all publishers

LLM-Coding

@llm-coding source repo

14 published skills

  1. ▌
    Anchor Prior Test 2 · llm-coding bundle
    Empirically test whether a candidate term qualifies as a semantic anchor by probing how densely it sits in LLM training data — across several model tiers in a clean room — before proposing it. Use when triaging an anchor proposal, deciding anchor vs contract, or vetting a rename. Produces a verdict against the four criteria (Precise, Rich, Consistent, Attributable), a tier rating, and a ready-to-paste proposal or rejection.
    4 installs
  2. ▌
    Arc42 Documentation 2 · llm-coding bundle
    arc42 Documentation Authoring
    7 installs
  3. ▌
    Semantic Anchor Onboarding 2 · llm-coding
    DEPRECATED alias of semantic-contracts-installer. Renamed because the skill's high-value job is installing Semantic Contracts (compositions the LLM cannot guess), not bare anchor lists. Use semantic-contracts-installer instead; this alias forwards to it and will be removed after one release.
    3 installs
  4. ▌
    Semantic Anchor Translator 2 · llm-coding bundle
    Bi-directional translator between verbose descriptions and established terminology (semantic anchors). Use when (1) user describes a concept verbosely and you want to identify the precise term, or (2) user asks for methodology/approach and you want to suggest relevant anchors. Covers 120+ terms across testing, architecture, design principles, problem-solving, requirements, documentation, communication, development workflow, statistical methods, strategic planning, and creative writing.
    4 installs
  5. ▌
    Semantic Contracts Installer 2 · llm-coding bundle
    Install Semantic Contracts (and, as a sub-mode, individual semantic anchors) into a coding agent's persistent context for Claude Code, Codex, Gemini CLI, Cursor, GitHub Copilot, and similar agents. Use when setting up project-level or user-level onboarding, generating or updating AGENTS.md / CLAUDE.md / GEMINI.md / Copilot instruction files, or choosing which contracts a project should run. A contract is the part the LLM cannot guess — a named composition of anchors plus the project's own rendered template — so installing contracts is the high-value path; installing a bare anchor list is the lightweight fallback.
    5 installs
  6. ▌
    Socratic Code Theory Recovery 2 · llm-coding bundle
    Recover the "theory" (Naur 1985) of an existing codebase through recursive question refinement before writing documentation. Use on brownfield projects where the spec is missing — produces a Question Tree separating what is answerable from code (with evidence) from what must be asked of the team (routed by role). Phase 1 builds the tree; team answers the OPEN leaves; Phase 2 synthesizes PRD, Cockburn use cases, arc42 architecture, and Nygard ADRs from the answered tree.
    5 installs
  7. ▌
    Arc42 Documentation · llm-coding bundle
    arc42 Documentation Authoring
    3 installs
  8. ▌
    Risk Assess · llm-coding
    Analyze a repository to assess vibe-coding risk per module. Detects modules, scans code patterns, asks targeted questions, and writes structured assessment to CLAUDE.md.
    5 installs
  9. ▌
    Risk Mitigate · llm-coding
    Help implement mitigation measures based on the risk assessment in CLAUDE.md. Detects existing tools, installs missing ones, and tracks progress.
    6 installs
  10. ▌
    Socratic Code Theory Recovery · llm-coding bundle
    Recover the "theory" (Naur 1985) of an existing codebase through recursive question refinement before writing documentation. Use on brownfield projects where the spec is missing — produces a Question Tree separating what is answerable from code (with evidence) from what must be asked of the team (routed by role). Phase 1 builds the tree; team answers the OPEN leaves; Phase 2 synthesizes PRD, Cockburn use cases, arc42 architecture, and Nygard ADRs from the answered tree.
    5 installs
  11. ▌
    Semantic Anchor Translator · llm-coding bundle
    Bi-directional translator between verbose descriptions and established terminology (semantic anchors). Use when (1) user describes a concept verbosely and you want to identify the precise term, or (2) user asks for methodology/approach and you want to suggest relevant anchors. Covers 120+ terms across testing, architecture, design principles, problem-solving, requirements, documentation, communication, development workflow, statistical methods, strategic planning, and creative writing.
    5 installs
  12. ▌
    Semantic Contracts Installer · llm-coding bundle
    Install Semantic Contracts (and, as a sub-mode, individual semantic anchors) into a coding agent's persistent context for Claude Code, Codex, Gemini CLI, Cursor, GitHub Copilot, and similar agents. Use when setting up project-level or user-level onboarding, generating or updating AGENTS.md / CLAUDE.md / GEMINI.md / Copilot instruction files, or choosing which contracts a project should run. A contract is the part the LLM cannot guess — a named composition of anchors plus the project's own rendered template — so installing contracts is the high-value path; installing a bare anchor list is the lightweight fallback.
    5 installs
  13. ▌
    Anchor Prior Test · llm-coding bundle
    Empirically test whether a candidate term qualifies as a semantic anchor by probing how densely it sits in LLM training data — across several model tiers in a clean room — before proposing it. Use when triaging an anchor proposal, deciding anchor vs contract, or vetting a rename. Produces a verdict against the four criteria (Precise, Rich, Consistent, Attributable), a tier rating, and a ready-to-paste proposal or rejection.
    7 installs
  14. ▌
    Semantic Anchor Onboarding · llm-coding
    DEPRECATED alias of semantic-contracts-installer. Renamed because the skill's high-value job is installing Semantic Contracts (compositions the LLM cannot guess), not bare anchor lists. Use semantic-contracts-installer instead; this alias forwards to it and will be removed after one release.
    7 installs