ralph-wiggum
Optional iterative polish loop. Repeats a task to refine output when quality > speed. OFF by default. Commands: "ralph on", "ralph off", "ralph once", "ralph max 3". Complements caveman skills.
- License 许可
- Unlicense
- 最近更新
- 2026-11-02
- Stars
- ★ 0
- Forks
- 0
01 前言 Front Matter
- name
- ralph-wiggum
- description
- Optional iterative polish loop. Repeats a task to refine output when quality > speed. OFF by default. Commands: "ralph on", "ralph off", "ralph once", "ralph max 3". Complements caveman skills.
03 SKILL.md 正文
Ralph Wiggum Loop — Optional Iterative Improvement
"Why use many token when few token do trick — but what if few token not quite right?"
WHAT THIS SKILL DOES
Repeats a task with fresh context each pass, improving the output until quality is met. OFF by default. Engage ONLY when the user explicitly asks.
WHEN TO USE
TURN ON ("ralph on")
- User has time and token budget for polish
- Quality critical: final thesis chapter, journal submission
- Complex multi-step document assembly
- "I have time, I need this polished"
KEEP OFF (default)
- Deadline tight, tokens scarce
- Quick draft or summary is enough
- Casual internal notes
- "I want it fast, I don't have tokens to spare" ← leave OFF, do one pass
ONE-SHOT ("ralph once")
- Run one verification pass after the initial output
- Safety net without full looping cost
- "Double-check my output once, then stop"
COMMANDS
| Command | Effect | Token cost |
|---|---|---|
ralph off |
One pass. Speed priority. Default. | None |
ralph once |
One verification pass after output. | ~2x output |
ralph on |
Loop until quality met or user stops. | Variable |
ralph max 3 |
Maximum 3 iterations, then stop. | ~3x output |
ralph status |
Show iteration count + estimated tokens used. | Small |
THE LOOP
[User prompt]
↓
[Pass 1: produce output]
↓
[Save output to file/history]
↓
[Pass 2: review pass 1 — what's weak? what broke?]
↓
[Improve → output v2]
↓
[Repeat until quality met, max loops reached, or user says stop]
- Each pass starts fresh (no accumulated context wall)
- Progress lives in files/git between passes
- Re-check facts, numbers, citations EVERY pass — never assume previous pass was right
INTEGRATION WITH GRUG/CAVEMAN
Ralph complements the caveman-be-brief skill:
- caveman-be-brief produces tight professional output (pass 1)
- ralph on loops: each pass re-runs SNIFF → FEAR → PLAN → ACT → SPEAK on the previous output
- Fear step each pass: "what still wrong? what break? what fact unchecked?"
- When quality met → user says "ralph off" / "done" → final output kept
EXAMPLES
Thesis abstract refinement (ralph on)
User: "ralph on — compress this thesis abstract for submission"
[Pass 1] → "Methodology: n=150 participants... Results: significant correlation..."
[Pass 2] → "Methodology (2024): n=150. Survey + interview. Results: X correlates Y (p<0.05)."
[Pass 3] → "Mixed-methods study (2024). Survey (n=150) + interviews (n=15).
Key finding: X predicts Y (β=0.42, p<0.01). Mediated by Z."
[User: "Good. ralph off."]
[Done, pass 3 kept.]
One-shot verification (ralph once)
User: "ralph once — review this email before I send it"
[Pass 1] → "L3: 🔴 typo: 'recieve' → 'receive'. L7: 🟡 risk: deadline missing timezone."
[Pass 2 (verification)] → "L3 fix confirmed. L7: Add 'EOD PST'. No new issues."
[Done, two passes complete.]
GUARDRAILS
- NEVER loop without user request — default is ONE pass
- Respect
ralph max N— never exceed it (token burn protection) - If user says "stop", "done", "that's enough", or "ralph off" mid-loop → stop immediately, keep last output
- If output quality stops improving between passes → stop early, report best version
- Each pass must VERIFY facts/numbers/citations, not just rephrase
WHY SEPARATE SKILL?
Keeping Ralph as its own skill means you control it independently:
- Low on time/tokens? Leave this skill OFF (or toggle off). caveman-be-brief still runs one-pass fast.
- Have time to polish? Toggle ON or just say "ralph on" — Claude loads this skill and loops.
No coupling. No forced token burn. Speed when you need it, polish when you want it.
OFF by default. ON only when quality matters.
04 同仓库更多 Skills
web-app-penetration-testing
Pentest a web app or website end to end — black-box testing of a live URL, staging environment, or local dev server that finds and exploits real vulnerabilities (auth bypass, broken access control, IDOR, injection, XSS, SSRF, business logic) and proves each one with a working proof-of-concept instead of a signature match. Runs with Strix, either the self-hosted open-source CLI or the managed app.strix.ai cloud. Use when the user asks to pentest, hack, security-test, or audit their web app, website, web application, or staging site.
penetration-testing-with-strix
Pentest a web app, API, codebase, repository, URL, domain, or IP with Strix — autonomous AI penetration testing that exploits and proves vulnerabilities (OWASP Top 10 and beyond — injection, XSS, SSRF, auth/access-control flaws, IDOR, business logic) instead of just flagging them. Runs self-hosted with the open-source CLI or via the managed app.strix.ai cloud, and returns validated findings with proof-of-concept exploits (Markdown, JSON, CSV, SARIF). Use when the user asks to pentest, hack, security-scan, security-audit, or find vulnerabilities in an app, API, website, or repo.
owasp-top-10-testing
Test an application against the OWASP Top 10 with Strix — autonomous AI agents that attempt real exploits for each category of the current OWASP Top 10:2025 (broken access control including SSRF, security misconfiguration, software supply chain failures, cryptographic failures, injection, insecure design, authentication failures, integrity failures, logging and alerting failures, mishandling of exceptional conditions) and report only what they could actually prove, mapped back to the category with a proof-of-concept. Also covers the OWASP API Security Top 10 (2023). Use when the user asks for an OWASP Top 10 assessment, OWASP compliance testing, or a security review mapped to OWASP categories.
managed-pentesting-with-strix
Run a managed pentest of a web app, API, repository, or local workspace on the app.strix.ai platform with the `strix cloud` CLI or REST API — no local Docker or LLM key needed. Safely review and upload local source, register assets, launch and poll scans, triage vulnerabilities, export SARIF, download compliance reports, start PR reviews, buy credits, and set up schedules or webhooks. Use for managed, continuous, scheduled, team-tracked, or sandboxed-agent security testing.
fix-security-vulnerabilities-with-strix
Fix security vulnerabilities found by a Strix pentest (open-source CLI or app.strix.ai cloud) — triage by severity, patch the root cause rather than the symptom, and re-run Strix to prove each fix actually closes the exploit. Handles injection, XSS, SSRF, broken access control, IDOR, and other validated findings. Use after a Strix scan reports findings, or when the user asks to remediate, patch, or fix security issues from a strix_runs report, vulnerabilities.json, findings.sarif, or a cloud scan.
find-security-vulnerabilities-in-code
Find security vulnerabilities in a codebase or repository with Strix — a white-box AI security review that reads your source, reasons about the actual data flow and authorization model, then exploits what it finds in a live sandbox so every reported issue has a working proof-of-concept instead of a noisy static-analysis alert. Covers injection, XSS, SSRF, broken access control and IDOR, insecure deserialization, secrets in code, unsafe dependencies, and business-logic flaws. Use when the user asks to security-scan, security-review, or audit their code, repo, or pull request for vulnerabilities.