Skip to content
Back to skills

Lexi

ASecurity

Lexicon axis standalone — extract high-frequency vocabulary, code-switching ratio, onomatopoeia. Triggers: "my vocabulary", "lexicon", "word habits", "speech patterns".

  • 3 stars
  • 0 votes
  • 0 copies
  • 4 views
  • Added May 28, 2026
ai-agentsbash

Works with

  • cli

Security analysis

A100/100

Pro scans all 3 files and shows the line behind each finding

Scanned May 28, 2026

npx -y skills add jazz1x/honne --skill lexi --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Lexi?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Lexi
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/jazz1x-lexi/badge)](https://www.skillsdirectory.com/skills/jazz1x-lexi)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: lexi
version: 0.0.5
description: >
  Lexicon axis standalone — extract high-frequency vocabulary, code-switching ratio, onomatopoeia.
  Triggers: "my vocabulary", "lexicon", "word habits", "speech patterns".
ssl:
  scheduling:
    anti_triggers:
      - "전체 7-axis 분석이 필요할 때 (whoami 사용)"
  structural:
    scenes:
      - "Step 1: HITL (scope + locale)"
      - "Step 2: Scan"
      - "Step 3: Axis extract"
      - "Step 4: Review JSON"
      - "Step 5: HITL accept/reject/edit"
      - "Step 6: Record claim"
      - "Step 7: Check past rejections"
    branches:
      - "Step 5: y → Step 6 record claim"
      - "Step 5: n → record rejection, halt"
      - "Step 5: edit → user-revised text → Step 6 record claim"
    resumable: false
  logical:
    tools: ["bash"]
    side_effects:
      reads:
        - ".honne/cache/scan.json"
      writes:
        - ".honne/assets/claims.jsonl  # append"
      deletes: []
      network: []
    idempotent: false
    rollback: ".honne/assets/claims.jsonl 의 마지막 lexicon 라인을 수동 제거."
---

# lexi — Lexicon Axis

Standalone lexicon extraction and analysis. Uses the unified `honne` CLI, presents findings, records claims.

## Step 1: HITL (scope + locale)

Ask for scope (repo/global) AND locale (ko/en/jp). Set `SCOPE` and `LOCALE` variables from the replies.

## Step 2: Scan

`bash "${CLAUDE_PLUGIN_ROOT}/scripts/honne" scan --base-dir ".honne" --scope "$SCOPE"`

## Step 3: Axis extract

`bash "${CLAUDE_PLUGIN_ROOT}/scripts/honne" axis run lexicon --scan .honne/cache/scan.json --locale "$LOCALE"`

## Step 4: Review JSON

Read JSON output — review `candidate_claim`, `quotes`, `insufficient_evidence` fields.

## Step 5: HITL accept/reject/edit

Present candidate claim with sample quotes, ask (y/n/edit):
- **y**: proceed to Step 6
- **n**: record rejection — `bash "${CLAUDE_PLUGIN_ROOT}/scripts/honne" record claim --base-dir ".honne" --type rejection --axis lexicon --scope "$SCOPE" --text "$candidate"`; skip to done
- **edit**: user provides revised text, use as claim

## Step 6: Record claim

`bash "${CLAUDE_PLUGIN_ROOT}/scripts/honne" record claim --base-dir ".honne" --type claim --axis lexicon --scope "$SCOPE" --text "$claim"`

## Step 7: Check past rejections

Avoid re-proposing: `bash "${CLAUDE_PLUGIN_ROOT}/scripts/honne" query --base-dir ".honne" --type rejection --tag lexicon --scope "$SCOPE"`

**Progress monitoring** — use Monitor until-loop (never `sleep N && cat`):
```bash
# ✓ Monitor: until [ -f ".honne/cache/.axis_lexicon.json" ]
```

Report saved to stdout + .honne/assets/claims.jsonl

Files in this skill

  • SKILL.jp.md2.8 KB
  • SKILL.ko.md2.7 KB
  • SKILL.md2.6 KB

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.