Unified entry point for the superomni framework. Activates all skills, detects current pipeline stage, and launches the guided workflow. Triggers: "/vibe", "activate framework", "start workflow", "what's next".
From superomninpx claudepluginhub wilder1222/superomni --plugin superomniThis skill is limited to using the following tools:
SKILL.md.tmplSearches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Searches prompts.chat for AI prompt templates by keyword or category, retrieves by ID with variable handling, and improves prompts via AI. Use for discovering or enhancing prompts.
Compares coding agents like Claude Code and Aider on custom YAML-defined codebase tasks using git worktrees, measuring pass rate, cost, time, and consistency.
mkdir -p ~/.omni-skills/sessions
_PROACTIVE=$(~/.claude/skills/superomni/bin/config get proactive 2>/dev/null || echo "true")
_BRANCH=$(git branch --show-current 2>/dev/null || echo "unknown")
_TEL_START=$(date +%s)
echo "Branch: $_BRANCH | PROACTIVE: $_PROACTIVE"
If PROACTIVE is false: do NOT proactively suggest skills. Only run skills the
user explicitly invokes. If you would have auto-invoked, say:
"I think [skill-name] might help here — want me to run it?" and wait.
Report status using one of these at the end of every skill session:
Pipeline stage order: THINK → PLAN → REVIEW → BUILD → VERIFY → SHIP → REFLECT
REVIEW is the only human gate. All other stages auto-advance on DONE.
| Status | At REVIEW stage | At all other stages |
|---|---|---|
| DONE | STOP — present review summary, wait for user input (Y / N / revision notes) | Auto-advance — print [STAGE] DONE → advancing to [NEXT-STAGE] and immediately invoke next skill |
| DONE_WITH_CONCERNS | STOP — present concerns, wait for user decision | STOP — present concerns, wait for user decision |
| BLOCKED / NEEDS_CONTEXT | STOP — present blocker, wait for user | STOP — present blocker, wait for user |
When auto-advancing:
docs/superomni/[STAGE] DONE → advancing to [NEXT-STAGE] ([skill-name])When the user sends a follow-up message after a completed session, before doing anything else:
ls docs/superomni/specs/spec-*.md docs/superomni/plans/plan-*.md docs/superomni/ .superomni/ 2>/dev/null | head -20
git log --oneline -3 2>/dev/null
To find the latest spec or plan:
_LATEST_SPEC=$(ls docs/superomni/specs/spec-*.md 2>/dev/null | sort | tail -1)
_LATEST_PLAN=$(ls docs/superomni/plans/plan-*.md 2>/dev/null | sort | tail -1)
workflow skill for stage → skill mapping) and announce:
"Continuing in superomni mode — picking up at [stage] using [skill-name]."using-skills/SKILL.md.When asking the user a question, match the confirmation requirement to the complexity of the response:
| Question type | Confirmation rule |
|---|---|
| Single-choice — user picks one option (A/B/C, 1/2/3, Yes/No) | The user's selection IS the confirmation. Do NOT ask "Are you sure?" or require a second submission. |
| Free-text input — user types a value and presses Enter | The submitted text IS the confirmation. No secondary prompt needed. |
| Multi-choice — user selects multiple items from a list | After the user lists their selections, ask once: "Confirm these selections? (Y to proceed)" before acting. |
| Complex / open-ended discussion — back-and-forth clarification | Collect all input, then present a summary and ask: "Ready to proceed with the above? (Y/N)" before acting. |
Rule: never add a redundant confirmation layer on top of a single-choice or text-input answer.
Custom Input Option Rule: Whenever you present a predefined list of choices (A/B/C, numbered options, etc.), always append a final "Other" option that lets the user describe their own idea:
[last letter/number + 1]) Other — describe your own idea: ___________
When the user selects "Other" and provides their custom text, treat that text as the chosen option and proceed exactly as you would for any other selection. If the custom text is ambiguous, ask one clarifying question before proceeding.
Load context progressively — only what is needed for the current phase:
| Phase | Load these | Defer these |
|---|---|---|
| Planning | Latest docs/superomni/specs/spec-*.md, constraints, prior decisions | Full codebase, test files |
| Implementation | Latest docs/superomni/plans/plan-*.md, relevant source files | Unrelated modules, docs |
| Review/Debug | diff, failing test output, minimal repro | Full history, specs |
If context pressure is high: summarize prior phases into 3-5 bullet points, then discard raw content.
All skill artifacts are written to docs/superomni/ (relative to project root).
See the Document Output Convention in CLAUDE.md for the full directory map.
Agent failures are harness signals — not reasons to retry the same approach:
harness-engineering skill to update the harness before retrying.It is always OK to stop and say "this is too hard for me." Escalation is expected, not penalized.
After completing any skill session, run a 3-question self-check before writing the final status:
If any answer is NO, address it before reporting DONE. If it cannot be addressed, report DONE_WITH_CONCERNS and name the gap.
For a full performance evaluation spanning the entire sprint, use the self-improvement skill.
_TEL_END=$(date +%s)
_TEL_DUR=$(( _TEL_END - _TEL_START ))
~/.claude/skills/superomni/bin/analytics-log "SKILL_NAME" "$_TEL_DUR" "OUTCOME" 2>/dev/null || true
Nothing is sent to external servers. Data is stored only in ~/.omni-skills/analytics/.
Goal: Activate the superomni skill framework, detect the current pipeline stage, and guide the user to the right skill.
/vibe — activate framework, detect stage, show guided menu
/vibe status — show current pipeline position and available next steps
/vibe reset — clear superomni artifacts and restart from THINK
/vibe is the single unified entry point. It never executes work itself — it detects the current stage and delegates to the appropriate skill.
