#232 by GitHub stars
Q00/ouroboros
Agent OS: the agent gets smarter on its own. We just hold the line: Interview-gated, staged evaluation, budgeted evolution loop. MCP server, 14 runtimes: Claude Code, Codex CLI, Gemini CLI, OpenCode, Copilot, Kiro and more.
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
skills/auto/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
125327a54970 → 722172ef0967
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 125327a54970
No earlier version was observed for comparison.
skills/brownfield/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
125327a54970 → 722172ef0967
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 125327a54970
No earlier version was observed for comparison.
skills/cancel/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
125327a54970 → 722172ef0967
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 125327a54970
No earlier version was observed for comparison.
skills/config/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
125327a54970 → 722172ef0967
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 125327a54970
No earlier version was observed for comparison.
skills/evaluate/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
125327a54970 → 722172ef0967
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 125327a54970
No earlier version was observed for comparison.
skills/evolve/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
125327a54970 → 722172ef0967
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 125327a54970
No earlier version was observed for comparison.
skills/help/SKILL.md
Week of Nov 2, 2026 · +2 / −0 lines
Before Network or broad shell → After Network or broad shell
125327a54970 → 722172ef0967
+ 40 | `ooo idk` | Calibrate interview wording from stated familiarity | MCP, in-session fallback |
+ 70 | "I don't know this term", "explain at my level" | `ooo idk` |
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 125327a54970
No earlier version was observed for comparison.
skills/idk/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 722172ef0967
No earlier version was observed for comparison.
skills/interview/SKILL.md
Week of Nov 2, 2026 · +28 / −0 lines
Before Network or broad shell → After Network or broad shell
125327a54970 → 722172ef0967
+ 52 ### Interview language calibration
+ 53
+ 54 Before asking or relaying the first question, look in the current conversation
+ 55 for the most recent `Interview calibration` produced by `ooo idk`. If present,
+ 56 apply it to all user-facing interview prose:
+ 57
+ 58 - **Foundational**: use plain language, define necessary terms before using
+ 59 them, and add one neutral concrete example when it helps.
+ 60 - **Working**: use standard terminology and briefly define only new or
+ 61 overloaded terms; frame questions around practical trade-offs.
+ 62 - **Fluent**: use precise domain terminology and concise trade-off language.
+ 63
+ 64 Use one overall explanation level plus explicitly unknown terms. Do not infer
+ 65 low general ability from an unknown English term, typo, or terse answer. Adapt
+ 66 vocabulary, sentence structure, context, and example depth only; preserve the
+ 67 original question's decision, constraints, acceptance
+ 68 meaning, and all interview gates.
+ 69 If the previous `ooo idk` or `ooo interview` response included
+ 70 `meta.interview_calibration`, pass it to the next `ouroboros_interview` MCP call
+ 71 as the `interview_calibration` argument.
+ 72
+ 73 If the user says they do not know a word or invokes `ooo idk` while a question
+ 74 is pending, do not forward that statement to MCP as the answer. Explain the term
+ 75 at the calibrated level, update the provisional calibration when warranted,
+ 76 rephrase the same question without steering the decision, and wait for the
+ 77 user's actual answer. The active calibration lives only in the current
+ 78 conversation unless the user supplies it again.
+ 79
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 125327a54970
No earlier version was observed for comparison.
skills/ooo/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
125327a54970 → 722172ef0967
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 125327a54970
No earlier version was observed for comparison.
skills/pm/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
125327a54970 → 722172ef0967
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 125327a54970
No earlier version was observed for comparison.
skills/publish/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
125327a54970 → 722172ef0967
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 125327a54970
No earlier version was observed for comparison.
skills/qa/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
125327a54970 → 722172ef0967
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 125327a54970
No earlier version was observed for comparison.
skills/ralph/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
125327a54970 → 722172ef0967
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 125327a54970
No earlier version was observed for comparison.
skills/resume-session/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
125327a54970 → 722172ef0967
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 125327a54970
No earlier version was observed for comparison.
skills/run/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
125327a54970 → 722172ef0967
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 125327a54970
No earlier version was observed for comparison.
skills/seed/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
125327a54970 → 722172ef0967
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 125327a54970
No earlier version was observed for comparison.
skills/setup/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
125327a54970 → 722172ef0967
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 125327a54970
No earlier version was observed for comparison.
skills/status/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
125327a54970 → 722172ef0967
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 125327a54970
No earlier version was observed for comparison.
skills/tutorial/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
125327a54970 → 722172ef0967
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 125327a54970
No earlier version was observed for comparison.
skills/unstuck/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
125327a54970 → 722172ef0967
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 125327a54970
No earlier version was observed for comparison.
skills/update/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
125327a54970 → 722172ef0967
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 125327a54970
No earlier version was observed for comparison.
skills/welcome/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
125327a54970 → 722172ef0967
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 125327a54970
No earlier version was observed for comparison.
tests/fixtures/router/skills/frontmatter-body/run/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
125327a54970 → 722172ef0967
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 125327a54970
No earlier version was observed for comparison.
Verified commit 722172ef096767583679d04aef5e847458fee6b2
git clone --filter=blob:none --no-checkout https://github.com/Q00/ouroboros.git .hotskills/q00-ouroboros && git -C .hotskills/q00-ouroboros checkout --detach 722172ef096767583679d04aef5e847458fee6b2
# Copy each selected skill directory from .hotskills/q00-ouroboros into .claude/skills/<skill-name>/git clone --filter=blob:none --no-checkout https://github.com/Q00/ouroboros.git .hotskills/q00-ouroboros && git -C .hotskills/q00-ouroboros checkout --detach 722172ef096767583679d04aef5e847458fee6b2
# Copy each selected skill directory from .hotskills/q00-ouroboros into .agents/skills/<skill-name>/Heat
6.6- Star growth, last 7 daysAhead of 75% of tracked repositories
- Star growth, last 24 hoursAhead of 69% of tracked repositories
- Rank movement, last 7 daysAhead of 67% of tracked repositories
- Commits, last 30 daysAhead of 96% of tracked repositories
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekAhead of 0% of tracked repositories
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
Individual skills in this repository
- auto
skills/auto - brownfield
skills/brownfield - cancel
skills/cancel - ouroboros-config
skills/config - evaluate
skills/evaluate - evolve
skills/evolve - ouroboros-help
skills/help - idk
skills/idk - interview
skills/interview - ooo
skills/ooo - pm
skills/pm - publish
skills/publish - qa
skills/qa - ralph
skills/ralph - resume-session
skills/resume-session - ouroboros-run
skills/run - seed
skills/seed - setup
skills/setup - ouroboros-status
skills/status - tutorial
skills/tutorial - unstuck
skills/unstuck - update
skills/update - welcome
skills/welcome - run
tests/fixtures/router/skills/frontmatter-body/run
How it works
auto
When your agent uses it
Use when the work spans several files or replaces a framework, language, auth, storage, or API layer (rewrites and migrations included), and the user wants it to end up working and tested. Asks only what is missing, writes a spec with acceptance criteria, then runs and verifies it in the background. Not for questions, small edits, or an existing Seed (use run).
