All authors
Claude Skills by Next-AI-Labs-Inc
github.com/Next-AI-Labs-Inc195 skills0 installs0 views
- IntentHow to write intent statements that a human can validate without guessing. Use when writing intent statements, testable contracts, scope declarations, or any documentation that describes what the system does or what a person experiences. MUST be consumed before writing to the Intent DB, before creating verification contracts, before writing journey documentation, or before any /declare-scope.Votes: 0GitHub stars: 2
- Investigate ErrorInvestigate a production error with structured certainty tagging — separates observed code facts from inferences from predictions. Produces human-reviewable output where every claim has a confidence score and verification step. Use when triaging error logs, investigating production bugs, or when an agent needs to determine root cause without hallucinating conclusions.Votes: 0GitHub stars: 2
- Ix Sila Leverage ScoringScore any initiative through the IX-SILA 9-variable multiplicative model to surface weak links and predict higher-leverageVotes: 0GitHub stars: 2
- Jonathan CheckUser review simulator — consult 8,525 historical corrections before declaring work done. SVotes: 0GitHub stars: 2
- Jonathan Check2User response predictor v2 — queries a NotebookLM notebook loaded with 8,562 real agent↔user conversations to predict what the user would say to your output. Replaces the local Python predictor with NotebookLM's semantic retrieval + synthesis. Use before declaring work done, before presenting work, or when you need to anticipate the user's reaction.Votes: 0GitHub stars: 2
- Jonathan Check3God-mode user oracle — queries the god-mode notebook loaded with all extracted session data (coherence checks, reflect outputs, align outputs, skill sequences, compaction intents, scope declarations). Predicts what the user would say AND what the next step should be. Loops autonomously until the oracle signals scope is complete. Everything printed observably.Votes: 0GitHub stars: 2
- Knowledge Atom ExtractionExtract and consume typed knowledge atoms (corrections, mental models, findings, decisions, patterns, open questions,Votes: 0GitHub stars: 2
- Leverage PredictorPredict the next highest leverage move for the codebase. Use when asked 'what should we work on next', 'highest impact task', 'leverage prediction', or proactively after completing a major task. Agents analyze codebase state and propose strategic improvements.Votes: 0GitHub stars: 2
- Log New Mems In SwarmQuick-reference for logging new memories to the agent swarm. Use when wrapping up a task, capturing learnings, documentingVotes: 0GitHub stars: 2
- Multi Tier Audit PipelineRun a three-tier autonomous audit pipeline that discovers findings, validates them against real code, and turns confirmedVotes: 0GitHub stars: 2
- Nested IntentRetrospective /align — look backward at a session's completed work and decompose it into a nested intent map with alive, partner-explaining tone. Use at end of session, during compaction, or anytime an agent needs to articulate what a body of work produced and why. Produces parseable output for programmatic extraction into compactions.Votes: 0GitHub stars: 2
- Nested Intent2Produce a nested intent map for a multi-layered initiative — top-level goal, child goals, sub-goals, cross-cutting intents — where each node carries an intent paragraph in the user's voice with enough precision that a subagent reading just that node can act at 100% fidelity. Use when the human asks for nested intent on an initiative with multiple sub-goals, when a plan needs to be turned into a context-managed handoff package for subagents, or when an existing outline needs intent paragraphs ...Votes: 0GitHub stars: 2
- Next Priority TasksAggregate system logs, UX assignments, and agent proposals into a single prioritized task list.Votes: 0GitHub stars: 2
- On Agent Getting StuckUse the moment you find yourself thinking "I should stop and ask the user." That thought is common and often wrong. This skill is the check that tells the difference between a genuine need for the human and a stall you should predict your way through. Triggers — scope feels ambiguous mid-task, you're unsure what the user would prefer, you're about to ask a clarifying question, you're about to hand work back unfinished, you feel blocked, you want to pause and reconfirm.Votes: 0GitHub stars: 2
- On Complete All Queued TasksDrain the centralized agent action-queue — every action the user queued from a dashboard command button (propose/align/clarity/reflect/predict-skills) gets carried out by a fresh agent that orients at the command's crystallized authorized operation, writes its interpretation into the document so the seam between command and action is visible, and is verified to have actually moved the item forward before it is marked done. Use when the user says "/on-complete-all-queued-tasks", "drain the que...Votes: 0GitHub stars: 2
- On Scope ChangeUse whenever the active scope shifts during a session — entering a sub-task, dropping into a bug, climbing back to a parent goal, or pivoting. Emits a visible nested breadcrumb of the current focus (deepest < parent < root) so the user gets instant recall of exactly where the agent is in the work's nesting, and fires the chapter-mark so it lands in the transcript/TOC.Votes: 0GitHub stars: 2
- On Talking About CodeMANDATORY discipline for any communication that references code — to the user, in comments, in docs, in proposals, in reports. A code reference is worthless-to-negative unless it is fused with the exact literal conditions (numbers, states, inputs the system actually checks) AND the precise user journey that makes the statement true. Force-read whenever you reference code, and especially on triggers like "what exact ux", "i don't understand", "what are the conditions". Read this BEFORE writing...Votes: 0GitHub stars: 2
