Skip to content

Claude Skills by Next-AI-Labs-Inc

github.com/Next-AI-Labs-Inc

195 skillsA× 190B× 50 installs0 views

SeedALoad the SMC seed document into session memory for alignment work and user-intent context.ai-agentspythongoVotes: 0GitHub stars: 2
Session ReminderAReflect-style pass over a session's human messages that produces the session's killer title plus its full structured reminder — the artifact the sessions list shows on hover so the human remembers EXACTLY what the session was about. Copied from /reflect and restructured so its output is machine-consumable by the DSH session-reminder pipeline.documentationgoVotes: 0GitHub stars: 2
Session Titles NameARename unnamed Claude Code sessions with intent-rich titles using batched haiku subagents. Dispatches as background orchestrator task.ai-agentspythongoVotes: 0GitHub stars: 2
Show Proof To HumanAThe final 30-second sanity check before going live. Produces a tiny guide the user walks through to confirm the work actually does what it was supposed to do. Use after ALL agent testing is complete — the user is NOT the tester, the user is the final stamp of approval. Also use when the human says 'prove it', 'show me', 'is this actually working'.developmentrustgoVotes: 0GitHub stars: 2
Skill CreatorACreate new skills, improve existing skills, and measure skill performance.documentationpythonrustVotes: 0GitHub stars: 2
Skill ExtractorAScans markdown files across the codebase and converts documentation into searchable agent skills.toolsgoshellVotes: 0GitHub stars: 2
Skills DirectorySkills Directory 3 slots · $399/mo · one ad per page · sponsors can never buy grades.See placements
Skill File Create Pre Check Self Healing ProtocolARead this before creating or updating any skill file. The user's articulation, in the user's own words, of how to encode intent with precision so that the encoded artifact actually produces capacity in future agents who consume it rather than reducing their capability to apply intent to context. Includes a self-healing protocol — when the user is dissatisfied with a skill, the agent reviews the calibration with a third-party agent, prints its critique, responds, and fixes, narrating the process.developmentrustgoVotes: 0GitHub stars: 2
Smc Consumption PromptAWire and protect the SMC consumption prompt that prefixes all alignment injectionsai-agentsrustbashVotes: 0GitHub stars: 2
Smc EvaluatorANotebookLM-based alignment evaluator — independent scoring of agent sessions against CLAUDE.md rules, principles, and correction patternsai-agentsrustgoVotes: 0GitHub stars: 2
Smc Frustration DetectorADetect frustration spikes in user messages and fire telemetry alertsdevopsrustgoVotes: 0GitHub stars: 2
Smc Prediction ServerARun the persistent prediction server for user-response predictionsai-agentspythonrustVotes: 0GitHub stars: 2
SmcASMC alignment injection — detects agent drift and injects targeted user corrections. Use /smc to check status, verify telemetry, or troubleshoot.ai-agentsrustgoVotes: 0GitHub stars: 2
Speak HumanATranslate agent-speak into plain human language. Use when writing explanations, status updates, proposals, or any communicationresearchgobashVotes: 0GitHub stars: 2
Superpowers UseAMANDATORY orchestrator that forces the full Superpowers workflow chain. Invoke at the start of ANY non-trivial task. Enforces brainstorm → plan → worktree → execute (TDD + subagents) → verify → review → finish. No skipping phases.code-qualitydebuggingcode-reviewVotes: 0GitHub stars: 2
Superpowers Writing Plans V2AAlignment-coaxed clone of superpowers:writing-plans (v1). Additively enforces the product's alignment protocol: Obsidian filing, open-on-create, required frontmatter, ascendant-chain confirmation, probability-qualified claims, speak-human tone, §0.4 handoff contract, kill-switch section, additive-feedback default, parent-agent self-enforcing loop awareness. v1 behavior preserved byte-accurate in PART A.developmentpythonrustVotes: 0GitHub stars: 2
Task Get One ImportantASurface the single most critical proposable task from the current conversation — derives gap between user intent and reality, fills the full SessionCompaction incompleteItem proposal schema, and presents it in human terms.developmentrustreactVotes: 0GitHub stars: 2
Task OrchestratorAAutomatic task orchestration — ensures every agent task gets the right pipeline steps (/align, /governer, /decompose, /declare-scope, /reflect, /consume, /complete-agentic-task) without the user having to ask. Predicts which steps are needed based on task characteristics, prints them, and spawns guardian agents.code-qualitygobashVotes: 0GitHub stars: 2
