zenx0x/allinluna/research-routes

Claude Code and agent skill by zenx0x/allinluna

Trust tier 2
  • community
LLM review pending
Source check pending

Checking that the SKILL.md file is still in the repository.

Compare multiple research routes with explicit Claims, Evidence, unknowns, failure regimes, and reversible probes. Use when a person needs route-neutral exploration before implementation, experiment authorization, HumanDecision, or canonical-state promotion.

Install

npx vskill@latest install zenx0x/allinluna/research-routes

SKILL.md

Research Routes

Keep a route-neutral terrain map separate from decisions and execution.

  1. Inventory candidate routes and source-backed evidence.
  2. Keep observations, interpretations, Claims, Evidence, contradictions, and unknowns distinct.
  3. Compare assumptions, mature-method comparators, costs, failure regimes, and falsifiable probes.
  4. Preserve every evidence polarity, including support, counter, null, boundary, conflict, failure, context, mixed, and unknown.
  5. Choose only a reversible next probe when the user authorizes exploration.
  6. Record FailureRecord, RewindProposal, Lesson, ReopenedProblem, and canonical downgrade as append-only research records; never erase the failed path.
  7. State that a terrain map is not a route choice, experiment authorization, implementation, HumanDecision, or canonical-state promotion.

The Pack runtime lives under runtime/research_routes_runtime/ and compiles research-pack/v1. It uses only generic host, artifact, snapshot, decision, and promotion boundaries supplied by All in Luna; it does not add research state to Core. A route authorization must name a confirmed HumanDecision, and canonical promotion needs its own explicit decision scope.

When a route is authorized for product work, hand off its bounded decision and evidence package to $allinluna; do not silently turn research notes into implementation tasks.

Security

  • Security scanPassed, 100 of 100Pattern checks on the skill's files.
  • Model reviewNot runA model review is scheduled for the next rescan.

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

Repository stars
65
Repository forks
1
7-day trend score
0

Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/zenx0x/allinluna/research-routes/badge)](https://verified-skill.com/skills/zenx0x/allinluna/research-routes)

Something wrong with this skill or its page? Tell us.