ariaxhan/kernel-claude

help

Show KERNEL help. The unified skill system, state operations, agents, current plugin status. Triggers: help, how, what, skills, commands.

Langue du texte source : anglais

human-pass

Write the guided acceptance pass a human runs against a real build: literal taps, real inputs, expected outcome per step, worst case first, bundled to cost one sitting. Triggers: testflight, human pass, acceptance test, before we ship, hand it to the user,…

Langue du texte source : anglais

ship

Release-gate sequence: validate → review → push → tag. Wraps kernel:git mechanics with the pre-ship safety chain. Triggers: ship, release, push to main, ready to merge, deploy.

Langue du texte source : anglais

build

Solution exploration and implementation. Generate 2-3 approaches, pick simplest. Never implement first idea. Triggers: build, implement, create, feature, add.

Langue du texte source : anglais

ingest

Unified entry point for new AND resumed work. Research → classify → scope → execute for new tasks; manifest validate → divergence check → bounded context compile → resume for kernel.handoff/v1 / kernel.checkpoint/v1 manifests. Triggers: start, begin, do,…

Langue du texte source : anglais

landing-page

Explicit landing-page build and deployment operator. Loads marketing strategy and frontend judgment, scaffolds the smallest suitable site, verifies rendered behavior, and deploys to the user's or project's configured target.

Langue du texte source : anglais

frontend

Context-led frontend design and UI implementation. Derives art direction from the product, audience, brand, content, and existing design system; prevents generic AI defaults without imposing a Kernel house style. Triggers: frontend, ui, styling, css, visual,…

Langue du texte source : anglais

orchestration

Multi-agent orchestration. Lane contracts, worker-model doctrine, fault tolerance, worktree isolation. Triggers: orchestrate, coordinate, agents, parallel, spawn, contract, tier 2, tier 3.

Langue du texte source : anglais

knowledge-graph

Build + keep-fresh + query a deterministic code knowledge graph to cut agent orientation-token cost. Triggers: knowledge graph, graphify, code graph, god nodes, orientation cost, token bill, map the codebase, what connects X to Y, callers of, blast radius.

Langue du texte source : anglais

debug

Systematic debugging methodology based on Zeller's scientific method. Reproduce, hypothesize, predict, test, isolate via binary search, fix root cause. Every fix gets a regression test. Triggers: bug, error, fix, broken, not working, fails, crashed,…

Langue du texte source : anglais

diagnose

Systematic debugging and refactor analysis. Diagnosis before prescription. Bug mode: reproduce, trace, isolate, hypothesize, diagnose. Refactor mode: map, trace deps, measure coupling, risks, diagnose.

Langue du texte source : anglais

marketing-site

Honest marketing and client-site methodology for landing pages, product/company websites, portfolios, launch or campaign pages, service-business sites, and conversion copy. Clarifies audience, positioning, offer, proof, objections, CTA, privacy, art…

Langue du texte source : anglais

governance-sync

Audit or explicitly synchronize Claude and Codex repository governance without overwriting conflicts. Triggers: governance sync, CLAUDE.md, AGENTS.md, instruction mirror.

Langue du texte source : anglais

retrospective

Cross-session learning synthesis. Finds patterns, resolves contradictions, promotes insights into project skills, agents, and hooks. Triggers: retrospective, reflect, patterns, learnings, synthesis.

Langue du texte source : anglais

experiment

Autonomous experimentation engine + scientific method for development rules. Every rule is a hypothesis; nothing is proven until tested. Seeds from CLAUDE.md, designs falsifiable experiments, runs them, updates confidence, graduates or kills rules. Triggers:…

Langue du texte source : anglais

forge

Autonomous development engine with experimental self-correction. Heats solutions, hammers through iteration, quenches with quality gates, experiments on its own output. Runs until antifragile or reports why it can't be.

Langue du texte source : anglais

init

Initialize KERNEL links and AgentDB in a confirmed Vaults directory.

Langue du texte source : anglais

context-mgmt

Context engineering and token management. Compaction strategies, progressive disclosure, structured note-taking via AgentDB. Triggers: tokens, compaction, memory, handoff, summarize, context window.

Langue du texte source : anglais

checkpoint

Persist bounded mid-task progress as a kernel.checkpoint/v1 JSON manifest so a fresh session or context reset can resume at the exact position without a full handoff. Triggers: checkpoint, save progress, context reset, compact soon, long task.

Langue du texte source : anglais

handoff

Compile session state into an authoritative kernel.handoff/v1 JSON manifest for bounded resume. Saves provenance, decisions, workflow phases, context policy, next steps. Triggers: handoff, save, pause, context, continue later.

Langue du texte source : anglais

dream

Deep creative exploration engine. Competing perspectives, stress-tested by a 4-persona council, scored by integrity. The approach that survives attack wins — not the one that sounds best.

Langue du texte source : anglais

app-dev

Mobile/web app build pipeline: fastlane-first local builds, store submission, pre-submission checklists. Triggers: app, mobile, store submission, build, deploy app, fastlane, expo, react native, flutter.

Langue du texte source : anglais

architecture

System architecture and design patterns. Modular design, interface stability, dependency management, AI-code health nexus. Triggers: architecture, design, structure, modules, dependencies, coupling, system design.

Langue du texte source : anglais

eval

Eval-Driven Development (EDD) for AI workflows. pass@k metrics, capability evals, regression evals. Triggers: eval, edd, pass@k, capability, regression, benchmark.

Langue du texte source : anglais

metrics

Observability dashboard. Session stats, agent tracking, hook performance, learning health. Triggers: metrics, stats, dashboard, observability.

Langue du texte source : anglais

review

Code review for PRs or staged changes. >80% confidence threshold. Verdict: APPROVE, REQUEST CHANGES, or COMMENT. Triggers: review, pr, code review.

Langue du texte source : anglais

tearitapart

Critical pre-implementation review. Find what AI breaks. Verdict: PROCEED, REVISE, or RETHINK. Triggers: review plan, tear apart, critique, analyze.

Langue du texte source : anglais