tachyon-beep/skillpacks

Plugin marketplace

48 specialist packs with 54 skill entrypoints and 530 optional reference sheets. Focused engineering, AI/ML, design, documentation and evidence workflows.

GitHub stars: 15
plugins: 48
last updated: Nov 11, 2026

View on GitHub

Add marketplace

/plugin marketplace add tachyon-beep/skillpacks

Run it inside Claude Code, then install plugins from it with /plugin.

Plugins

1axiom-audit-pipelinesUse when decisions require verifiable provenance, tamper-evident exports, or defensible retention and replay limits. Ordinary application logging does not require this workflow.

2axiom-contract-engineeringUse when typed records cross subsystem authority boundaries and absence, meaning changes, blinded views, or derived decisions must remain explicit and reproducible.

3axiom-determinism-and-replayUse when past stateful execution must be reproduced or investigated: RNG isolation, snapshots, external-effect substitution, scheduling, rollback or first-divergence localization.

4axiom-devops-engineeringUse when building or fixing delivery and operations: artifact identity, rollout health, rollback/restore evidence, infrastructure and runtime reliability.

5axiom-distributed-systemsUse when multiple processes or failure domains must remain correct through crashes, partitions, retries, duplicates, clock changes or overload.

6axiom-embedded-databaseUse when SQLite or DuckDB application behavior depends on connection configuration, write concurrency, atomic claims, migrations, backup/restore, FTS or query/storage boundaries.

7axiom-engineering-foundationsUniversal software engineering methodology - systematic debugging, safe refactoring, code review, incident response, technical debt triage, codebase confidence building - 6 language-agnostic skills

8axiom-experiment-formalisationUse when experiment records need ontology interoperability, verified EXPO/SUMO/BFO/PROV mappings, executable competency questions or auditable description. Do not activate for ordinary experiment execution.

9axiom-mcp-engineeringUse when designing or reviewing MCP server surfaces: model-visible capability contracts, host negotiation, retries, authorization, bounded output and real task evaluation.

10axiom-planningUse when reviewing an implementation plan for source accuracy, missing dependencies, failure paths or acceptance evidence.

11axiom-procedural-architectureUse when designing or reviewing procedures, runbooks or interactive flows whose stages, decisions and handoffs must be correct for a particular audience.

12axiom-product-managementUse when deciding product value or maintaining product ownership across sessions: durable state, decision provenance, falsifiable acceptance and authority.

13axiom-program-managementUse when coordinating delivery across workstreams with real dependency agreements, risks, capacity limits and evidence-based forecasts.

14axiom-pyo3-interopUse when a PyO3 extension needs safe ownership/lifetimes, array exchange, thread attachment, async cancellation, interpreter teardown, wheel compatibility or measured FFI performance.

15axiom-python-engineeringUse for Python-specific compatibility, type/lint repair, cancellation/resource handling, profiling, packaging or Textual lifecycle issues that need focused checks against a real project.

16axiom-rust-engineeringUse for Rust-specific ownership/API, async cancellation, unsafe/FFI soundness, feature/toolchain compatibility, diagnostics, packaging or profiling problems in a real crate.

17axiom-rust-workspacesUse when multi-crate Cargo composition, feature unification, workspace policy inheritance, internal/public APIs, publishing order or target-specific test subsets cause concrete problems.

18axiom-sdlc-engineeringUse when an organization explicitly selects a software governance profile requiring lifecycle evidence, traceability, risk decisions or measurement.

19axiom-solution-architectUse when making or reviewing system design choices against measurable requirements, alternatives, migration constraints and source evidence.

20axiom-static-analysis-engineeringUse when building analyzers or rules whose traversal, abstract domain, unknown-call handling, termination, incremental cache or findings output must have explicit guarantees.

21axiom-system-archaeologistUse when reconstructing an existing codebase: source-linked architecture, dependency and risk findings, coverage limits and incremental refresh.

22axiom-system-architectTDD-validated architectural assessment enforcing professional discipline - prevents diplomatic softening, analysis paralysis, and security priority compromise - 3 specialist skills + router

23axiom-tensor-compiler-engineeringUse when tensor lowering/transforms, torch.fx/compile capture, numerical tolerances, artifact identity or cache behavior need reference-versus-compiled conformance checks.

24axiom-web-backendUse when implementing or reviewing production API behavior: authorization, compatibility, transaction boundaries, retries, bounded results and contract tests.

