explicitly asks to use $ralph-specum-triage, or explicitly asks Ralph Specum in Codex to triage a large effort into multiple specs. Ralph Specum Triage is an agent skill from tzachbon/smart-ralph. This skill should be used only when the user explicitly asks to use $ralph-specum-triage, or explicitly asks Ralph Specum in Codex to triage a large effort into multiple specs.

When should I use Ralph Specum Triage?

Ralph Specum Triage fits situations like: explicitly asks to use $ralph-specum-triage; explicitly asks Ralph Specum in Codex to triage a large effort into multiple specs.

How do I install Ralph Specum Triage in Claude Code?

Run `npx skills add tzachbon/smart-ralph --skill ralph-specum-triage -a claude-code`. Or copy the skill folder (plugins/ralph-specum-codex/skills/ralph-specum-triage in tzachbon/smart-ralph) into .claude/skills/ralph-specum-triage in your project. Claude Code loads it when a task matches its description.

How do I install Ralph Specum Triage in Codex?

Run `npx skills add tzachbon/smart-ralph --skill ralph-specum-triage -a codex`. Or copy the skill folder (plugins/ralph-specum-codex/skills/ralph-specum-triage in tzachbon/smart-ralph) into .agents/skills/ralph-specum-triage in your project. Codex loads it when a task matches its description.

Can I use Ralph Specum Triage in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add tzachbon/smart-ralph --skill ralph-specum-triage -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ralph-specum-triage, .gemini/skills/ralph-specum-triage, .github/skills/ralph-specum-triage and .opencode/skills/ralph-specum-triage in your project.

What does Ralph Specum Triage need to run?

Going by SKILL.md and its folder, Ralph Specum Triage needs the command-line tools its instructions call (jq and go).

Does Ralph Specum Triage access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Ralph Specum Triage safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Ralph Specum Triage use?

Ralph Specum Triage is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Ralph Specum Triage use?

About 1.7k tokens (SKILL.md is roughly 6.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Ralph Specum Triage?

Skills that share tags, products or a category with Ralph Specum Triage: Triaging Issues (pytorch/pytorch, 104k stars), Issue Triage (paperclipai/paperclip, 100k stars), Triage (pnpm/pnpm, 37k stars) and Herdr Issue Triage (herdrdev/herdr, 43k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Ralph Specum Triage?

tzachbon (a GitHub user) maintains it in tzachbon/smart-ralph, which has 559 GitHub stars. The repository holds 26 skills in this directory. The repository was last updated on September 16, 2026.

Source: tzachbon/smart-ralph on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.