Meta-skill: use when creating a new skill for the superomni framework. Guides through the process of designing and writing a well-structured skill. Triggers: "create a new skill", "write a skill for", "add a skill that".
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.
Dispatches parallel agents to independently tackle 2+ tasks like separate test failures or subsystems without shared state or dependencies.
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: $_PROACTIVE"
When this skill is active, NEVER use Claude Code's built-in EnterPlanMode tool.
Use the superomni pipeline skills (brainstorm, writing-plans, executing-plans) instead.
If PROACTIVE is false: do NOT proactively suggest skills. Only run skills the
user explicitly invokes. If you would have auto-invoked, say:
"I think [skill-name] might help here — want me to run it?" and wait.
Report status using one of these at the end of every skill session:
Pipeline stage order: THINK → PLAN → REVIEW → BUILD → VERIFY → SHIP → REFLECT
REVIEW is the only human gate. All other stages auto-advance on DONE.
| Status | At REVIEW stage | At all other stages |
|---|---|---|
| DONE | STOP — present review summary, wait for user input (Y / N / revision notes) | Auto-advance — print [STAGE] DONE → advancing to [NEXT-STAGE] and immediately invoke next skill |
| DONE_WITH_CONCERNS | STOP — present concerns, wait for user decision | STOP — present concerns, wait for user decision |
| BLOCKED / NEEDS_CONTEXT | STOP — present blocker, wait for user | STOP — present blocker, wait for user |
When auto-advancing:
docs/superomni/[STAGE] DONE → advancing to [NEXT-STAGE] ([skill-name])When the user sends a follow-up message after a completed session, before doing anything else:
ls docs/superomni/specs/spec-*.md docs/superomni/plans/plan-*.md docs/superomni/ .superomni/ 2>/dev/null | head -20
git log --oneline -3 2>/dev/null
To find the latest spec or plan:
_LATEST_SPEC=$(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: Create a new, well-designed skill that integrates cleanly into the superomni framework.
A skill is good when:
{{PREAMBLE}} for consistencyAlways follow this order before writing a new skill from scratch:
1. Check project built-ins → ls skills/ && bin/skill-manager list
2. Search the network → bin/skill-manager search <query>
3. Install from URL → bin/skill-manager install <url>
4. Write from scratch → follow steps below
Never write a new skill without first completing steps 1–3.
Before writing anything, verify no existing skill already covers your need:
# Check built-in skills for overlap
bin/skill-manager list
grep -rn "name:" skills/*/SKILL.md.tmpl | head -20
Gate: If an existing skill fits → use or extend it. Stop here. If none fits → proceed to Step 2.
If no built-in skill covers your need, search GitHub and known registries:
# Search GitHub for matching skills
bin/skill-manager search <your-query>
Check known registries:
https://github.com/obra/superpowers/tree/main/skillshttps://github.com/garrytan/gstack/tree/main/skillsGate: If a suitable skill is found online → install it:
bin/skill-manager install <raw-url>
Stop here. If nothing suitable → proceed to Step 3.
Answer these questions before writing:
systematic-debugging, writing-plans)SKILL_NAME="your-skill-name"
mkdir -p "skills/${SKILL_NAME}"
Create skills/<skill-name>/SKILL.md.tmpl:
---
name: <skill-name>
description: |
[2-3 sentence description]
Triggers: [comma-separated trigger phrases]
allowed-tools: [Bash, Read, Write, Edit, Grep, Glob]
---
{{PREAMBLE}}
# <Skill Title>
**Goal:** [One sentence: what does this skill accomplish?]
## Iron Law (if applicable)
[Absolute rule that must never be violated]
## Phase 1: [First Phase Name]
[Steps, commands, outputs]
## Phase N: [Last Phase Name]
[...]
## Status Report
[Required output format for this skill]
{{PREAMBLE}} is includedname, description, allowed-toolsbash lib/gen-skill-docs.sh "skills/${SKILL_NAME}/SKILL.md.tmpl"
Verify the output:
cat "skills/${SKILL_NAME}/SKILL.md"
head -5 "skills/${SKILL_NAME}/SKILL.md" # confirm preamble was expanded
Add the new skill to the Skills Quick Reference in CLAUDE.md:
| <skill-name> | [trigger phrases] | P[0-2] |
Write a brief test scenario:
{{PREAMBLE}})---
name: my-skill
description: |
Use when [trigger condition].
Triggers: "keyword 1", "keyword 2".
allowed-tools: [Bash, Read, Write, Edit, Grep, Glob]
---
{{PREAMBLE}}
# My Skill
**Goal:** [What this accomplishes.]
## Iron Law
[Non-negotiable rule]
## Phase 1: [Name]
[Steps]
## Phase 2: [Name]
[Steps]
## Report
\`\`\`
MY SKILL REPORT
════════════════
Status: DONE | DONE_WITH_CONCERNS | BLOCKED
[Key output]
════════════════
\`\`\`