Tests Failing CheckAAlign intent vs actuality for a single failing test. Use when a user asks whether a failing test actually proves the intended behavior, and how to change the test or code so the intent is truly verified.testingtestingVotes: 0GitHub stars: 2
Trace The UxATrace a user journey through the codebase — tell the story of what a person experiences, step by step, stopping at the first break. Use when investigating bugs, auditing flows, explaining code changes, or grounding proposals in reality.content-marketinggodatabaseVotes: 0GitHub stars: 2
TrackAUse when performing any multi-step audit, triage, or alignment task where future agents may repeat the same work.ai-agentsgonodeVotes: 0GitHub stars: 2
Ultraplan2ADeep-research planning workflow. Takes any scope and iterates through reflect → align → gap-identification → research-agent dispatch → oracle consultation → repeat until 95% confidence → outputs a full intent-nested decomposed plan, gated by jonathan-check2, written to Obsidian and opened. Use when a scope is complex, ambiguous, or high-leverage and requires multi-source research before committing to a plan.ai-agentsgobashVotes: 0GitHub stars: 2
Unify Obsidian VaultsAUnify scattered repo documentation into the one canonical Obsidian "intent" vault (<vault-repo>/docs/intent) via symlinks, with source-repo provenance rendered without editing source files. Use when repo docs are fragmented across repos and should be navigable/searchable from the single intent vault, or when an accidental second .obsidian vault config needs collapsing into the canonical one.testinggobashVotes: 0GitHub stars: 2
Until Proven DoneAKeep working on an objective until it is finished and proven, not just attempted. Arm a tracked goal, work in rounds, run a frame-exit check whenever stuck, and stop only when done is proven with runnable evidence, or when the same concrete external blocker has persisted across rounds with the missing dependency named exactly. Use when the person says things like \"keep going until it's fixed\", \"don't stop until it works\", \"until done and proven\", \"get unstuck\" or \"loop until done\", ...ai-agentsgogitVotes: 0GitHub stars: 2
Update The FounderAUser-voice status check-in after every substantive turn — 1-7 sentences that instantly clarify what you're working on, what just happened, what the intent was, what's predicted next, with quick single-letter commands attached. Replaces verbose agent narration with synthesized signal the user can scan in 5 seconds instead of reading paragraphs. Use after finishing any substantive task, when the user says START, when handing off mid-work, when you sense the user needs to observe state for human...businessrustgoVotes: 0GitHub stars: 2
User State Intent MapperAConverts a codebase domain into a complete intent map — every conditional branch mapped to a human-readable intent statement, organized as linked documents. Use when you need to understand what the codebase intends for every user state in a domain (access control, onboarding, billing, etc.).documentationgonodeVotes: 0GitHub stars: 2
Ux Assignment Reasoning ProtocolAMANDATORY reading before creating any UX assignment. Contains the required reasoning structure that MUST be present in every UXai-agentsgobashVotes: 0GitHub stars: 2
Ux Criticality MeasurementAMeasures how critical it is to get an initiative right from a UX perspective.developmentrustbashVotes: 0GitHub stars: 2
Ux Failure DecompositionAConsume the nested intent map for a product, derive every way each intent could fail in actual use, decompose into concrete validation tasks that return with deterministic evidence. The skill that asks "does this actually work for real?" — not "does the code exist?"testingpythonrustVotes: 0GitHub stars: 2
Ux Pre Execution ReflectionAStructured pre-execution reasoning that agents run BEFORE building, triggered when ux-criticality-measurement returns a scoredesignrustgoVotes: 0GitHub stars: 2
Ux Testing LearningsASearch and log UX testing learnings — agent swarm institutional memory for autonomous testingai-agentsbashnodeVotes: 0GitHub stars: 2
Validate Against Live DataAPattern for validating code correctness by auditing against real production data.testingjavascriptrustVotes: 0GitHub stars: 2