What it loads into context
Frontmatter
188 tokensAlways available to the agent
SKILL.md
3,206 tokensWhen the skill is activated
Reference documents
45,141 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Dispatch requirement
- Usage
- CLI flag → MCP arg translation
- Behavior
- Background monitoring
- Synapse intent refinement
- Active Conductor decision policy
- RFC #1392 State Breadcrumb Footer
Scripts executed separately
../../scripts/drift-monitor.py../../scripts/keyword-detector.py../../scripts/session-start.py
Files
../../.claude-plugin/.mcp.jsonasset357 bytes../../.claude-plugin/SKILL_CAPABILITY_GUIDE.mddoc2,522 bytes../../.claude-plugin/marketplace.jsonasset2,080 bytes../../.claude-plugin/plugin.jsonasset1,121 bytes../../.codex/hooks.jsonasset1,525 bytes../../.mcp.jsonasset349 bytes../../hooks/hooks.jsonasset7,151 bytes../../scripts/drift-monitor.pyruns2,126 bytes../../scripts/keyword-detector.pyruns14,748 bytes../../scripts/session-start.pyruns1,552 bytesSKILL.mdcore13,633 bytesSKILL.mdcore13,633 bytes../brownfield/SKILL.mddoc7,325 bytes../cancel/SKILL.mddoc4,637 bytes../config/SKILL.mddoc3,524 bytes../evaluate/SKILL.mddoc6,934 bytes../evolve/SKILL.mddoc4,922 bytes../help/SKILL.mddoc5,116 bytes../idk/SKILL.mddoc5,198 bytes../interview/SKILL.mddoc24,087 bytes../ooo/SKILL.mddoc853 bytes../pm/SKILL.mddoc12,560 bytes../publish/SKILL.mddoc5,818 bytes../qa/SKILL.mddoc6,166 bytes../ralph/SKILL.mddoc8,987 bytes../resume-session/SKILL.mddoc2,175 bytes../run/SKILL.mddoc14,352 bytes../seed/SKILL.mddoc14,727 bytes../setup/SKILL.mddoc14,703 bytes../status/SKILL.mddoc2,449 bytes../tutorial/SKILL.mddoc2,961 bytes../unstuck/SKILL.mddoc9,379 bytes../update/SKILL.mddoc2,793 bytes../welcome/SKILL.mddoc25,150 bytes
Read SKILL.md
# /ouroboros:auto
Run the full-quality auto pipeline from a single task description.
## Dispatch requirement
This skill must be executed by invoking MCP tool `ouroboros_start_auto`. Do not
manually inspect repositories, run shell commands, query GitHub, edit files, or
otherwise emulate the auto pipeline. The background starter returns `job_id`
and `auto_session_id` quickly; retain both. If `ouroboros_start_auto` or a
required job wait/result tool is unavailable, stop and report that the required
MCP tool is unavailable. A manual fallback is not an `ooo auto` run.
If a started auto job returns `detached`, `blocked`, `failed`, or anotherView the complete source on GitHubbrownfield
When your agent uses it
Scan and manage brownfield repository/worktree defaults for interviews
What it loads into context
Frontmatter
20 tokensAlways available to the agent
SKILL.md
1,786 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Loading MCP tools (deferred-schema guard)
- Default flow (`ooo brownfield`)
- Subcommands
- RFC #1392 State Breadcrumb Footer
Files
SKILL.mdcore7,325 bytesSKILL.mdcore7,325 bytes
Read SKILL.md
# /ouroboros:brownfield
Manage the registry of existing git repositories and linked worktrees, and the default repos used as interview context. The registry lives in the Ouroboros DB: listing, defaults, and search read it and never walk the filesystem. Only `scan` walks the disk.
```
ooo brownfield # List registered repos and set defaults (scans only if none are registered)
ooo brownfield scan # Rescan the scan root and refresh the search index
ooo brownfield defaults # Show current defaults
ooo brownfield find <topic> # Rank registered repos by relevance to a topic
ooo brownfield set 6,18,19 # Set defaults by repo numbers
ooo brownfield detect [path] # Author mechanical.toml via one AI call
```
## Loading MCP tools (deferred-schema guard)View the complete source on GitHubcancel
When your agent uses it
Cancel stuck or orphaned executions
What it loads into context
Frontmatter
21 tokensAlways available to the agent
SKILL.md
1,078 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Instructions
- Fallback (no MCP server)
- RFC #1392 State Breadcrumb Footer
Files
SKILL.mdcore4,637 bytes
Read SKILL.md
# /ouroboros:cancel
Cancel stuck or orphaned executions and background jobs through the Ouroboros MCP tools, which work on hosts without shell access.
```
/ouroboros:cancel # list this project's active executions, ask which to cancel
/ouroboros:cancel <id> # cancel one execution (orch_... or execution id) or job (job_...)
/ouroboros:cancel --all # cancel every running or paused execution of this project
```
## Instructions
### Loading MCP tools (deferred-schema guard)
View the complete source on GitHubouroboros-config
When your agent uses it
Open or drive the Ouroboros settings GUI (browser, TUI, or conversational fallback)
What it loads into context
Frontmatter
29 tokensAlways available to the agent
SKILL.md
855 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Instructions
- RFC #1392 State Breadcrumb Footer
Files
SKILL.mdcore3,524 bytesSKILL.mdcore3,524 bytesSKILL.mdcore3,524 bytesSKILL.mdcore3,524 bytesSKILL.mdcore3,524 bytes
Read SKILL.md
# /ouroboros:ouroboros-config
Edit `~/.ouroboros/config.yaml`: global and per-stage runtime and model choices, the LLM backend, install badges for missing CLIs, and env-override warnings.
