All authors
Claude Skills by Next-AI-Labs-Inc
github.com/Next-AI-Labs-Inc195 skills0 installs0 views
- AdvisorBrief on open, recent, or historical sessions in natural language. Use when asking what's up or what's incomplete.Votes: 0GitHub stars: 2
- Agent DebugPrint a diagnostic overview showing what hooks fired, what got injected into context, what's silent, and what's shaping agent behavior — before every response. Use when the user wants to see what's actually happening behind the scenes.Votes: 0GitHub stars: 2
- Agent Outcome SummaryGenerate a trustworthy, human-legible outcome report after completing dispatched work. Each item translates code changes into UX-testable statements with verification evidence grounding. The user reads this in 30 seconds and knows what happened.Votes: 0GitHub stars: 2
- Agent Ux VerificationAutomate screenshot evidence collection for UX verification assignments. Agents provide **evidence**, humans provide **judgment**. Agents never mark items as verified - they only attach screenshots and comments.Votes: 0GitHub stars: 2
- Agentic Actionable TasksGet human-approved incomplete tasks from compactions. Use when looking for approved work to pick up next.Votes: 0GitHub stars: 2
- Agentic Alignment OptimizationFix assumption cascades and feedback loops in agent workflows. Use when agents repeatedly err or validation is too slow.Votes: 0GitHub stars: 2
- Agentic Artifact CacheRead cached research and plan docs from past sessions by ID. Use when agent_find returns an artifact_id.Votes: 0GitHub stars: 2
- Agentic Chrome TestingTest your app in real Chrome via CDP — navigate, click, screenshot. Use when verifying UX or running frontend smoke tests.Votes: 0GitHub stars: 2
- Agentic Find How To Optimize Monthly Maintenence OnlyTune agent_find signal quality during monthly maintenance. Use when results feel noisy or need recalibration.Votes: 0GitHub stars: 2
- Agentic FindExplain how agent_find works and troubleshoot its results. Use when asked how to query IX institutional knowledge.Votes: 0GitHub stars: 2
- Agentic InitIdentify which skill handles a specific task type. Use when asked 'which skill for X?' or running /agent-init.Votes: 0GitHub stars: 2
- Agentic Prelaunch AuditRun 8-phase pre-launch audit: compaction, intent alignment, TDD, test health. Use when preparing any branch for prod.Votes: 0GitHub stars: 2
- Agentic Session CompactionsCreate, consume, triage, and act on agent session compactions. Use when capturing or retrieving intent across sessions.Votes: 0GitHub stars: 2
- Agentic Tooling RegistryQuery, register, and document agent tools. Use when finding a tool for X or registering endpoints via `alignment-harness store add tool-registry`.Votes: 0GitHub stars: 2
- Agentic Ux VerificationWorkflow for agents to capture UX screenshot evidence without marking verification status.Votes: 0GitHub stars: 2
- AlignFigure out what the human actually wants before doing anything. Use when starting a session, when intent is unclear, when switching topics, or when the human says "/align". This is not a technical document — it's a guide for how to listen.Votes: 0GitHub stars: 2
- Aligned BuildUse ONLY when explicitly invoked by name for an experiment run or when the user types /aligned-build. Forces the agent to surface its understanding of the request in writing and stop for human confirmation before any work begins — reflect at minimum, then align and nested-intent as task complexity warrants — then hands off to governer2 to build. This is the treatment arm of the compounding-misalignment experiment. NEVER auto-invoke.Votes: 0GitHub stars: 2
- Alignment DoctorCheck whether institutional context is being injected into this turn. Reads the most recent hook output file, greps for the injection block, prints the result with an 8-line evidence extract.Votes: 0GitHub stars: 2
- AskUse BEFORE asking the user any clarifying question. Replaces naked questions with a SILA-gated decision flow — synthesize the context the question emerges from, predict the likely answer with a confidence number, score the question using IX-SILA (the canonical scoring system that's already run for the session), then route based on criticality. Trivial questions get answered by the agent and announced. Medium questions get an agent_find pass before reasking. High-criticality questions get the ...Votes: 0GitHub stars: 2
- Audit Pre CommitPre-commit audit checklist — verify every diff against the 6 shipping principles before committing. Use before any commit, especially commits that touch user-facing code paths. Triggers: 'pre-commit', 'audit before commit', 'ready to commit', 'check before pushing', 'shipping checklist'.Votes: 0GitHub stars: 2