- On Turn EndRun at the end of any substantive turn that produced a work product with a governer score >30. Routes you to the right consumption skill so the user can see, understand, and act on what you did in seconds — never reading pages of output to figure out what you were working on, which part you just touched, or where to look at it. Skip for pure conversation/brainstorm with no work product.Votes: 0GitHub stars: 2
- Oracle Pre QueryStructured pre-check before any jonathan-check2 call. Forces agents to declare domain, audience, perfect-state, and negative boundaries so the oracle applies the right pattern library. Run /reflect on the scope first, then answer the schema.Votes: 0GitHub stars: 2
- OraclesThe oracle roster — 8 NotebookLM notebooks loaded with the user's institutional knowledge. Lists every oracle with explicit specificity about what it does and when to use it, in the user's voice. Includes query mechanics, output format with extraction markers, and routing. Use when you need to know which oracle to query, or when querying any oracle and needing the full format including flags, question echo, and verbatim response.Votes: 0GitHub stars: 2
- OrchestratorUse when a top-level agent must define outcomes, route work across analysis, research, and implementation layers, preserveVotes: 0GitHub stars: 2
- Pipeline Adversarial DesignStage 5.5 of the observable pipeline: adversarial thinking about a verified finding before it becomes a proposal. Fires AFTER verification confirms claims are real (Stage 4/5), BEFORE jonathan-check or proposal submission. Ask: what could go wrong if we act on this? What breaks if the fix is wrong? Outputs 05.5-adversarial-design.md with blast radius, risk-scored scenarios, and concrete UX test steps.Votes: 0GitHub stars: 2
- Pipeline Compliance AuditStage 10 of the observable pipeline. Audits every prior stage's output for every item in the batch — verifying that /align was invoked, agent_find ran, jonathan-check2 queried the oracle, /decompose converted verified findings into tasks, verification commands produced real output, proposals are zero-jargon, and reports have Mermaid diagrams and admin checkboxes. Outputs 09-compliance.md with per-stage PASS/FAIL. BLOCKS completion if any stage has FAIL. Designed to be invoked every 5 minutes ...Votes: 0GitHub stars: 2
- Pipeline Consumption HandoffProduce a consumption document for every completed pipeline item before handing off to the human. Use when work is finished and the human needs to know exactly what was built, how to open it, and what to look for. NEVER hand over a URL without verifying it first.Votes: 0GitHub stars: 2
- Pipeline Cross VerifyStage 5 of the observable pipeline: independent cross-verification of Stage 4 (Verify) output. Receives ONLY the verification contract and code diff/file references — NOT the Stage 4 reasoning. Independently runs its own commands, grades each claim PASS or FAIL with evidence, and writes 05-cross-verify.md. The evaluator's finding stands even when it contradicts the verifier's conclusion.Votes: 0GitHub stars: 2
- Pipeline Idea GeneratorStage 10 of the observable pipeline. Generates fresh high-leverage ideas to feed the pipeline queue when it runs low. Queries multiple sources (jonathan-check2 oracle, leverage-predictor, predict-next-action, agent_find for errors/complaints, compaction incomplete items), scores each candidate via governer methodology, formats as pipeline-ready items, and appends to PIPELINE-TRACKER.md after deduplicating against existing runs/.Votes: 0GitHub stars: 2
- Pipeline Scope GuardianScope compliance enforcer for the pipeline orchestrator. Registers the full promised scope at session start, tracks coverage across dispatch cycles, and blocks 'done' declarations when any list or requirement has been silently dropped. Designed to run every 10 minutes during orchestrated pipeline sessions. Prevents the v1 failure mode: 4 lists received, only 1 processed, 3 silently dropped.Votes: 0GitHub stars: 2
- Pipeline Ux VerifyStage 5.6 of the pipeline: dispatches haiku agents to verify UX claims against the actual running product. Use when Stage 5.5 (adversarial design) has produced test scenarios that need real browser validation. Input: 05.5-adversarial.md scenarios. Output: 05.6-ux-verify.md with PASS/FAIL per scenario and screenshot references.Votes: 0GitHub stars: 2
- Playwright ValidatorValidate UX flows using Playwright via MCP. Capture screenshots as evidence for UX assignments, system logs, and proposals. Use after making code changes to self-verify before creating UX assignments, or when asked to validate a flow.Votes: 0GitHub stars: 2
- Predict Next ActionPredict the next highest-leverage task based on the session, evaluate risk, and frame the UX possibility being moved toward.Votes: 0GitHub stars: 2
- Predict Next Action2Predict the next highest-leverage action by enriching session context through NotebookLM institutional knowledge, then producing a nuanced, UX-focused, intent-grounded recommendation. Use when finishing a session and wanting a deeply informed next-step prediction.Votes: 0GitHub stars: 2
- Predict Required SkillsQueries the Agent Skill Pattern Oracle (NotebookLM) with the current scope/intent and returns a MANDATORY skill sequence grounded in historical patterns. Each predicted skill MUST become a TaskCreate item. Integrates with /align, /governer, /decompose, /declare-scope. Caches result — only re-predicts on scope change.Votes: 0GitHub stars: 2