```
ooo config
/ouroboros:ouroboros-config
```
## Instructions
Pick the branch by one question: **can the user open a browser pointed at this machine?** Run commands with the active runtime's `run_shell` capability.
### Branch A: local harness on the user's own machineView the complete source on GitHubevaluate
When your agent uses it
Use when the user wants proof that finished work meets its acceptance criteria, not just that tests pass: 'verify it is actually done', 'check it against the spec', 'evaluate the run'. Runs mechanical checks, a semantic review per criterion, and multi-model consensus when uncertain. With execution.auto_evolve on (the default), a rejected result with a Seed continues into a Ralph fix loop; pass auto_evolve: false to verify only.
What it loads into context
Frontmatter
101 tokensAlways available to the agent
SKILL.md
1,598 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Stage authority
- Instructions
- RFC #1392 State Breadcrumb Footer
Files
SKILL.mdcore6,934 bytesSKILL.mdcore6,934 bytesSKILL.mdcore6,934 bytesSKILL.mdcore6,934 bytesSKILL.mdcore6,934 bytes
Read SKILL.md
# /ouroboros:evaluate
Evaluate an execution session with the three-stage verification pipeline.
```
/ouroboros:evaluate <session_id> [artifact]
```
## Stage authority
1. **Mechanical** (lint, build, test, static analysis, coverage; no model cost): the only stage that can grant approval. At least one configured check must run and all must pass.
2. **Semantic** (AC compliance, goal alignment, drift): advisory. Can withhold approval and give feedback; cannot grant it.
3. **Consensus** (multi-model, only on uncertainty or request): advisory. A rejection withholds approval; an approval cannot grant it or lift a Stage 2 block.
View the complete source on GitHubevolve
When your agent uses it
Start or monitor an evolutionary development loop
What it loads into context
Frontmatter
15 tokensAlways available to the agent
SKILL.md
1,178 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Usage
- Instructions
- RFC #1392 State Breadcrumb Footer
Files
SKILL.mdcore4,922 bytes
Read SKILL.md
# ooo evolve - Evolutionary Loop
Start, monitor, or rewind an evolutionary loop that refines the ontology and acceptance criteria across generations.
```
Gen 1: Seed → Execute(all ACs) → Judge → Gate
Gen 2+: Wonder(failed ACs) → Reflect(active ACs only) → Execute(active) → Gate(all)
...until the gate passes, the loop stagnates, or 30 generations are reached
```
## Usage
```
ooo evolve "build a task management CLI" # startView the complete source on GitHubouroboros-help
When your agent uses it
Full reference guide for Ouroboros commands and agents
What it loads into context
Frontmatter
21 tokensAlways available to the agent
SKILL.md
1,324 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Usage
- What Is Ouroboros?
- Commands
- Natural Language Triggers
- Agents
- RFC #1392 State Breadcrumb Footer
Files
SKILL.mdcore5,116 bytes
Read SKILL.md
# /ouroboros:ouroboros-help
Full reference guide for Ouroboros power users.
## Usage
```
ooo help
/ouroboros:ouroboros-help
```
## What Is Ouroboros?
A specification-first workflow engine: it turns vague ideas into a validatedView the complete source on GitHubidk
When your agent uses it
Calibrate interview explanations from the user's stated understanding
What it loads into context
Frontmatter
49 tokensAlways available to the agent
SKILL.md
1,119 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Usage
- Instructions
- Guardrails
- RFC #1392 State Breadcrumb Footer
Files
SKILL.mdcore5,198 bytes
Read SKILL.md
# /ouroboros:idk
Calibrate the language used by `ooo interview` without weakening the interview itself.
## Usage
```text
ooo idk <terms I do not know, or what I understand about them>
/ouroboros:idk <terms I do not know, or what I understand about them>
```
Examples:
```textView the complete source on GitHubinterview
When your agent uses it
Use when the user wants to build or change something but the request is vague or open-ended: 'help me figure out what to build', 'I'm not sure what it should do', 'add X' with no details, or no clear definition of done. Runs a short Socratic interview that turns the idea into goals, constraints, and acceptance criteria before any code is written. Not for simple questions, small clear edits, or an existing Seed.
What it loads into context
Frontmatter
132 tokensAlways available to the agent
SKILL.md
5,501 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Required Skill Capabilities
- Non-Skippable Gates
- Usage
- Path A: MCP Mode
- Path B: Fallback (No MCP Server)
- RFC #1392 State Breadcrumb Footer
Files
SKILL.mdcore24,087 bytesSKILL.mdcore24,087 bytesSKILL.mdcore24,087 bytesSKILL.mdcore24,087 bytes
Read SKILL.md
# /ouroboros:interview
Socratic interview that turns a vague request into the goals, constraints, and acceptance criteria a Seed needs.
## Required Skill Capabilities
- `ask_user`: ask human-judgment questions through the active runtime's `ask_user` capability.
- `inspect_code`: answer repo-local factual questions from exact local files before asking the user.
- `call_mcp`: use Ouroboros MCP tools for persistent interview state and seed generation.
- `orchestrate_subagents`: run advisory lanes and the Seed-ready Acceptance Guard lanes.
- `run_lateral_review`: invoke lateral thinking subagents before milestone turns and direct-answer synthesis.
- `web_research`: fetch current external facts only when the interview genuinely depends on them.
- `refine_answer`: confirm structured interpretations of free-text answers before forwarding them (Refine gate).
- `maintain_ledger`: keep ambiguity, gates, and unresolved decisions visible in the main session.View the complete source on GitHubooo
When your agent uses it
Start Ouroboros onboarding. Use when the user sends bare `ooo`, asks to start Ouroboros, or is using Ouroboros for the first time.
What it loads into context
Frontmatter
41 tokensAlways available to the agent
SKILL.md
197 tokensWhen the skill is activated
Reference documents
6,535 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- RFC #1392 State Breadcrumb Footer
Files
SKILL.mdcore853 bytes../welcome/SKILL.mddoc25,150 bytes
Read SKILL.md
# Start Ouroboros
Read `../welcome/SKILL.md` and follow its instructions exactly. This is the
explicit Marketplace-plugin entry point for a bare `ooo` message before any
runtime-specific setup has run.