When /vibe is invoked, you MUST follow this skill's phases (Phase 1-4) directly. NEVER trigger Claude Code's built-in EnterPlanMode tool at any point during the vibe workflow or any subsequent superomni skill session. EnterPlanMode bypasses the superomni pipeline entirely. For planning, delegate to the writing-plans skill. For implementation, delegate to executing-plans or subagent-development.
Scan for existing artifacts to determine where the project is in the sprint pipeline:
# Artifact detection (glob for dynamic filenames)
_HAS_SPEC=$(ls docs/superomni/specs/spec-*.md 2>/dev/null | sort | tail -1)
_HAS_PLAN=$(ls docs/superomni/plans/plan-*.md 2>/dev/null | sort | tail -1)
_HAS_EXECUTIONS=$(ls docs/superomni/executions/*.md 2>/dev/null | head -1)
_HAS_IMPROVEMENTS=$(ls docs/superomni/improvements/*.md 2>/dev/null | head -1)
# Session matching: extract session from plan filename for review detection
if [ -n "$_HAS_PLAN" ]; then
_PLAN_SESSION=$(basename "$_HAS_PLAN" .md | sed 's/plan-[^-]*-//' | sed 's/-[0-9]*$//')
_HAS_MATCHING_REVIEW=$(ls docs/superomni/reviews/review-*-${_PLAN_SESSION}-*.md 2>/dev/null | head -1)
_PLAN_OPEN=$(grep -c '^\- \[ \]' "$_HAS_PLAN" 2>/dev/null || echo "0")
_PLAN_DONE=$(grep -c '^\- \[x\]' "$_HAS_PLAN" 2>/dev/null || echo "0")
fi
# Recent git activity
git log --oneline -5 2>/dev/null
git status --short 2>/dev/null
Use the following priority-ordered rules (first match wins):
| Priority | Condition | Stage | Skill |
|---|---|---|---|
| 1 | No artifacts at all | THINK | brainstorm |
| 2 | spec-*.md exists, no plan-*.md | PLAN | writing-plans |
| 3 | plan-*.md exists, no review doc matching its session | REVIEW | plan-review — human gate: wait for Y/N |
| 4 | Plan reviewed + approved, has open items (- [ ]) | BUILD | executing-plans |
| 5 | plan-*.md all checked | VERIFY | Required: code-review → qa → verification. Optional: security-audit (if security-relevant), production-readiness (if deploying) |
| 6 | Verified | SHIP | ship, finishing-branch |
| 7 | Shipped | REFLECT | self-improvement → retro (run sequentially in one stage) |
Session matching for REVIEW detection: Extract the [session] segment from the plan filename (e.g., plan-main-auth-refactor-20260404.md → session = auth-refactor). A matching review doc must contain the same session identifier (e.g., review-main-auth-refactor-*.md). If no matching review exists → stage is REVIEW.
REVIEW is the only human gate. All other stages auto-advance on DONE.
[STAGE] DONE → advancing to [NEXT-STAGE] ([skill-name])Plan review complete. Proceed to BUILD? (Y / N / describe revisions)Only show the guided menu when:
/vibe without argumentsIf the user passes arguments with /vibe (e.g., /vibe I want to build a CLI tool), treat the arguments as the starting prompt and route to the detected skill with that context.
Present the available commands only when auto-advance does not apply:
| Command | What it does |
|---------|-------------|
| /brainstorm | Design a feature — produces spec-[branch]-[session]-[date].md |
| /write-plan | Turn a spec into an executable plan |
| /execute-plan | Run the plan step by step |
| /review | Plan review (before BUILD) |
| /qa | Quality assurance and test coverage |
| /verify | Verify task completion |
| /production-readiness | Pre-deploy readiness check |
| /investigate | Exploratory investigation |
| /self-improve | Post-task performance evaluation |
| /retro | Engineering retrospective |
| /workflow | See the full sprint pipeline |
| /ship | Release workflow |
Suggested next step → [skill-name]: [reason based on detected stage]
/vibe statusRun the stage detection from Phase 1 and display:
Pipeline: THINK → PLAN → REVIEW → BUILD → VERIFY → SHIP → REFLECT
Stage: [current] | Branch: [branch]
Artifacts: spec-*.md [Y/N] | plan-*.md [Y/N] | executions [N] | reviews [N] | prod-readiness [N] | improvements [N]
Next → [skill-name]: [reason]
/vibe resetWarn before clearing artifacts:
WARNING: This will remove all superomni artifacts:
- docs/superomni/specs/spec-*.md
- docs/superomni/plans/plan-*.md
- docs/superomni/executions/
- docs/superomni/reviews/
- docs/superomni/subagents/
- docs/superomni/production-readiness/
Self-improvement history will be preserved:
- docs/superomni/improvements/
- docs/superomni/evaluations/
- docs/superomni/harness-audits/
Proceed? (Y/N)
If confirmed:
rm -f docs/superomni/specs/spec-*.md docs/superomni/plans/plan-*.md
rm -rf docs/superomni/executions/ docs/superomni/reviews/ docs/superomni/subagents/ docs/superomni/production-readiness/
echo "Reset complete. Starting fresh from THINK stage."
Then re-run Phase 1-2 (will detect THINK stage).
After displaying the banner and menu:
Important: /vibe never executes implementation work directly. It always delegates to the appropriate skill. Do NOT use Claude Code's built-in EnterPlanMode — always delegate to the superomni skill (e.g., writing-plans for planning).
Report status: DONE — framework activated, stage detected, user guided to next skill.