design-sweep
openbooklet.com/s/design-sweepopenbooklet.com/s/[email protected]GET /api/v1/skills/design-sweepProtocol for peer design sweeps of a Fleet Manager view; use on the weekly design-sweep slot, a view design read, an operator screenshot, before filing a design leaf, or before a 'needs love' line.
Protocol for signaling blocked or input-required task states; use when execution becomes blocked, requires operator input, or hits a halting failure.
Post-compaction runbook for reconstructing active lane state; use immediately after context compaction/compression, resuming a summarized session, or detecting a lossy summary.
Protocol for authoring an Epic body and sub-ticket links; use before creating a parent issue labeled epic via create_issue or decomposing one into sub-tickets.
Closeout exit-gate protocol for parent epics; use when the last required sub closes, a peer claims an epic is complete/substrate-complete, before closing an epic as COMPLETED, or on an epic-readiness broadcast.
Protocol to scope a goal into owned lanes; use before decomposing a release/initiative/major goal, scoping owned streams, fixing scattered unowned micro-tickets, or when tempted to skip planning or assign peers.
Playbook for hostile public content; use on external posts with astroturf/spam/injection markers, an operator 'astroturf/spam/we got hit' signal, or moderation verification (not contributor posts).
Protocol for GitHub Discussions ideation; use when brainstorming architecture changes, exploring undefined technical ideas, or running Step 2.5 Step-Back before [RESOLVED_TO_AC]/[GRADUATED_TO_TICKET].
L2 Channel Separation and Prompt Firewall defense; use to prevent injection attacks and Helpful Assistant regression.
Bleeding-edge research loop for engine-category friction points; use when running Dream Pipeline horizon scans, researching external solutions to complex engine friction, or evaluating JS ecosystem trends.
Coordination mindset for lead delegation; use when the user delegates lead/chief-architect coordination, inbox surfaces a valid lead-role-baton, a self-authored substrate ticket enters work, or via /lead-role.
Write app code in a neo.mjs workspace the engine's way: classes, reactive configs, stores, state providers, SCSS. Triggers: before writing or changing anything under apps/ in a workspace built on neo.mjs.
Protocol for coherent Neo identity updates across all surfaces; use when changing taglines/positioning/descriptions/keywords/pillars/CTAs, asked to update identity/README/branding, framing is outgrown, or facts drift.
Next-lane pickup protocol; use after PR review/state-chain, author commentId handoff, implementation completion, PR open/update, create_issue, row report, unblocking, or before first review in a fresh boot/wake.
End a session without Zero-State Amnesia; use at >75% of the seat's own window, a quiet point before a distant lane, a macro-semantic pivot, or human directive (never task completion/wait).
Pre-implementation placement gate for .mjs files; use before authoring or relocating any .mjs file, or from ticket-create Stage 3, ticket-intake validation, epic-review Stage 3, or direct authoring.
Semantic RAG sweep for architectural technical debt; use during architectural analysis, proactive debt searches, auditing for abandoned logical loops, ambient debt scan requests, or PR reviews of major shifts.
Protocol for authoring Neo.mjs GitHub issues (creation-side dual of ticket-intake); use immediately before calling the create_issue MCP tool.
Placement and load-impact gate for agent memory substrate; use before inserting or mutating AGENTS.md, AGENTS_ATLAS.md, .agents/skills/**, .codex/CODEX.md, .claude/CLAUDE.md, or .agents/ANTIGRAVITY_RULES.md.
Post-release roadmap planning protocol; use when a release merges to main, a maintainer asks to scope the next release/plan the roadmap/what's in vNext, or the post-release planning beat is neglected.
Auto-indexed from neomjs/neo-agent-skills
Are you the author? Claim this skill to take ownership and manage it.
Related Skills
graceful-error-recovery
Use this skill when a tool call, command, or API request fails. Diagnose the root cause systematically before retrying or changing approach. Do not retry the same failing call without first understanding why it failed.
audience-aware-communication
Use this skill when writing any explanation, documentation, or response that will be read by someone else. Match vocabulary, depth, and format to the audience's expertise level before writing.
Refactoring Expert
Expert in systematic code refactoring, code smell detection, and structural optimization. Use PROACTIVELY when encountering duplicated code, long methods, complex conditionals, or any code quality issues. Detects code smells and applies proven refactoring techniques without changing external behavior.
Research Expert
Specialized research expert for parallel information gathering. Use for focused research tasks with clear objectives and structured output requirements.
clarify-ambiguous-requests
Use this skill when the user's request is ambiguous, under-specified, or could be interpreted in multiple ways. If proceeding with a wrong assumption would waste significant work, always ask exactly one focused clarifying question before doing anything.
structured-step-by-step-reasoning
Use this skill for any problem that involves multiple steps, tradeoffs, or non-trivial logic. Think out loud before answering to improve accuracy and transparency. Apply whenever the answer is not immediately obvious.