25bravos-game-designUse when inventing, diagnosing, repairing, balancing, or playtesting games across digital, tabletop, live, physical, educational, asynchronous, or hybrid media.

26bravos-simulation-tacticsUse when game simulation needs a fidelity/LOD decision, engine implementation, frame-budget evidence or desync diagnosis.

27bravos-systems-as-experienceUse when gameplay depends on interacting mechanics, player experimentation, optimization, emergent stories or a modding ecosystem.

28lyra-creative-writingUse when drafting, revising, critiquing, or planning prose fiction or creative nonfiction, especially when author voice, continuity, genre expectations, or truth claims need deliberate treatment.

29lyra-site-designerUse when building or maintaining static developer-tool, open-source, or documentation sites, including navigation, versioned URLs, code examples, theming, and build or deployment pipelines.

30lyra-tui-designerUse when building or reviewing interactive terminal applications, especially capability detection, rendering, input/focus, terminal restoration, accessibility, and cross-environment behavior.

31lyra-ux-designerUse when designing or reviewing application interfaces, audience needs, interaction flows, accessibility, or AI surfaces across web, mobile, desktop, and games.

32meta-skillpack-maintenanceUse when reviewing, simplifying, extending, or validating this marketplace’s plugins, skills, commands, agents, references, hooks, or packaging.

33meta-sme-protocolSME (Subject Matter Expert) Agent Protocol - mandatory protocol for all specialist agents defining fact-finding, output contracts, and confidence/risk assessment

34muna-document-designerUse when producing or validating Pandoc/Typst documents, reusable templates, print-ready PDFs, multilingual layouts, or accessible publication artifacts.

35muna-panel-reviewUse for optional staged synthetic reader reviews: precommitted expectations, controlled exposure and evidence-linked hypotheses requiring human validation.

36muna-technical-writerUse when documentation accuracy, executable procedures, institutional register, sensitive information, or source-to-document traceability needs deliberate review.

37muna-wiki-managementUse when related documents need explicit source lineage, audience-specific derivatives, claim consistency, reading paths, or controlled change propagation.

38ordis-quality-engineeringUse when test reliability, isolation, coverage gaps, performance experiments, resilience, or release evidence needs investigation or a concrete verification strategy.

39ordis-security-architectUse when system trust boundaries, threat models, control verification, AI/tool privileges, supply-chain assurance, classified information flows, or authorization evidence need design or review.

40yzmir-ai-engineering-expertPrimary router for all AI/ML engineering skillpacks - directs to specialized packs

41yzmir-counterfactual-statisticsUse when paired or branched ML experiments need uncertainty estimates, grouped splits, selection-bias controls, power analysis, or abstention calibration.

42yzmir-deep-rlUse when reinforcement-learning environment, reward, data-regime, algorithm or evaluation decisions need implementation checks.

43yzmir-dynamic-architecturesUse when a neural network grows, prunes, composes modules or adapts across tasks and needs lifecycle, gradient-isolation or state-integrity checks.

44yzmir-llm-specialistUse when an LLM application needs model/configuration evaluation, retrieval, context/cost controls, fine-tuning, tool reliability or safety checks.

45yzmir-ml-productionUse when a model or ML dataset must be released, served, monitored or recovered with operational evidence.

46yzmir-morphogenetic-rlUse when an RL controller decides when or how to change neural-network topology and needs governor, rollback, replay or fair-evaluation checks.

47yzmir-neural-architecturesUse when neural architecture families or components must be compared against data, quality, compute, latency or adaptation constraints.

48yzmir-pytorch-engineeringUse when PyTorch code has tensor/gradient, checkpoint, AMP, compile, distributed, memory or profiling obligations.

49yzmir-simulation-foundationsUse when a simulation needs numerical-model, integration, stability, control, stochastic or determinism checks.

50yzmir-structure-synthesisUse when a generator emits typed graph/program candidates and needs legality, canonical identity, diversity or search-space checks.

51yzmir-systems-thinkingUse when recurring interventions, feedback, delays or accumulation need a causal model and evidence-backed comparison.

52yzmir-training-optimizationUse when a training run needs evidence about convergence, objective, gradients, regularization, search budget, batch or precision strategy.

Details

Repository: github.com/tachyon-beep/skillpacks
Categories: development, game development, user experience, meta, documentation, testing, security, ai ml
Listed since: Dec 26, 2025