All authors
Claude Skills by Next-AI-Labs-Inc
github.com/Next-AI-Labs-Inc195 skills0 installs0 views
- Error Fix Safety EvalSafety evaluation for error log fixes — classifies fix risk and determines if autonomous or human-approved. UVotes: 0GitHub stars: 2
- ExecuteSession-persistent adversarial execution team. Creates a team on first call that stays alive for the entire session — scope guardian, compliance auditor, and self-healing log accumulate context across all task batches. Dispatches implementers with independent cross-verification, adversarial disproof, and oracle alignment checking. Use when you have a confirmed task list and need verified implementation.Votes: 0GitHub stars: 2
- Execute2Dispatch a single subagent on a task with full alignment discipline baked in — ascendant-context read, falsifiable verification contract, RECOVERABLE_DRAFTS handoff, and parent self-enforcing loop. Use when you (parent agent) want to delegate a discrete task to a subagent and get back work that you can independently verify with runnable commands instead of trusting self-assessment. Portable: works for any task in any project. Validated 2026-04-23 by T13-LBL-001 substrate test (9/9 V1-V9 PASS)...Votes: 0GitHub stars: 2
- Expand PerspectiveFrame-exit ritual for when you're stuck. If you have been unable to effectively solve a challenge within the amount of time you expected it would take to solve it, start asking every 5 minutes whether you are operating from within a perspective that is in fact limiting you. Teaches the perspective-shift move — popping your head out of the current frame to check whether there is more signal in a wider view — through 100 keyhole→wide-view examples across every domain. Use when debugging drags, ...Votes: 0GitHub stars: 2
- Extract Completions For LogUse when the user asks for a daily progress log, end-of-week roundup, "what did I get done", Obsidian dashboard entry, or any summary block describing recent work that the user will read. Produces signal-trigger blocks written in the user's own voice — verb-led headings, short prose paragraphs, inline obsidian wikilinks, plain date stamp. Read the `how-to-talk-like-the-founder` skill voice samples BEFORE drafting any block — non-negotiable.Votes: 0GitHub stars: 2
- Extract Wip From Past SessionsSweep a range of past Claude Code sessions with a fleet of Sonnet agents (one per session) to surface implied-but-unfinished work the user wanted done, filter to a target initiative (e.g. the <frontend-repo> launch), and convert each finding into a priority-prefixed, self-contained Obsidian proposal sorted into work-state triage folders. Use when the user wants to mine recent or older sessions for dropped actionables before a launch, or says "extract WIP", "sweep the last sessions", "what did...Votes: 0GitHub stars: 2
- Feature Completion Ux TestEnd-to-end product UX validation workflow. Use when confirming a change is truly complete: define intended UX, set conditions, execute the action, inspect request payloads, and verify admin logs (session diagnostics, pulse, the user notifications, system logs). Requires referencing $how-to-log-to-each-internal-log.Votes: 0GitHub stars: 2
- Feature Measurement WorkflowCanonical workflow for major feature creation with built-in measurement.Votes: 0GitHub stars: 2
- Fix Algo Bug Determine If Auto Fix OkSystematically eliminate a bug class by identifying the root cause, scoping all vulnerable call sites, building aVotes: 0GitHub stars: 2
- Fix Hallucinated Code Cleanup SourceIdentify code changes based on hallucinated intent, trace the source material that caused the hallucination, fix the code, thenVotes: 0GitHub stars: 2
- Flywheel ConsultantExpert on self-improving agent flywheels — systems where session data gets extracted into structured oracles that steer future sessions better. The IX alignment flywheel is the first working specimen of this pattern. Use this skill to understand how it works, audit signal quality, extend it to new data sources, diagnose degradation, OR to abstract the pattern and build a flywheel for a completely different domain. This is a case study AND a template.Votes: 0GitHub stars: 2
- Founder Knowledge StoreRead, write, and search the Founder Knowledge Store — personal insights, sales lessons, relationship patterns, strategic frameworksVotes: 0GitHub stars: 2
- Founder Voice Email WritingPreserve the user's authentic voice in all outreach, emails, and client-facing copy. The user's verbatim words with grammar fixes only — every AI "improvement" is a degradation.Votes: 0GitHub stars: 2
- Founder Watchable CanonicalCANONICAL entry for founder-watchable browser testing with screen recording. Pins the walkthrough doc, the recording command, the cohort definitions, and the append-only Instincts the user has taught across sessions. Use when the user wants to watch an agent test the UX live, or when learning a new instinct that should never be forgotten.Votes: 0GitHub stars: 2
- GapIsolate a specific measurable gap in the current scope, predict what's next, and design a plan in human terms that communicates the gap boundaries and what will fix it. Use when you need to zoom in from a large scope to one concrete, actionable piece.Votes: 0GitHub stars: 2