## RFC #1392 State Breadcrumb Footer
Your final response MUST end with exactly one breadcrumb footer line:
```
◆ <current state> → next: <recommended action>
```
View the complete source on GitHubpm
When your agent uses it
Use when the user wants product requirements rather than code: 'write a PRD', 'product requirements', 'spec this feature for the team', 'ooo pm'. Runs a PM-focused interview with automatic question classification and produces a PRD/PM document. Not for implementation requests.
What it loads into context
Frontmatter
63 tokensAlways available to the agent
SKILL.md
2,942 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Required Skill Capabilities
- Instructions
- RFC #1392 State Breadcrumb Footer
Files
SKILL.mdcore12,560 bytes
Read SKILL.md
# /ouroboros:pm
PM-focused Socratic interview that produces a Product Requirements Document (PRD).
## Required Skill Capabilities
- `ask_user`: ask the user through the active runtime's `ask_user` capability.
- `call_mcp`: `ouroboros_pm_interview` holds the interview state and writes the PRD.
- `orchestrate_subagents`: run the evidence lanes each question carries.
- `refine_answer`: confirm the structured answer before it is sent (Refine gate).
- `run_shell`: copy the finished PRD to the clipboard, when available.
## Instructions
View the complete source on GitHubpublish
When your agent uses it
Publish Seed specification as GitHub Issues for team-based project management
What it loads into context
Frontmatter
20 tokensAlways available to the agent
SKILL.md
1,541 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Instructions
- RFC #1392 State Breadcrumb Footer
Files
SKILL.mdcore5,818 bytesSKILL.mdcore5,818 bytesSKILL.mdcore5,818 bytes
Read SKILL.md
# /ouroboros:publish
Convert a Seed into a GitHub Epic issue plus Task issues. Works entirely through the `gh` CLI (no MCP), creates new issues only, and never modifies existing ones.
```
ooo publish [seed_path]
/ouroboros:publish [seed_path]
```
## Instructions
Run commands with the active runtime's `run_shell` capability and ask every question with the active runtime's `ask_user` capability.
### Step 1: PrerequisitesView the complete source on GitHubqa
When your agent uses it
General-purpose QA verdict for any artifact type
What it loads into context
Frontmatter
16 tokensAlways available to the agent
SKILL.md
1,450 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Instructions
- RFC #1392 State Breadcrumb Footer
Files
SKILL.mdcore6,166 bytesSKILL.mdcore6,166 bytesSKILL.mdcore6,166 bytesSKILL.mdcore6,166 bytesSKILL.mdcore6,166 bytes
Read SKILL.md
# /ouroboros:qa
Fast single-pass quality verdict with actionable suggestions for any artifact: code, documents, API responses, test output, or custom content. For formal three-stage verification of an execution, use `ooo evaluate`.
```
ooo qa [file_path | artifact_text]
ooo qa # recent execution output
/ouroboros:qa [file_path | artifact_text]
```
The QA Judge scores the artifact against a quality bar on Correctness, Completeness, Quality, Intent Alignment, and Domain-Specific dimensions:
| Score | Verdict | Loop action |
|-------|---------|-------------|View the complete source on GitHubralph
When your agent uses it
MCP-owned Ralph loop around background evolve_step jobs
What it loads into context
Frontmatter
42 tokensAlways available to the agent
SKILL.md
2,052 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Usage
- Instructions
- RFC #1392 State Breadcrumb Footer
Files
SKILL.mdcore8,987 bytes
Read SKILL.md
# /ouroboros:ralph
MCP-owned Ralph loop around background `evolve_step` jobs. "The boulder never stops."
## Usage
```
ooo ralph --lineage-id <lineage_id>
/ouroboros:ralph --lineage-id <lineage_id>
```
The `ouroboros_ralph` tool owns the loop (do not reimplement it): one background job runs repeated `evolve_step` generations until QA pass, convergence, a terminal evolution action, cancellation, or `max_generations`. Router dispatch reads only the named `--lineage-id` option, never trailing text.
## InstructionsView the complete source on GitHubresume-session
When your agent uses it
List in-flight Ouroboros sessions and show the commands needed to re-attach after MCP disconnect
What it loads into context
Frontmatter
28 tokensAlways available to the agent
SKILL.md
511 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Instructions
- RFC #1392 State Breadcrumb Footer
Files
SKILL.mdcore2,175 bytes
Read SKILL.md
# /ouroboros:resume-session
Recover in-flight Ouroboros sessions after an unexpected MCP server disconnect. The name avoids shadowing Claude Code's built-in `/resume`.
```
ooo resume-session [--all]
/ouroboros:resume-session
```
## Instructions
1. Run with the active runtime's `run_shell` capability:
```View the complete source on GitHubouroboros-run
When your agent uses it
Use when an Ouroboros Seed (a spec file with a goal and acceptance criteria, such as *.seed.yaml) already exists and the user wants it executed: 'run the seed', 'execute this spec', 'ooo run'. Executes it and verifies every acceptance criterion. Not for raw requests without a Seed (use interview or auto).
What it loads into context
Frontmatter
113 tokensAlways available to the agent
SKILL.md
3,341 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Usage
- Instructions
- Fallback (No MCP Server)
- RFC #1392 State Breadcrumb Footer
Files
SKILL.mdcore14,352 bytesSKILL.mdcore14,352 bytes
Read SKILL.md
# /ouroboros:ouroboros-run
Execute a Seed specification through the Ouroboros workflow engine as a background job. A completed run enqueues formal evaluation by default, and a rejection continues through a bounded Ralph loop.
## Usage
```
/ouroboros:ouroboros-run [seed_file_or_content]
```
## Instructions
### Loading MCP tools (deferred-schema guard)
View the complete source on GitHubseed
When your agent uses it
Use when goal, constraints, and success criteria are already settled and the user wants them frozen into a formal spec an agent can execute and verify: 'turn this into a spec', 'write it up as a Seed', or right after an interview. Returns an immutable Seed with acceptance criteria. Not for vague requests (use interview first).
