Term Interrogation

Walks a finished document line by line, finds every word and phrase standing in for a concept, and breaks each one down until a reader with no background can follow it. Targets the assumed-knowledge phrase, the kind that sounds ordinary while hiding everything that matters ("moat", "flywheel", "product-market fit", "at scale"), not merely the rare word. Explains each term where it is used, then re-reads its own explanation and unpacks any new term that explanation introduced, repeating until every word bottoms out in ordinary language. Produces a term ledger recording what was flagged, how it

200 stars 25 forksOther Plugin marketplace

Install

Claude Code plugin
/plugin marketplace add lyndonkl/claude

The repo is a Claude Code plugin marketplace. Run /plugin afterwards to pick the plugin that includes this skill.

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add lyndonkl/claude --skill term-interrogation
Manual install
git clone --depth 1 https://github.com/lyndonkl/claude.git /tmp/claude
mkdir -p ~/.claude/skills
cp -r /tmp/claude/skills/term-interrogation ~/.claude/skills/term-interrogation

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Term interrogation

A reader who nods along and learns nothing has been failed by the writing, not by their own
attention. The words that cause it are rarely the difficult ones. Difficult words announce
themselves and get looked up. The dangerous words are the ordinary-sounding ones that carry
a whole concept quietly inside them.

"The company built a moat around its core workflow." Every word there is common English.
The sentence is still unreadable, because "moat" is standing in for an argument about why
competitors cannot take these customers away, and that argument was never made.

This skill finds those words and makes them explain themselves.

## What this skill is for, and what it is not

It runs **after** a draft exists. It is an audit and repair pass over finished prose, not a
drafting style.

It is the recursive layer above `reader-first-prose`. That skill introduces a term before
leaning on it, once. This one keeps going: it reads its own replacement text and asks
whether that text introduced something new the reader also cannot follow.

Hand off rather than duplicate:

- `reader-first-prose` for the surrounding sentence work, metaphor grounding, and the
  honesty rules.
- `ladder-of-abstraction` when a passage is abstract all the way through. That is an
  altitude problem, not a vocabulary problem. See also the density case below, which looks
  similar and is not.
- `readability-check` for scoring afterwards.
Read the full skill on GitHub

Details

Skill name
term-interrogation
Path
skills/term-interrogation/SKILL.md
Repo updated
1 September 2026

FAQ

What does the Term Interrogation skill do?

Walks a finished document line by line, finds every word and phrase standing in for a concept, and breaks each one down until a reader with no background can follow it. Targets the assumed-knowledge phrase, the kind that sounds ordinary while hiding everything that matters ("moat", "flywheel", "product-market fit", "at scale"), not merely the rare word. Explains each term where it is used, then re-reads its own explanation and unpacks any new term that explanation introduced, repeating until every word bottoms out in ordinary language. Produces a term ledger recording what was flagged, how it

How do I install the Term Interrogation skill?

Claude Code plugin: /plugin marketplace add lyndonkl/claude. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Term Interrogation popular?

It lives in lyndonkl/claude, which has 200 GitHub stars and 25 forks.

Related skills

Abstraction Concrete Examples

200

lyndonkl/claude

Builds structured abstraction ladders that translate high-level principles into concrete, actionable examples across 3-5 levels. Bridges communication gaps, reveals hidden assumptions, and tests whether abstract ideas work in practice. Use when explaining concepts at different expertise levels, moving between abstract principles and concrete implementation, identifying edge cases by testing ideas against scenarios, designing layered documentation, decomposing complex problems into actionable steps, or bridging strategy-execution gaps.

Testing & QA25

Academic Letter Architect

200

lyndonkl/claude

Guides the creation of evidence-based academic recommendation letters, reference letters, and award nominations that combine concrete examples, meaningful comparisons, and genuine enthusiasm. Use when writing recommendation letters for students, postdocs, or colleagues, or when user mentions recommendation letter, reference, nomination, letter of support, endorsement, or needs help with strong advocacy and comparative statements.

Research & Science25

Adr Architecture

200

lyndonkl/claude

Documents significant architectural and technical decisions with full context, alternatives considered, trade-offs analyzed, and consequences understood. Creates a decision trail that helps teams understand why decisions were made. Use when choosing between technology options, making infrastructure decisions, establishing standards, migrating systems, or when user mentions ADR, architecture decision, technical decision record, or decision documentation.

Software Development25

Update Topic Ledger

200

lyndonkl/claude

Maintains substacker shared-context/topic-ledger.md as an append-and-update index of all topics in the corpus. Each topic row tracks seed/draft/published counts, last-touched date, top-3 seed ids by density, and a hot/warm/cold temperature indicator. Use after any seed is created, promoted to draft, published, or killed. Trigger keywords — ledger, topic index, update index, topic ledger, hot/cold topics.

Other25

Tag By Topic

200

lyndonkl/claude

Assigns 1-4 topic tags to a seed body from the controlled vocabulary in substacker shared-context/topic-ledger.md. Prevents tag sprawl at small-corpus scale by requiring existing-tag match or logged addition. Uses keyword + title match; logs near-miss candidates to pending-tags. Use after format normalization and before dedupe. Trigger keywords — tag, topics, categorize, classify, taxonomy, controlled vocabulary, topic ledger.

Other25

Update Watchlist

200

lyndonkl/claude

Proposes adds and removes to the Trend Scout watchlist based on consecutive-failure sources, repeated-reference external authors, and user-added feedback markers. Emits a proposed diff at ops/trend-scout/watchlist-proposed-diff.md for user review. On explicit approval, applies the diff. Monthly cadence. Trigger keywords — watchlist update, add source, remove source, watchlist review, monthly review, source pruning.

Other25

Browse the most popular Claude skills, all other skills, or write your own with the skills generator.