Lens — Development skill for Claude Code
Review a prompt, page, component, or draft through expert lenses (findings), fix it in place with --fix, or grade a prompt against a rubric with --grade (verdict + --against comparison).
How to install Lens
Installs to ~/.claude/skills/emtcmca-promptsmith-lens/SKILL.md
mkdir -p ~/.claude/skills/emtcmca-promptsmith-lens && curl -fsSL https://raw.githubusercontent.com/emtcmca/promptsmith/HEAD/commands/lens.md -o ~/.claude/skills/emtcmca-promptsmith-lens/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Lens does
description: "Review a prompt, page, component, or draft through expert lenses (findings), fix it in place with --fix, or grade a prompt against a rubric with --grade (verdict + --against comparison)." usage: "/promptsmith:lens [--lens name,name] [--fix] [--grade [--against ] [--rubric a,b]] — e.g. /promptsmith:lens (paste a component) --lens accessibility --fix · /promptsmith:lens (paste a prompt) --grade --against (paste v1)" category: "dev"
Review an e
Alternatives in Development
- Lens Reviewer — Use the @lens-reviewer agent to review the following code: $ARGUMENTS 523 ★
- Extraction Judge.Prompt — Extraction Judge — Fact Durability Rubric 189 ★
- Fix Review Findings — 修复已有 Review 报告中的问题,验证后执行复审 113 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Helpful Content Review Skill
A Claude skill that reviews and scores any draft or live page against Google's helpful, reliable, people-first
Problem Lens
A Claude Skill that analyzes any problem through 12 lenses and returns 5 diverse solutions plus an Occam's Raz
Pharn Dev Review
Review what /pharn-dev-build produced. Apply the 4 review lenses (each citing a principle), emit findings in t
Debrief Agent
Post-session review that proposes changes to the agent's environment — never to the code. Nine lenses over the
Hammer
GATE H — must-have census, baseline comparison, cut list + ship verdict
Examiner Sim
Simulate the CAS-AISE examiner — rebuild the real submission PDFs, grade them against the Moodle rubric with a
Related Agents
Prose Judge
Fresh-context fidelity judge for the prose bench. Reads ONE gate file (docs/prose-rubric.md, the materials, on
Fable Experimenter
Use this agent whenever Pulkit gives a new project/UI experiment prompt in the fable repo (a request to build
Fix Applier
Use this agent after root-cause-analyst has issued a verdict with a spec-only or guarded fix scope, to make th