What it loads into context
Frontmatter
103 tokensAlways available to the agent
SKILL.md
3,576 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Required Skill Capabilities
- Usage
- Instructions
- After Seed Generation
- RFC #1392 State Breadcrumb Footer
Files
SKILL.mdcore14,727 bytesSKILL.mdcore14,727 bytesSKILL.mdcore14,727 bytesSKILL.mdcore14,727 bytesSKILL.mdcore14,727 bytesSKILL.mdcore14,727 bytesSKILL.mdcore14,727 bytesSKILL.mdcore14,727 bytesSKILL.mdcore14,727 bytesSKILL.mdcore14,727 bytesSKILL.mdcore14,727 bytes
Read SKILL.md
# /ouroboros:seed
Generate a validated Seed specification from an interview or from requirements this conversation already settled.
## Required Skill Capabilities
`ask_user` (the active runtime's user-question surface), `inspect_code`, `call_mcp`, `orchestrate_subagents` (lateral persona payloads), `run_shell` (audit-trail and prefs writes), `refine_answer` (confirm free-form decisions), `maintain_ledger` (QA scores, candidate decisions, rejected proposals).
## Usage
```
ooo seed [session_id]
/ouroboros:seed [session_id]
```View the complete source on GitHubsetup
When your agent uses it
Guided onboarding wizard for Ouroboros setup
What it loads into context
Frontmatter
24 tokensAlways available to the agent
SKILL.md
3,972 tokensWhen the skill is activated
Reference documents
855 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Usage
- Setup Wizard Flow
- Uninstall
- Setup Troubleshooting
- RFC #1392 State Breadcrumb Footer
Files
../config/SKILL.mddoc3,524 bytesSKILL.mdcore14,703 bytesSKILL.mdcore14,703 bytesSKILL.mdcore14,703 bytesSKILL.mdcore14,703 bytesSKILL.mdcore14,703 bytesSKILL.mdcore14,703 bytesSKILL.mdcore14,703 bytesSKILL.mdcore14,703 bytesSKILL.mdcore14,703 bytesSKILL.mdcore14,703 bytesSKILL.mdcore14,703 bytesSKILL.mdcore14,703 bytesSKILL.mdcore14,703 bytesSKILL.mdcore14,703 bytes
Read SKILL.md
# /ouroboros:setup
Guided Ouroboros setup inside a Claude Code session.
> Other runtimes (Codex, Copilot, OpenCode, and others) configure through the
> CLI instead, for example `ouroboros setup --runtime codex` or
> `ouroboros setup --runtime copilot`. See
> [Getting Started](https://github.com/Q00/ouroboros/blob/main/docs/getting-started.md).
## Usage
```
ooo setup
/ouroboros:setupView the complete source on GitHubouroboros-status
When your agent uses it
Check session status and measure goal drift
What it loads into context
Frontmatter
45 tokensAlways available to the agent
SKILL.md
591 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Instructions
- Fallback (no MCP server)
- RFC #1392 State Breadcrumb Footer
Files
SKILL.mdcore2,449 bytes
Read SKILL.md
# /ouroboros:ouroboros-status
Check an execution session's status and, on request, measure drift from the Seed goal.
```
/ouroboros:ouroboros-status [session_id]
```
## Instructions
### Loading MCP tools (deferred-schema guard)
Ouroboros tools may be deferred, and a schema loaded on one turn can unload by the next. Immediately before each `ouroboros_*` call, load it with the active runtime's tool-discovery capability: `"+ouroboros session status"` for `ouroboros_session_status` and `ouroboros_measure_drift`. A call whose schema is not loaded fails with "Invalid tool parameters". If the tool is already callable, discovery is a no-op and an empty result is expected. Use the fallback only when the tool is genuinely absent.
View the complete source on GitHubtutorial
When your agent uses it
Interactive tutorial teaching Ouroboros hands-on
What it loads into context
Frontmatter
23 tokensAlways available to the agent
SKILL.md
687 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Usage
- Principles
- Flow (about 5 minutes)
- RFC #1392 State Breadcrumb Footer
Files
SKILL.mdcore2,961 bytes
Read SKILL.md
# /ouroboros:tutorial
Interactive tutorial that teaches Ouroboros through hands-on experience.
## Usage
```
ooo tutorial
/ouroboros:tutorial
```
## Principles
1. Show something useful in the first 30 seconds.View the complete source on GitHubunstuck
When your agent uses it
Use when the user is stuck or going in circles: the same fix failed twice or more, 'nothing works', 'I've tried everything', or a consequential choice with no clear winner that is hard to undo or splits the team (which database, which architecture). Brings hacker, researcher, simplifier, architect, and contrarian perspectives and converges on one recommendation. Not for a first error or normal progress.
What it loads into context
Frontmatter
99 tokensAlways available to the agent
SKILL.md
2,187 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Usage
- Personas (lateral pool)
- Instructions
- RFC #1392 State Breadcrumb Footer
Files
SKILL.mdcore9,379 bytes
Read SKILL.md
# /ouroboros:unstuck
Break through stagnation, or advise on a hard choice, with lateral thinking personas. **Solo** runs one persona; **debate** runs several in parallel and synthesizes them.
## Usage
```
ooo lateral # debate: all 5 lateral personas
ooo lateral <persona> # solo: one persona
ooo lateral debate <p1> <p2> ... # debate with explicit members
ooo lateral @all # debate preset (the only preset)
```
## Personas (lateral pool)View the complete source on GitHubupdate
When your agent uses it
Check for updates and upgrade Ouroboros to the latest version
What it loads into context
Frontmatter
20 tokensAlways available to the agent
SKILL.md
618 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Instructions
- RFC #1392 State Breadcrumb Footer
Files
SKILL.mdcore2,793 bytesSKILL.mdcore2,793 bytes
Read SKILL.md
# /ouroboros:update
Upgrade Ouroboros without changing the installation's manager, environment, or optional-dependency profile.
```
ooo update
/ouroboros:update
```
## Instructions
The native command is the single source of truth. Run it with the active runtime's `run_shell` capability.
