Menu
Check and invoke available skills before starting work. Invoke at the start of any task to ensure relevant skills are loaded.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
| name | using-skills |
| description | Check and invoke available skills before starting work. Invoke at the start of any task to ensure relevant skills are loaded. |
Before starting any task, check your available skills. Skills encode proven practices — ignoring them means reinventing wheels or missing important patterns.
If there's even a small chance a skill applies, invoke it. The cost of loading an irrelevant skill is low. The cost of missing relevant guidance is high.
Skills compose. One skill may tell you to invoke another.
| Skill | Use When |
|---|---|
using-skills | Start of any task |
writing-documents | Writing any documentation, READMEs, designs, plans |
code-review | Reviewing PRs, commits, staged changes, auditing code |
review-responder | Processing and responding to code review feedback |
mermaid-diagrams | Creating diagrams in markdown documents |
skill-builder | Creating or improving Claude Code skills |
domain-expert | Brainstorming, checking availability, choosing registrars |
config-packager | Updating agentic-config repo, auditing for PII, packaging skills |
research | Gathering evidence for decisions, investigating unknowns, comparing approaches |
red-team | Testing code, services, or infrastructure for vulnerabilities |
qa-engineer | Building features, reviewing work, validating output, anything that feels "done" |
game-devParent router for 14 sub-skills covering the full game dev lifecycle. Invoke game-dev to find the right sub-skill.
Sub-skills: session-planner, sprint-manager, scope-guardian, decision-journal, learning-planner, boot-dev-companion, gdd-writer, prototype-coach, game-research, art-pipeline, sound-designer, steam-publisher, playtest-coordinator, plane
wellbeingPersonal support for ADHD, emotional regulation, and self-doubt. Invoke wellbeing to route to the right help.
Sub-skills: adhd-coach, inner-ally
infrastructureHomelab cluster operations, deployments, and automation. Invoke infrastructure to route to the right tool.
Sub-skills: home-ops-deployer, k8s-operator, n8n-workflow-builder
task → using-skills → identify relevant skills → invoke them → work
game dev work → game-dev → (routes to sub-skill)
struggling / stuck → wellbeing → adhd-coach or inner-ally
cluster / deploy → infrastructure → (routes to sub-skill)
writing task → writing-documents → [document type guidance]
code review → code-review → writing-documents (for findings)
review feedback → review-responder → apply/skip each item
new skill → skill-builder → writing-documents (skills are agent docs)
research task → research → writing-documents (for synthesis report)
security testing → red-team → review-responder (for remediation)
building features → qa-engineer (wear the QA hat throughout)
validating work → qa-engineer → verification checklist
| Situation | Invoke |
|---|---|
| Starting game dev work | game-dev |
| Can't start / stuck / ADHD | wellbeing |
| Emotionally overwhelmed | wellbeing |
| Cluster / deploy / automation | infrastructure |
| Writing docs | writing-documents |
| Code review | code-review |
| Making a big decision | game-dev → decision-journal |
| Investigating / comparing / deciding | research |
| Security testing | red-team |
| Building / verifying work | qa-engineer |
| Packaging config | config-packager |
| Domain names | domain-expert |
| New skill | skill-builder |
Check skills first. Missing relevant guidance costs more than loading unused skills.
Declare what the system should be before writing code. Use when building new features, redesigning feature areas, or making significant changes that need a declaration of intent. Guides the declaration chain from findings through plans.
Wear the QA hat — think about quality the way a 15-year senior QA thinks. Use when building features, reviewing work, validating output, or when anything feels "done" but hasn't been proven to work. Prevents the gap between "it runs" and "it works."
Evidence-first research with mandatory citations and source evaluation. Use when gathering information for decisions, comparing approaches, investigating unknowns, or any task requiring verified evidence from multiple sources. Invoke at the START of research, not when writing up results.
Effective Mermaid diagrams. Use when creating markdown documents with human audiences.
Guides effective documentation creation. Activates relevant guidance for north-star, gestalt, reference, research, design, plan, flow, findings, concepts, or process documents. Prevents cascading harm from wrong information.
Audit, sanitize, and package ~/.claude/ configuration into a distributable repository with versioned releases. Use when updating the public agentic-config repo, syncing local changes, creating releases, or auditing for PII. Handles cross-platform install scripts and semantic versioning.