Validate Load Bearing Claims Against RealityAUse when you are about to report or act on a load-bearing conclusion — especially one a governer scored 90+ — that you reached by reading code, docs, or any single source of inference. This skill is the discernment that turns operating-certainty into validated truth by measuring the actual reality your claim describes. Triggers — high-leverage conclusion, "the code shows", "the DB does X", "this resolves to", "the gate fires", reporting a finding you have not measured against the thing it is ...researchrustgoVotes: 0GitHub stars: 2
Verification ContractsATask-specific verification contracts generated by governer at task start, enforced by the Stop hook at task end.testinggoapiVotes: 0GitHub stars: 2
Verification GateAFinal-pass auditor that verifies every code citation in a research/synthesis answer against actual files BEFORE publishing. Use at the end of any code-grounded research task. Catches the retrieval-augmented confabulation pattern where agents invent specific file/line citations that feel grounded but don't exist.ai-agentsbashnodeVotes: 0GitHub stars: 2
Verify Ux Assignment StateAFor each UX assignment, determine the exact user state required to test it, verify that state against actual code (never trustdevelopmentpythonrustVotes: 0GitHub stars: 2
VerifyAOutcome-first verification protocol. Forces the agent to define what the OUTCOME looks like in measurable terms BEFORE gathering any evidence. Blocks the failure pattern of substituting mechanism-evidence (hook is configured, file exists, command runs) for outcome-evidence (the thing the human wants to be true is actually happening). Use whenever asked to check if something is working.toolsgobashVotes: 0GitHub stars: 2
Whats LeftASummarize unfinished assigned work for admins in UX-first language. Use when asked what is left, what is in progress, or to communicate incomplete work without technical jargon; translate into user-facing flows and call out what remains with concrete blockers.devopsgoVotes: 0GitHub stars: 2
Work Complete AuditAEnd-of-session self-audit and checkin. Produces a structured UX story report, status check, leverage predictions, code qualitycode-qualitygonodeVotes: 0GitHub stars: 2
Work Status ReportAThe second report — after the substantive report or answer, show every piece of work grouped by how far it has actually got (proposed / work in progress / done not committed / done, committed, merged to staging), each item written as one conversational paragraph carrying what it is, the intent read back for the user to validate or reject, what happens next, and what the user will then have. Use whenever reporting status, what is left, or what is actionable.developmentgoVotes: 0GitHub stars: 2
Workflow DesignADesign agent pipeline systems from scratch. Use when creating a new multi-stage agent workflow, pipeline, or team operation for any objective.researchrustgoVotes: 0GitHub stars: 2
Workflow Extract From SessionAExtract a reproducible workflow from the current session's methodology. Use when a session produced a breakthrough result and you want to capture the exact steps, corrections, and quality gates into a permanent skill that any future agent can invoke. Invoke when the user says 'capture this', 'make this reproducible', 'I don't want to lose this', or 'extract this into a workflow'.researchnodeVotes: 0GitHub stars: 2
Workflow FactoryAFully autonomous workflow production system. Takes any objective + seed, produces a verified self-healing workflow document. Uses agent_find, /insight, /jonathan-check2 for autonomous alignment. Self-heals on failure — patches its own stage designs when auditors catch errors. The factory that builds workflows IS a self-healing workflow.researchgobashVotes: 0GitHub stars: 2
Workload Status CheckAPost-implementation status check that validates UX gap, confirmations, and file audit.securityVotes: 0GitHub stars: 2
Worktree Pr WorkflowAWhen an agent has completed work, isolate it in a git worktree, commit, push, and open a PR for human review.code-qualitygobashVotes: 0GitHub stars: 2
Writing Aligned User Facing WordsAUse when about to compose copy that will live on a Next AI Labs / <Product> / personal portfolio public surface — vehicle pages, intent pages, dedicated seed pages, audience-facing sections, CTA framings, or any prose a real reader will encounter as the organization's voice. The skill exists because this kind of work fails at the substrate level when an agent treats it as a composition task, and it succeeds when treated as an articulation-of-existing-intent task that selects and arranges from...developmentrustgoVotes: 0GitHub stars: 2