1. Run `ouroboros update --check`.View the complete source on GitHubwelcome
When your agent uses it
First-touch experience for new Ouroboros users
What it loads into context
Frontmatter
24 tokensAlways available to the agent
SKILL.md
6,535 tokensWhen the skill is activated
Reference documents
4,827 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Usage
- Instructions
- RFC #1392 State Breadcrumb Footer
Files
../config/SKILL.mddoc3,524 bytes../setup/SKILL.mddoc14,703 bytesSKILL.mdcore25,150 bytesSKILL.mdcore25,150 bytesSKILL.mdcore25,150 bytesSKILL.mdcore25,150 bytesSKILL.mdcore25,150 bytesSKILL.mdcore25,150 bytesSKILL.mdcore25,150 bytesSKILL.mdcore25,150 bytesSKILL.mdcore25,150 bytesSKILL.mdcore25,150 bytesSKILL.mdcore25,150 bytesSKILL.mdcore25,150 bytesSKILL.mdcore25,150 bytesSKILL.mdcore25,150 bytesSKILL.mdcore25,150 bytesSKILL.mdcore25,150 bytesSKILL.mdcore25,150 bytesSKILL.mdcore25,150 bytesSKILL.mdcore25,150 bytesSKILL.mdcore25,150 bytesSKILL.mdcore25,150 bytes
Read SKILL.md
# /ouroboros:welcome
Interactive onboarding for new Ouroboros users.
## Usage
```
/ouroboros:welcome # First-time or update onboarding
/ouroboros:welcome --skip # Skip welcome, mark as shown
/ouroboros:welcome --force # Force re-run welcome even if shown
```
## Instructions
View the complete source on GitHubrun
When your agent uses it
What it loads into context
Frontmatter
50 tokensAlways available to the agent
SKILL.md
137 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
SKILL.mdcore506 bytes
Read SKILL.md
# Run
This fixture keeps dispatch metadata in YAML frontmatter while the markdown
body contains text that looks similar enough to catch accidental whole-file
parsing.
```yaml
mcp_tool: body_should_not_be_loaded
mcp_args:
seed_path: body-value
cwd: body-cwd
aliases:
- body-alias
```
View the complete source on GitHubSkills included
- auto
- brownfield
- cancel
- ouroboros-config
- evaluate
- evolve
- ouroboros-help
- idk
- interview
- ooo
- pm
- publish
- qa
- ralph
- resume-session
- ouroboros-run
- seed
- setup
- ouroboros-status
- tutorial
- unstuck
- update
- welcome
- run
Repository facts
- License
- MIT
- Created
- Jan 14, 2026
- Last pushed
- Nov 5, 2026
- Forks
- 641
- Open issues
- 65
- Project activity
- Active
Rank over the last 12 weeks
Now #232 · best #192 · down 22 in 30 days
- #230 on Oct 30
- #231 on Oct 31
- #229 on Nov 1
- #230 from Nov 2 to Nov 3
- #231 from Nov 4 to Nov 5
- #232 since Nov 6
67 earlier periods
- #188 on Aug 2
- #187 on Aug 7
- #186 from Aug 8 to Aug 9
- #191 on Aug 10
- #192 from Aug 11 to Aug 12
- #195 on Aug 13
- #196 on Aug 14
- #194 from Aug 15 to Aug 16
- #193 on Aug 17
- #195 from Aug 18 to Aug 19
- #194 on Aug 20
- #196 on Aug 21
- #192 on Aug 22
- #199 on Aug 23
- #197 on Aug 24
- #198 from Aug 25 to Aug 26
- #200 on Aug 27
- #198 on Aug 28
- #199 on Aug 29
- #198 on Aug 30
- #197 on Aug 31
- #202 on Sep 1
- #197 on Sep 2
- #203 on Sep 3
- #199 on Sep 4
- #202 on Sep 5
- #199 on Sep 6
- #204 on Sep 7
- #205 from Sep 8 to Sep 10
- #206 on Sep 11
- #207 on Sep 12
- #208 from Sep 13 to Sep 14
- #205 on Sep 15
- #204 on Sep 16
- #203 on Sep 17
- #204 on Sep 18
- #203 on Sep 19
- #206 on Sep 20
- #207 from Sep 21 to Sep 25
- #209 on Sep 26
- #208 on Sep 27
- #209 on Sep 28
- #210 on Sep 29
- #206 on Sep 30
- #208 on Oct 1
- #210 on Oct 2
- #206 on Oct 3
- #204 on Oct 4
- #206 on Oct 5
- #208 on Oct 6
- #211 on Oct 7
- #210 on Oct 8
- #213 on Oct 9
- #210 from Oct 10 to Oct 11
- #213 on Oct 12
- #214 on Oct 13
- #212 from Oct 14 to Oct 15
- #211 on Oct 16
- #214 from Oct 17 to Oct 18
- #216 from Oct 19 to Oct 20
- #218 on Oct 21
- #217 on Oct 22
- #216 on Oct 23
- #218 on Oct 24
- #221 on Oct 25
- #222 on Oct 28
- #225 on Oct 29
Before you install
Network or broad shellAutomated signals, not a guarantee
Checked Nov 2, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 64 notes
skills/auto/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/brownfield/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/config/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/config/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/config/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/config/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/evaluate/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/evaluate/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/evaluate/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/evaluate/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/interview/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/interview/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/interview/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/publish/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/publish/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/qa/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/qa/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/qa/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/qa/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/run/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- No broad tool permissions
- 6 dangerous shell commandsin 1 file: skills/setup/SKILL.md:116
- 38 network referencesin 6 files: skills/setup/SKILL.md:12 skills/publish/SKILL.md:21 .claude-plugin/marketplace.json:1 and 3 more
- No hidden or obfuscated text
- No instruction overrides
- 3 executable scriptsin 3 files: scripts/drift-monitor.py:1 scripts/keyword-detector.py:1 scripts/session-start.py:1
- 11 references to secretsin 2 files: skills/welcome/SKILL.md:231 skills/pm/SKILL.md:54
- No requests to vote in Hot
Show all 58 signals by file
.claude-plugin/marketplace.json
- Network accessline 1
{ "$schema": "https://anthropic.com/claude-code/marketplace.schema.json", - Network accessline 2
"$schema": "https://anthropic.com/claude-code/marketplace.schema.json", - Network accessline 18
"source": "./", "category": "development", "homepage": "https://github.com/Q00/ouroboros", - Network accessline 19
"category": "development", "homepage": "https://github.com/Q00/ouroboros", "repository": "https://github.com/Q00/ouroboros", - Network accessline 20
"homepage": "https://github.com/Q00/ouroboros", - Network accessline 21
"repository": "https://github.com/Q00/ouroboros",
.claude-plugin/plugin.json
- Network accessline 7
"email": "jqyu.lee@gmail.com" }, "repository": "https://github.com/Q00/ouroboros", - Network accessline 8
}, "repository": "https://github.com/Q00/ouroboros", "homepage": "https://github.com/Q00/ouroboros", - Network accessline 9
"repository": "https://github.com/Q00/ouroboros", - Network accessline 10
"homepage": "https://github.com/Q00/ouroboros",
scripts/drift-monitor.py
- Executable scriptline 1
#!/usr/bin/env python3
scripts/keyword-detector.py
- Executable scriptline 1
#!/usr/bin/env python3
scripts/session-start.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/config/SKILL.md