- Batch Whats NextPresent finished, already-verified work — a batch ready to commit, a delegated fix that came back, a re-proposal after a gap was closed — as a set of per-item cards the user can say yes/no/hold to, each one framed as the intent that must be true if the work is aligned, never as a description of what the code now does.Votes: 0GitHub stars: 2
- BatchReview uncommitted files, group them by concern, and walk through each batch with UX impact analysis before committing. Default to the Obsidian dashboard pattern — one reviewable note per concern in a one-click approve/reject/request-evidence surface — for any multi-concern sweep.Votes: 0GitHub stars: 2
- Blackhat Challenge ProposalOps-agent red-team role. Reads a generated proposal and adversarially challenges its assumptions — hunting for claims asserted as fact that are actually unverified, load-bearing assumptions that could be wrong, and reasoning that would lead a fixer astray. Documents every challenge INLINE in the proposal document, next to the claim it challenges. Use after /propose-runner produces a proposal, before the user trusts it. The skeptic half of the proposal pipeline.Votes: 0GitHub stars: 2
- Calibrate UnderstandingFirst-session calibration: the harness starts with no understanding of a new person, so it offers, once, to build some from what is already on their machine. With their yes, a low-cost model (Haiku) writes one structured note per past session (what they were after, corrections, leans, decisions, their words for things, every quote checked against what they really said), the notes become one map the agent reads at each session start, and, as a separate yes, the plans and memory notes already w...Votes: 0GitHub stars: 2
- CalibrateRe-ground to CLAUDE.md Core Protocol. Invoke when an agent is drifting from its core operating contract — communicating too technically/densely, skipping coherence checks, not reflecting intent before acting, or losing track of the alignment-first principle. Re-injects the first-principles operating contract from CLAUDE.md so the agent remembers what it's actually supposed to be doing. Especially important at end of substantive turns where agents lose protocol awareness amid context bloat.Votes: 0GitHub stars: 2
- CloseSingle command for large/critical sessions — spins up a team to produce a perfect compaction with nested intent, every artifact linked, every incomplete captured, communication audited, and jonathan-check approved. Sequences /reflect, /align, /nested-intent, /incomplete-tasks-get-from-session, artifact linking, then /compact-agentic-session as the final POST. For small sessions, use /compact-agentic-session directly.Votes: 0GitHub stars: 2
- Code Principles How To CodePrinciples for writing resilient React code that eliminates fragility without risking UX breakage. Use when writing new components, refactoring existing ones, extracting hooks, managing state, or reviewing code for structural quality. These are the coding standards for how we build.Votes: 0GitHub stars: 2
- Coherence CheckPer-message alignment ritual. Run at the top of every reply to confirm intent alignment with the user before acting. Prints COHERENCE_CHECK header, surfaces intent, calibrates communication style, tracks pending scope, and determines whether to run /governer.Votes: 0GitHub stars: 2
- CommitHandle git commits with structured messages and staged file control. Use when asked to commit, stage, or push changes.Votes: 0GitHub stars: 2
- Commit2Pre-commit intent tracing gate. Spawns an agent team to trace uncommitted code back to its originating intent (compactions, sessions, intent DB), evaluate whether the code delivers on that intent, and present the user with a decision menu before committing. Use when running /commit across repos or when uncommitted work needs intent verification before staging.Votes: 0GitHub stars: 2
- Communicate What You FinishedOn task completion, surface the work product to the user as a list of UX changes — one sentence per change in "when X then a user would see Y because Z but D" form, with emojis flagging which were verified in Chrome. Use after finishing any code change, UX fix, or feature work that produced observable user-facing outcomes. Pairs with /update-the-founder when you also need a synthesized status check-in. Triggers: task complete, work done, finished, ship summary, what did you change, list ux ch...Votes: 0GitHub stars: 2
- Communication Pattern ValidatedHOW to communicate with the user. This is not a checker or validator — it is the way you talk. When invoked, immediately apply this pattern to your NEXT response about your actual work. Do not use this to analyze your own communication.Votes: 0GitHub stars: 2
- Compact Agentic SessionCreate and consume agent session compactions for cross-session continuity. Use when capturing or retrieving intent.Votes: 0GitHub stars: 2