- Predict Required Skills2Predicts the skills a scope needs from what agents ACTUALLY did in 632 past sessions. Queries the Skill Pattern Oracle v3 notebook (<your-notebook-id>) — ONE merged JSON document holding every session's skill invocations with each agent's own in-the-moment reasoning for why it reached for that skill. Fully automatic end to end: agent prints a 🔥 annotation at each Skill invocation → SessionEnd runs scrape-fire-annotations.js → it rebuilds the merged corpus and replaces the notebook's single s...Votes: 0GitHub stars: 2
- Principle Alignment Scanner WorkflowAutomated 6-phase audit that maps CLAUDE.md coding rules to scanner detectors, finds violations, and fixes them safely.Votes: 0GitHub stars: 2
- Process ActionableOrchestrates the 5-stage process-actionables pipeline: Notice (/align) → Score (/governer) → Verify (/investigate-error) → Propose (/translate inline) → Heal. Accepts a raw signal string or an existing proposal ID. Checks for prior runs first. Writes observable output to a run directory. Does NOT contain any stage logic — it invokes canonical skills and captures their output.Votes: 0GitHub stars: 2
- Proof Its FixedProduce a full evidence package proving something was broken and is now fixed. Use when an agent finishes a fix and needs to prove before/after with data, screenshots, and optionally video. Invoke after completing any fix that touches user-facing behavior.Votes: 0GitHub stars: 2
- Proposal GroundGround a proposal in the actual user journey — translate code findings into a continuous narrative of what a person experiences, where the experience deviates from intent, and what fixing it would change. Required for every proposal before it can be reviewed. Multi-agent: composer writes, researcher validates, adversary tries to disprove. All must agree.Votes: 0GitHub stars: 2
- Proposal SchemaEnforces normalized proposal format when creating or filing proposals, findings, seeds, or pipeline items. Use when creating any document that needs the user's review.Votes: 0GitHub stars: 2
- Propose RunnerOps-agent role for generating a user-instantly-understood proposal on a single triage item. Runs /propose on the item, applies the anti-hallucination guardrail (inline % certainty on every load-bearing claim), grounds claims in live code (not the item's own framing), and attaches the finished proposal to the TOP of the item document. Use when dispatched to author a proposal for an item in a "get me a proposal" triage folder. Pairs with /blackhat-challenge-proposal, which challenges what this ...Votes: 0GitHub stars: 2
- ProposeOne command to turn the current situation — a conversation, a finding, a flagged session, or a raw item that needs a proposal — into a proposal the user understands the first time the user reads it. Chains the three canonical proposal skills: ground it in what a real person experiences, enforce the recognizable proposal shape, and file it. Use when an item needs a full proposal authored, when the user says "/propose", or when a triage folder item is flagged "get me a proposal."Votes: 0GitHub stars: 2
- Rapid Fire TestingInvoked directly via /rapid-fire-testing when the user names an idea and wants the agent to race by the most direct path possible to one piece of tangible evidence proving whether the idea can actually produce the desirable outcome. Open-source-first, no stopping for permission, no perfecting prompts, no human-in-the-loop until first real artifact lands.Votes: 0GitHub stars: 2
- ReflectReflect on the ASSIGNED SCOPE that is still incomplete — what the human is trying to get, where the work stands against it, and the shortest path to close the gap. Never a reflection on the agent's own performance. Use after completing significant work, before declaring a task done, or at the start of a session to align on what you are about to do.Votes: 0GitHub stars: 2
- ResearchFull lifecycle guide for conducting structured research: check existing findings, create a record, gather evidence, and recordVotes: 0GitHub stars: 2
- Resolve ProposalsFix approved proposals and close the loop — claim, fix, commit with Resolves-Proposal tags, mark implemented. UVotes: 0GitHub stars: 2
- Respond To Direct QuestionWhen the user asks a direct question alone without other directions, just answer the question.Votes: 0GitHub stars: 2
- Review Proposal GreenlightImplementation dispatch triggered by the user saying "build it" during a proposal review conversation. Creates worktree, implements, tests, opens PR. Invoked by /review-proposal — do not invoke directly unless in the context of a proposal review conversation.Votes: 0GitHub stars: 2
- Review ProposalLoad a proposal with full context and have a conversation about it. Use when the user says "review LP-032", "look at this proposal", "what about LP-033", or clicks a proposal in the admin UI.Votes: 0GitHub stars: 2
- Run Discoverability AuditReproducible full-codebase discoverability audit — ensures every tool, skill, endpoint, and MCP tool is findable by any agent on any surface.Votes: 0GitHub stars: 2
- Sanity CheckConfirms that work matches intent — before starting, after completing, before committing, or when reviewing a plan or diff.Votes: 0GitHub stars: 2
- Seed CompanyLoad the product's founding mission — why the product exists, the Silver Grail thesis, and the alignment-first philosophy — in the user's actual voice. Use when you need customer-facing mission language, when drafting communications that connect someone to the "why", or when an agent needs the founding story for retention or outreach.Votes: 0GitHub stars: 2