Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Full reference guide for Ouroboros commands and agents
.claude/skills/q00-ouroboros-help/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-03 | ✗→✓ | ▲ Improved | 16% | 0% |
| case-01 | ✗→✓ | ▲ Improved | 17% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 80% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 21% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 39% | 0% |
Full reference guide for Ouroboros power users.
ooo help
/ouroboros:ouroboros-helpOuroboros is a requirement crystallization engine for AI workflows. It transforms vague ideas into validated specifications through:
| Command | Purpose | Mode | |---------|---------|------| | ooo | Welcome + quick start | Plugin | | ooo interview | Socratic requirement clarification | Plugin | | ooo seed | Generate validated seed spec | Plugin | | ooo run | Execute seed workflow | MCP | | ooo evaluate | 3-stage verification | MCP | | ooo unstuck | 5 lateral thinking personas | Plugin | | ooo status | Session status + drift check | MCP | | ooo resume-session | List in-flight sessions and re-attach commands | CLI | | ooo setup | Installation wizard | Plugin | | ooo welcome | First-touch welcome guide | Plugin | | ooo tutorial | Interactive hands-on learning | Plugin | | ooo help | This reference guide | Plugin | | ooo pm | PM-focused interview + PRD generation | MCP | | ooo qa | General-purpose QA verdict for any artifact | Plugin | | ooo cancel | Cancel stuck or orphaned executions | CLI | | ooo update | Check for updates + upgrade to latest | Plugin | | ooo brownfield | Scan and manage brownfield repo defaults | MCP | | ooo publish | Publish Seed as GitHub Issues for teams | Plugin |
| Command | Purpose | Mode | |---------|---------|------| | ooo evolve | Start/monitor evolutionary development loop | MCP | | ooo ralph | Client-driven loop until verified (uses background evolve_step jobs) | Plugin + MCP |
Plugin = Works immediately after ooo setup. MCP = Requires ooo setup (Python >= 3.12 auto-detected). Run setup once to unlock all features.
| Phrase | Triggers | |--------|----------| | "interview me", "clarify requirements", "socratic interview" | ooo interview | | "crystallize", "generate seed", "create seed", "freeze requirements" | ooo seed | | "ouroboros run", "execute seed", "run seed", "run workflow" | ooo run | | "evaluate this", "3-stage check", "verify execution" | ooo evaluate | | "think sideways", "i'm stuck", "break through", "lateral thinking" | ooo unstuck | | "am I drifting?", "drift check", "session status" | ooo status |
| Phrase | Triggers | |--------|----------| | "write prd", "pm interview", "product requirements", "create prd" | ooo pm | | "qa check", "quality check" | ooo qa | | "cancel execution", "stop job", "kill stuck", "abort execution" | ooo cancel | | "in-flight sessions", "mcp disconnected", "lost Ouroboros execution" | ooo resume-session | | "update ouroboros", "upgrade ouroboros" | ooo update | | "brownfield defaults", "brownfield scan" | ooo brownfield | | "publish to github", "create issues from seed", "seed to issues" | ooo publish |
| Phrase | Triggers | |--------|----------| | "ralph", "don't stop", "must complete", "until it works", "keep going" | ooo ralph | | "evolve", "evolutionary loop", "iterate until converged" | ooo evolve |
| Skill | Purpose | Mode | |-------|---------|------| | /ouroboros:welcome | First-touch welcome experience | Plugin | | /ouroboros:interview | Socratic requirement clarification | Plugin | | /ouroboros:seed | Generate validated seed spec | Plugin | | /ouroboros:ouroboros-run | Execute seed workflow | MCP | | /ouroboros:evaluate | 3-stage verification | MCP | | /ouroboros:unstuck | 5 lateral thinking personas | Plugin | | /ouroboros:ouroboros-status | Session status + drift check | MCP | | /ouroboros:resume-session | List in-flight sessions and re-attach commands | CLI | | /ouroboros:setup | Installation wizard | Plugin | | /ouroboros:tutorial | Interactive hands-on learning | Plugin | | /ouroboros:ouroboros-config | Settings GUI | Plugin | | /ouroboros:ouroboros-help | This guide | Plugin | | /ouroboros:pm | PM-focused interview + PRD generation | MCP | | /ouroboros:qa | General-purpose QA verdict for any artifact | Plugin | | /ouroboros:cancel | Cancel stuck or orphaned executions | CLI | | /ouroboros:update | Check for updates + upgrade to latest | Plugin | | /ouroboros:brownfield | Scan and manage brownfield repo defaults | MCP | | /ouroboros:publish | Publish Seed as GitHub Issues for teams | Plugin |
| Skill | Purpose | Best For | |-------|---------|----------| | /ouroboros:ralph | Client-driven loop over background evolve_step jobs | "Don't stop", must complete | | /ouroboros:evolve | Evolutionary ontology refinement | Spec iteration until convergence |
| Agent | Purpose | |-------|---------| | ouroboros:socratic-interviewer | Exposes hidden assumptions through questioning | | ouroboros:ontologist | Finds root problems vs symptoms | | ouroboros:seed-architect | Crystallizes requirements into seed specs | | ouroboros:evaluator | Three-stage verification | | ouroboros:contrarian | "Are we solving the wrong problem?" | | ouroboros:hacker | "Make it work first, elegance later" | | ouroboros:simplifier | "Cut scope to absolute minimum" | | ouroboros:researcher | "Stop coding, start investigating" | | ouroboros:architect | "Question the foundation, redesign if needed" |
After installing Ouroboros, run ooo setup once to register the MCP server. This connects your runtime backend to the Ouroboros Python core and unlocks all features.