- Network accessline 33
2. Relay the `http://localhost:<port>` line in case the browser did not open. - Network accessline 33
2. Relay the `http://localhost:<port>` line in case the browser did not open. - Network accessline 33
2. Relay the `http://localhost:<port>` line in case the browser did not open. - Network accessline 33
2. Relay the `http://localhost:<port>` line in case the browser did not open.
skills/evolve/SKILL.md
- Network accessline 61
Explain the evolutionary loop and suggest installing the MCP server (see [Getting Started](https://github.com/Q00/ouroboros/blob/main/docs/getting-started.md)), then running `ouroboros mcp serve --runtime claude-cli` and adding it to the ru - Network accessline 61
Explain the evolutionary loop and suggest installing the MCP server (see [Getting Started](https://github.com/Q00/ouroboros/blob/main/docs/getting-started.md)), then running `ouroboros mcp serve --runtime claude-cli` and adding it to the ru
skills/pm/SKILL.md
skills/publish/SKILL.md
- Network accessline 21
Run `command -v gh`. If missing, tell the user to install it from https://cli.github.com/ and stop. Run `gh auth status`; if not authenticated, tell the user to run `gh auth login` and stop. - Network accessline 21
Run `command -v gh`. If missing, tell the user to install it from https://cli.github.com/ and stop. Run `gh auth status`; if not authenticated, tell the user to run `gh auth login` and stop. - Network accessline 94
**Seed ID**: `<seed_id or pm_id>` | **Ambiguity Score**: <score> | **Seed**: `<seed_file_path>` *Generated by [Ouroboros](https://github.com/Q00/ouroboros) via `ooo publish`* - Network accessline 94
**Seed ID**: `<seed_id or pm_id>` | **Ambiguity Score**: <score> | **Seed**: `<seed_file_path>` *Generated by [Ouroboros](https://github.com/Q00/ouroboros) via `ooo publish`* - Network accessline 95
*Generated by [Ouroboros](https://github.com/Q00/ouroboros) via `ooo publish`* - Network accessline 95
*Generated by [Ouroboros](https://github.com/Q00/ouroboros) via `ooo publish`* - Network accessline 101
*Part of [Epic] #<epic> | Generated by [Ouroboros](https://github.com/Q00/ouroboros) via `ooo publish`* - Network accessline 101
*Part of [Epic] #<epic> | Generated by [Ouroboros](https://github.com/Q00/ouroboros) via `ooo publish`* - Network accessline 107
Show `Published to <TARGET_REPO>:` with the Epic and its Tasks as a tree (`#<n> [Epic|Task] <title>`) and the link `https://github.com/<TARGET_REPO>/issues/<epic>`. Suggest next steps: assign tasks, track on a GitHub Projects board, run `oo - Network accessline 107
Show `Published to <TARGET_REPO>:` with the Epic and its Tasks as a tree (`#<n> [Epic|Task] <title>`) and the link `https://github.com/<TARGET_REPO>/issues/<epic>`. Suggest next steps: assign tasks, track on a GitHub Projects board, run `oo
skills/setup/SKILL.md
- Network accessline 12
> CLI instead, for example `ouroboros setup --runtime codex` or > `ouroboros setup --runtime copilot`. See > [Getting Started](https://github.com/Q00/ouroboros/blob/main/docs/getting-started.md). - Network accessline 12
> CLI instead, for example `ouroboros setup --runtime codex` or > `ouroboros setup --runtime copilot`. See > [Getting Started](https://github.com/Q00/ouroboros/blob/main/docs/getting-started.md). - Network accessline 12
> CLI instead, for example `ouroboros setup --runtime codex` or > `ouroboros setup --runtime copilot`. See > [Getting Started](https://github.com/Q00/ouroboros/blob/main/docs/getting-started.md). - Network accessline 14
> [Getting Started](https://github.com/Q00/ouroboros/blob/main/docs/getting-started.md). - Network accessline 14
> [Getting Started](https://github.com/Q00/ouroboros/blob/main/docs/getting-started.md). - Network accessline 14
> [Getting Started](https://github.com/Q00/ouroboros/blob/main/docs/getting-started.md). - Network accessline 114
Prefer package managers for uv: `pipx install uv`, `pip install --user uv`, or `brew install uv`; the vendor one-liner `curl -LsSf https://astral.sh/uv/install.sh | sh` is the last resort. - Network accessline 114
Prefer package managers for uv: `pipx install uv`, `pip install --user uv`, or `brew install uv`; the vendor one-liner `curl -LsSf https://astral.sh/uv/install.sh | sh` is the last resort. - Network accessline 114
Prefer package managers for uv: `pipx install uv`, `pip install --user uv`, or `brew install uv`; the vendor one-liner `curl -LsSf https://astral.sh/uv/install.sh | sh` is the last resort. - Dangerous shell operationline 116
`curl -LsSf https://astral.sh/uv/install.sh | sh` is the last resort. - Dangerous shell operationline 116
`curl -LsSf https://astral.sh/uv/install.sh | sh` is the last resort. - Dangerous shell operationline 116
`curl -LsSf https://astral.sh/uv/install.sh | sh` is the last resort. - Network accessline 116
`curl -LsSf https://astral.sh/uv/install.sh | sh` is the last resort. - Network accessline 116
`curl -LsSf https://astral.sh/uv/install.sh | sh` is the last resort. - Network accessline 116
`curl -LsSf https://astral.sh/uv/install.sh | sh` is the last resort. - Dangerous shell operationline 344
python@3.12`, `sudo apt install python3.12`, or python.org/downloads). - Dangerous shell operationline 344
python@3.12`, `sudo apt install python3.12`, or python.org/downloads). - Dangerous shell operationline 344
python@3.12`, `sudo apt install python3.12`, or python.org/downloads).
skills/welcome/SKILL.md
- Access to secretsline 231
[Credential-related source omitted] - Access to secretsline 231
[Credential-related source omitted] - Access to secretsline 231
[Credential-related source omitted] - Access to secretsline 574
[Credential-related source omitted] - Access to secretsline 574
[Credential-related source omitted] - Access to secretsline 574
[Credential-related source omitted] - Access to secretsline 694
[Credential-related source omitted] - Access to secretsline 694
[Credential-related source omitted] - Access to secretsline 694
[Credential-related source omitted]
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
Some files could not be read; the facts below still hold.