- Compact From TranscriptCreate a full-quality session compaction from an uncompacted Claude Code session transcript. Uses signal extraction to strip noise, then invokes /reflect + /align + alignment-harness compaction put. For sessions that have never been compacted.Votes: 0GitHub stars: 2
- Compactions EnrichEnrich session compactions with structured reflection, intent alignment, leverage scoring, and incomplete task extraction. Use when enriching existing compactions post-hoc, when running batch enrichment across all sessions, or when a compaction needs deeper analysis than the mechanical Haiku field-extraction pass provides.Votes: 0GitHub stars: 2
- Company Intent DbQuery or document company-level strategic intentions. Use when reading or writing company mission or pricing philosophy.Votes: 0GitHub stars: 2
- Complete Agentic TaskRun the mandatory completion protocol before returning control. Use when finishing any substantive piece of work.Votes: 0GitHub stars: 2
- Complete SeedAgent-invoked completion gate. When an agent believes its work is done, this skill forces it to collect evidence — load the page, grab screenshots, run verification commands from the seed's success criteria. The agent invokes this itself when it's ready. No hooks, no interrupts.Votes: 0GitHub stars: 2
- Compose Domain Knowledge ArticleCreate a Wikipedia-style domain knowledge article for the project's Obsidian vault. Use when documenting a business domain, capturing institutional knowledge, or building the knowledge base at docs/intent/knowledge-base/. Produces intent-first, evidence-backed articles that prevent hallucination cascading.Votes: 0GitHub stars: 2
- ConsumePresent finished work with clickable URLs and UX stories. Use when handing off completed work for the human to consume.Votes: 0GitHub stars: 2
- ContributeProfessional contribution workflow for upstream repos with a minimal token budget. Use when you need to split changes into atomic commits/PRs, preserve respectful credit to original authors, and delegate monotone edits to low-cost agents via short, precise briefs.Votes: 0GitHub stars: 2
- Conversation MinerScan past sessions for unlogged patterns and missing skills. Use during monthly audits or when repeated questions recur.Votes: 0GitHub stars: 2
- Declare ScopeDecompose a task into testable UX intent statements and post to compaction. Use at the start of every non-trivial task.Votes: 0GitHub stars: 2
- Decompose Nested Intent From TranscriptTake a specific transcript and produce an intent map of the client's system — restructured to lead with the critical opportunities and critical leverage, in the user's exact voice, with every relevant verbatim quote integrated and noise removed. The artifact is the highest-fidelity signal about the client's intent — their actual words on the most substantive opportunities, with all critical context that makes those opportunities lucid, clear, and born. Use when a transcript needs to become a ...Votes: 0GitHub stars: 2
- DecomposeConvert a confirmed intent map into zero-loss actionable tasks. Use after /align has produced a confirmed intent map. This is NOT a format converter — it's a reasoning guide that teaches you HOW to think about turning confirmed human intent into tasks that preserve every word of the original signal.Votes: 0GitHub stars: 2
- Deploy Alignment GuardianDeploy the Alignment Guardian agent for the current project. Use when governer scores a task >= 50, or when the human requests persistent alignment monitoring.Votes: 0GitHub stars: 2
- Devtools Site TestingChrome DevTools (MCP) workflow to load and test real production/staging/local app sites, validate Cloudflare bypass access, run perf traces, and surface console/network failures with root-cause notes.Votes: 0GitHub stars: 2
- Discoverability Audit Learnings Findable By AgentsAudit whether tools, skills, and workflows you created are actually findable by future agents — and fix gaps before they become iVotes: 0GitHub stars: 2
- Dispatch SeedPipeline from intent alignment to agent dispatch. Runs /align until confirmed, creates observable seed in Obsidian, generates plan with docs-first approach, then dispatches. The full lifecycle from "I want this done" to "an agent is working on it."Votes: 0GitHub stars: 2
- Enrich All CompactionsSingle-command pipeline to deep-enrich every session compaction in the DB. Dispatches parallel subagents (Max subscription, $0 cost) that invoke /reflect, /align, /compact-agentic-session, /incomplete-tasks-get-from-session on each compaction and write results incrementally to the local compaction store. Covers leverage scoring, phase/category assignment, full /align markdown in reflectionOnScope, and UX-first incomplete item extraction.Votes: 0GitHub stars: 2