ooo setup # One-time setup (~1 minute)| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-03 | fail→pass | 15,607 | 8,296 | -47% | 1 | 1 | 0% | 2,876 | 3,327 | +16% | 0 | 0 | — |
case-01 | fail→pass | 20,076 | 19,014 | -5% | 1 | 1 | 0% | 2,826 | 3,300 | +17% | 0 | 0 | — |
case-02 | fail→pass | 13,152 | 8,380 | -36% | 1 | 1 | 0% | 1,873 | 3,369 | +80% | 0 | 0 | — |
case-04 | pass→pass | 10,521 | 5,422 | -48% | 1 | 1 | 0% | 1,621 | 2,448 | +51% | 0 | 0 | — |
case-05 | pass→pass | 12,444 | 15,381 | +24% | 1 | 1 | 0% | 2,366 | 3,913 | +65% | 0 | 0 | — |
case-06 | pass→pass | 9,586 | 8,920 | -7% | 1 | 1 | 0% | 1,801 | 3,043 | +69% | 0 | 0 | — |
case-07 | fail→pass | 9,621 | 3,374 | -65% | 1 | 1 | 0% | 1,692 | 2,044 | +21% | 0 | 0 | — |
case-08 | fail→pass | 10,418 | 2,069 | -80% | 1 | 1 | 0% | 1,430 | 1,988 | +39% | 0 | 0 | — |
case-09 | fail→pass | 26,415 | 3,335 | -87% | 1 | 1 | 0% | 1,404 | 2,067 | +47% | 0 | 0 | — |
case-10 | fail→pass | 13,788 | 2,289 | -83% | 1 | 1 | 0% | 1,824 | 1,998 | +10% | 0 | 0 | — |
case-11 | fail→pass | 11,988 | 2,476 | -79% | 1 | 1 | 0% | 1,676 | 2,009 | +20% | 0 | 0 | — |
case-12 | fail→pass | 10,372 | 2,466 | -76% | 1 | 1 | 0% | 1,712 | 2,078 | +21% | 0 | 0 | — |
case-13 | pass→pass | 16,565 | 3,335 | -80% | 1 | 1 | 0% | 2,198 | 2,223 | +1% | 0 | 0 | — |
case-14 | pass→pass | 15,932 | 3,588 | -77% | 1 | 1 | 0% | 2,645 | 2,102 | -21% | 0 | 0 | — |
case-15 | pass→pass | 10,074 | 2,343 | -77% | 1 | 1 | 0% | 1,464 | 2,054 | +40% | 0 | 0 | — |
case-16 | pass→pass | 11,151 | 2,956 | -73% | 1 | 1 | 0% | 1,887 | 1,990 | +5% | 0 | 0 | — |
case-17 | fail→pass | 7,744 | 2,159 | -72% | 1 | 1 | 0% | 1,469 | 1,937 | +32% | 0 | 0 | — |
case-18 | fail→pass | 13,819 | 1,825 | -87% | 1 | 1 | 0% | 2,240 | 1,942 | -13% | 0 | 0 | — |
case-19 | fail→pass | 14,969 | 5,301 | -65% | 1 | 1 | 0% | 2,287 | 2,335 | +2% | 0 | 0 | — |
case-20 | fail→pass | 12,347 | 2,138 | -83% | 1 | 1 | 0% | 1,749 | 1,985 | +13% | 0 | 0 | — |
case-21 | pass→pass | 15,786 | 2,853 | -82% | 1 | 1 | 0% | 2,035 | 2,103 | +3% | 0 | 0 | — |
case-22 | fail→pass | 38,822 | 1,845 | -95% | 1 | 1 | 0% | 6,986 | 1,861 | -73% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted. The headline lift of +64 percentage points is the difference between those two pass rates over the 22 comparable cases.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.