indexable-inc/index-bak/craft-standard

Claude Code and agent skill by indexable-inc/index-bak

Trust tier 3
  • community
Source check pending

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

The craft bar and defaults for every change: clear ownership, typed boundaries, checked defaults, root-cause fixes, no silent fallbacks.

Install

npx vskill@latest install indexable-inc/index-bak/craft-standard

SKILL.md

Craft standard

Write for the next reader. Pick the simplest design that makes the owner obvious: small named helpers, typed boundaries, no anonymous blobs or copy-pasted orchestration. DRY one domain fact, but do not force an abstraction over genuinely different behavior. Own domain logic once in Rust; bindings (Python, Wasm, FFI) stay thin and logic-free.

Defaults are checked, typed, reproducible, secret- and network-conservative, and overridable with a named reason. Prefer the future-correct interface over a compatibility layer, and delete the code it obsoletes in the same change.

Reject fallbacks: a missing owner, route, config, schema, or transport returns a typed, observable error, never a guessed default, sentinel, or silent retry. Fix root causes at the owner: when an adapter, conversion, or fallback recurs, move the invariant to the boundary that owns it.

Lint failures and repo rules are binding. Bypass only with local evidence, kept small, reason next to the line. Before rebuilding what the ecosystem already provides, push back once: name the tool, the cost, and the gap; when you present a choice, name the recommended default.

A fix lands code plus the nearest durable test; diagnosis alone is unfinished. Tests defend behavior that crosses a boundary, not implementation trivia.

Confirming an explanation's premises is not testing the explanation. A causal claim -- this ordering is what keeps it safe, this index is what makes it fast -- is tested only by breaking the cause and watching the effect disappear. Checking that the premises hold is the agreeable form of review, and it passes claims that are true in every part and wrong as a whole. It is most tempting exactly when the premises are cheap to verify and the conclusion sounds right. Where the claim is load-bearing, pin it with a test named for the property rather than for the mechanism, because the next refactor will preserve the mechanism it can see and break the property nobody wrote down.

Security

  • Security scanPassed, 90 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

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

Source

Popularity

Repository stars
31
Repository forks
9
7-day trend score
22

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/indexable-inc/index-bak/craft-standard/badge)](https://verified-skill.com/skills/indexable-inc/index-bak/craft-standard)

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