Signal confidence: 48 facts
- Executable script in code of a file that runsscripts/drift-monitor.py:1High confidence
- Executable script in code of a file that runsscripts/keyword-detector.py:1High confidence
- Executable script in code of a file that runsscripts/session-start.py:1High confidence
- Network access in prose of the SKILL.mdskills/config/SKILL.md:33Low confidence
- Network access in prose of the SKILL.mdconfig/SKILL.md:33Low confidence
- Network access in prose of the SKILL.mdskills/config/SKILL.md:33Low confidence
- Network access in prose of the SKILL.mdskills/config/SKILL.md:33Low confidence
- Network access in prose of the SKILL.mdskills/evolve/SKILL.md:61Low confidence
- Network access in prose of the SKILL.mdevolve/SKILL.md:61Low confidence
- Access to secrets in prose of the SKILL.md: a variable, placeholder or call, not a stored valueskills/pm/SKILL.md:54Low confidence
- Access to secrets in prose of the SKILL.md: a variable, placeholder or call, not a stored valuepm/SKILL.md:54Low confidence
- Network access in prose of the SKILL.mdskills/publish/SKILL.md:21Low confidence
- Network access in prose of the SKILL.mdpublish/SKILL.md:21Low confidence
- Network access in code of the SKILL.mdskills/publish/SKILL.md:94High confidence
- Network access in code of the SKILL.mdpublish/SKILL.md:94High confidence
- Network access in code of the SKILL.mdskills/publish/SKILL.md:95High confidence
- Network access in code of the SKILL.mdpublish/SKILL.md:95High confidence
- Network access in code of the SKILL.mdskills/publish/SKILL.md:101High confidence
- Network access in code of the SKILL.mdpublish/SKILL.md:101High confidence
- Network access in prose of the SKILL.mdskills/publish/SKILL.md:107Low confidence
- Network access in prose of the SKILL.mdpublish/SKILL.md:107Low confidence
- Network access in prose of the SKILL.mdskills/setup/SKILL.md:12Low confidence
- Network access in prose of the SKILL.mdsetup/SKILL.md:12Low confidence
- Network access in prose of the SKILL.mdskills/setup/SKILL.md:12Low confidence
- Network access in prose of the SKILL.mdskills/setup/SKILL.md:14Low confidence
- Network access in prose of the SKILL.mdsetup/SKILL.md:14Low confidence
- Network access in prose of the SKILL.mdskills/setup/SKILL.md:14Low confidence
- Network access in prose of the SKILL.mdskills/setup/SKILL.md:114Low confidence
- Network access in prose of the SKILL.mdsetup/SKILL.md:114Low confidence
- Network access in prose of the SKILL.mdskills/setup/SKILL.md:114Low confidence
- Dangerous shell operation in prose of the SKILL.mdskills/setup/SKILL.md:116Low confidence
- Dangerous shell operation in prose of the SKILL.mdsetup/SKILL.md:116Low confidence
- Dangerous shell operation in prose of the SKILL.mdskills/setup/SKILL.md:116Low confidence
- Network access in prose of the SKILL.mdskills/setup/SKILL.md:116Low confidence
- Network access in prose of the SKILL.mdsetup/SKILL.md:116Low confidence
- Network access in prose of the SKILL.mdskills/setup/SKILL.md:116Low confidence
- Dangerous shell operation in prose of the SKILL.mdskills/setup/SKILL.md:344Low confidence
- Dangerous shell operation in prose of the SKILL.mdsetup/SKILL.md:344Low confidence
- Dangerous shell operation in prose of the SKILL.mdskills/setup/SKILL.md:344Low confidence
- Access to secrets in code of the SKILL.md: a variable, placeholder or call, not a stored valueskills/welcome/SKILL.md:231Low confidence
- Access to secrets in code of the SKILL.md: a variable, placeholder or call, not a stored valueskills/welcome/SKILL.md:231Low confidence
- Access to secrets in code of the SKILL.md: a variable, placeholder or call, not a stored valuewelcome/SKILL.md:231Low confidence
- Access to secrets in code of the SKILL.md: a variable, placeholder or call, not a stored valueskills/welcome/SKILL.md:574Low confidence
- Access to secrets in code of the SKILL.md: a variable, placeholder or call, not a stored valueskills/welcome/SKILL.md:574Low confidence
- Access to secrets in code of the SKILL.md: a variable, placeholder or call, not a stored valuewelcome/SKILL.md:574Low confidence
- Access to secrets in code of the SKILL.md: a variable, placeholder or call, not a stored valueskills/welcome/SKILL.md:694Low confidence
- Access to secrets in code of the SKILL.md: a variable, placeholder or call, not a stored valueskills/welcome/SKILL.md:694Low confidence
- Access to secrets in code of the SKILL.md: a variable, placeholder or call, not a stored valuewelcome/SKILL.md:694Low confidence
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Native | Manifest .claude-plugin/marketplace.json | .claude/skills/<skill-name>/ |
| Codex | Native | Manifest AGENTS.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md skills/auto/SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md skills/auto/SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md skills/auto/SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md skills/auto/SKILL.md | .opencode/skills/<skill-name>/ |
- Native The repository ships a manifest, folder or frontmatter field for this agent.
- Compatible A standard SKILL.md that this agent can read.
- Unknown No evidence either way.
Derived automatically from paths, manifests and frontmatter. Not tested on each agent.
Add this badge to your README
It updates every night and links to this page.
[](https://hotskills.dev/skill/q00-ouroboros/)