- GateReal-time scope listener + skill router. Spawns a persistent team where a listener agent watches conversation for actionables, shows its interpretation, and routes to the right existing skill. Use when starting any substantive session.Votes: 0GitHub stars: 2
- Genome ExperimentA/B test changes to the agent operating system (skills, hooks, CLAUDE.md) by measuring alignment KPIs via Statsig. Use when restoring skills, changing hooks, editing CLAUDE.md, or modifying governer config and you want to know if it helped or hurt.Votes: 0GitHub stars: 2
- Governer Adaptive Score Consumer GuideHow to consume the adaptive scoring response — every variable an agent can condition on, what each means, and how to build cVotes: 0GitHub stars: 2
- GovernerLeverage-tiered feature pipeline. Auto-scores features via IX-SILA or category overrides, routes to the right validation depth, executes steps sequentially with confidence-gated self-reflection and tracing. Invoke at the START of any new task or feature implementation.Votes: 0GitHub stars: 2
- Governer2EXPERIMENTAL clone of /governer with FORCED workflow stages, A/B-tested oracle enrichment, and full observability. Each required skill returned by the oracle becomes a TaskCreate item agents cannot skip. Every invocation announces variant + WHEN it runs in /speak-human form, prints full oracle input/output transcript, and logs any forced-stage violations. Behind GOVERNER2_ORACLE_ENRICH and GOVERNER2_FORCED_STAGES flags — both default off. Created by Lattice 2026-04-23 under L-SEED-001 + L-G2-...Votes: 0GitHub stars: 2
- HallucinationDiagnostic protocol invoked when an agent stated or acted on something false as if it were fact.Votes: 0GitHub stars: 2
- Harness SetupGuided, optional first-run setup for the alignment harness. Walks the person through each checkpoint — their own risk table, their writing voice, a memory search over their past work, optional oracles, and the dials — says what each step will do before doing it, and never changes anything without their yes. Use when the person runs /harness-setup, asks how to set the harness up, or a harness message says setup is unfinished.Votes: 0GitHub stars: 2
- HarnessThe alignment harness's front door. /harness setup (guided, optional setup), /harness status (every piece: on, off, set up, working, waiting on setup), /harness settings (a page on this machine that turns every piece on and off and shows what each does for you), /harness on|off|remind <piece> (turn one piece up, down, on or off), /harness conflicts (your own hooks or skills that already do a harness job, so nothing fires twice), /harness uninstall (how to remove it, and what lives outside the...Votes: 0GitHub stars: 2
- How To Bulk Register Atomic ToolsBulk register API endpoints, functions, and skills as discoverable tools in the agent tooling registry.Votes: 0GitHub stars: 2
- How To Create Or Update Skill Files 2Variant 2 — Protocol for creating and updating skill files, with positive-instruction guidance for skills that produce nuanced human-aligned output. Use when creating a skill that has to elicit user-voice, nested intent, or any output where collapsing into binaries, inflating with unsupported assertions, or sliding altitude would harm the workflow.Votes: 0GitHub stars: 2
- How To Create Or Update Skill FilesProtocol for creating and updating skill files. Use when asked to create a new skill, document a workflow as a skill, or update existing skill documentation.Votes: 0GitHub stars: 2
- How To Name ThingsGuidelines for naming variables, test descriptions, and admin UI surfaces.Votes: 0GitHub stars: 2
- How To Submit And Track ProposalsLEGACY/SEARCH-ONLY. The DB-backed developer-proposals API documented here is preserved as a read/search surface for OLD proposals — do NOT file NEW proposals here. To author a new proposal, use /propose (it lands the proposal as an Obsidian vault note that the canonical "1 - Open Proposals" dashboard surfaces). Use this skill only to look up or track proposals already in the DB API.Votes: 0GitHub stars: 2
- How To Talk Like The FounderALWAYS ON for every communication a human will read — every chat reply, status update, report, proposal, plan, commit message, comment, or doc, with no exempt category. Holds the user's verbatim directives for how to communicate to any human (conversational synthesis grounded in a real person's intended vs actual experience, no undefined terms, exact conditions when referencing code, broken is scope not "how it works"). Also governs writing in the user's first-person voice, which additionally...Votes: 0GitHub stars: 2
- How To Write Meta Analysis DocsCreate and store meta-analysis documents — deep audits, conversation mining reports, state audits, and architectural investigationsVotes: 0GitHub stars: 2
- Incomplete Tasks Get From SessionCapture unfinished tasks from the current Claude session transcript and persist them to the compaction system.Votes: 0GitHub stars: 2
- IncompleteCapture unfinished tasks from the current Claude session transcript and persist them to the compaction system.Votes: 0GitHub stars: 2
- Incomplete2Surface unfinished work from the current Claude session transcript and print it to the user in the user's own voice for approval. Sonnet does the analysis. Nothing is written to any database — the user decides what happens to each item.Votes: 0GitHub stars: 2
- InfoSummarize the session's UX intent in one sentence and evaluate compaction value.Votes: 0GitHub stars: 2
- InfuseQuery the Operating Mind — the institutional knowledge oracle built from 1,407 principles across 389 agent sessions. Use when you need to know what has been learned about any domain before acting, when starting work in an unfamiliar area, when making decisions that could conflict with established principles, or when the user says "/infuse". Returns grounded, cited answers from the full principles vault.Votes: 0GitHub stars: 2
- InitBootstrap a session by activating orchestrator mode, confirming governer calibration, and arming declare-scope — all in one command. Use at the start of any session instead of running /orchestrator, /governer, and /declare-scope separately.Votes: 0GitHub stars: 2
- Initiative PlaygroundReusable pre-code playground for any major, user-impacting initiative. Before touching real code, model the whole thing as wikilinked Markdown files (runtime vs build-harness), anchor the user's verbatim intent, decompose quotes to plans, make every decision observable, run A/B tests in chat, log every correction back into the model, and refine the response on evidence until it's right. Only then build. Use when the user says "explore this potential / I want to build X / let's sandbox this / ...Votes: 0GitHub stars: 2
- InsightRoute to the right NotebookLM knowledge oracle — 8 notebooks containing the user's institutional knowledge. Use when you need domain knowledge before acting, when asked "what does the user think about X", "check the notebooks", "query knowledge oracle", or when starting work in any unfamiliar domain. Triggers: institutional knowledge, notebooks, oracle, knowledge base, what would the user say, the user's patterns, check notebooks.Votes: 0GitHub stars: 2
- Instinct HarvestMine INSTINCTS (not facts) from user-confirmed sanity checks and coherence checks in session transcripts, and maintain a per-domain instinct ledger that agents read before entering a situation. General tier — domain-agnostic. A domain layer (e.g. /instinct-harvest-seo) supplies the ledger path, the situation taxonomy, the session filter and extra seed sources, then invokes this skill. Use when seeding a domain's instinct ledger, when harvesting a session's confirmed checks, when generating th...Votes: 0GitHub stars: 2
- Intent Alignment AuditOn-demand audit that cross-references Intent DB against codebase @intent tags and @intents-covered test headers.Votes: 0GitHub stars: 2
- Intent ArchitectCurate and map human intent into validated seed documents with nested structure, certainty scores, and predict-and-validate communicationVotes: 0GitHub stars: 2
- Intent Audit And RepairAudit one component of the app for every intention living in its code, state each in plain language a non-programmer confirms on sight, determine whether each currently works, and repair what is broken so that every failure announces itself in the wild with a human-readable headline. Use when assigned a component, screen, function, or subsystem to make observable. Test-driven — the test comes before the change, always.Votes: 0GitHub stars: 2
- Intent DbQuery or document UX intentions in the Intent DB. Use for READ ("what should happen when X", "what's the intended UX", "check the intent db") or WRITE ("log intent", "document intent", "record why we built X", "add to intent db", "propose intent").Votes: 0GitHub stars: 2
- Intent Journey Documentation V2Team-based workflow that produces human-readable journey documentation grounded in institutional knowledge with governing agents auditing every section. Use when documenting any user-facing flow, conversion funnel, or system behavior that needs the user's validation. Supersedes v1 for new work — v1 remains available.Votes: 0GitHub stars: 2
- Intent Leverage AuditAudit Intent DB items by leverage priority. Fetch highest-priority unvalidated intents, verify code still matches UX promises,Votes: 0GitHub stars: 2
- Intent LifecycleUse when starting any feature, bugfix, or refactor — ensures user intent survives from conversation through planning, iVotes: 0GitHub stars: 2
- Intent Map Docs AddAdd or update documentation in the Intent Map — the centralized map of every system, tool, and domain in the IX ecosystem, organized by nested intent. Use when documenting a new system, tool, or subsystem, or when adding artifacts to an existing domain. Target: docs/intent/Intent-Map/Votes: 0GitHub stars: 2
- Intent Map Domain SynthesisCompose or restructure a domain-level INDEX and synthesis for the Intent Map at <api-repo>/docs/intent/Intent-Map/. Use when creating a new domain, restructuring an existing one, or building the navigational synthesis layer. For adding a single entry, use /intent-map-docs-add instead.Votes: 0GitHub stars: 2
- Intent NestedName every intent from this session at all levels, one sentence each, nested to show relationships.Votes: 0GitHub stars: 2
- Intent Validation EngineValidate proposed UX intents against code and Playwright tests.Votes: 0GitHub stars: 2