Hedge Detector
Classifies every hedge in a substacker draft as either a precision hedge (keep — "n=1 may not replicate", "I do not know") or an epistemic-weakness hedge (flag — "I think", "perhaps", "arguably", "it could be argued"). Only flags weakness hedges; suggests either a commit (remove hedge, take position) or a specific hedge (name the uncertainty). Use when a draft feels wishy-washy or when a cluster of modal verbs appears. Trigger keywords — hedging, I think, perhaps, arguably, uncertainty, weak claim, wishy-washy.
Install
/plugin marketplace add lyndonkl/claudeThe repo is a Claude Code plugin marketplace. Run /plugin afterwards to pick the plugin that includes this skill.
npx skills add lyndonkl/claude --skill hedge-detectorgit clone --depth 1 https://github.com/lyndonkl/claude.git /tmp/claude
mkdir -p ~/.claude/skills
cp -r /tmp/claude/skills/hedge-detector ~/.claude/skills/hedge-detectorPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Hedge Detector ## Table of Contents - [Precision vs weakness](#precision-vs-weakness) - [Workflow](#workflow) - [Worked example](#worked-example) - [Guardrails](#guardrails) **Related skills:** Called by the Editor in the voice pass. Complements `voice-check` (which flags "I think" as a don't-list phrase when used as primary hedge). This skill does the finer classification. ## Precision vs weakness **Precision hedge (KEEP)**: scope-naming, sample-size-caveat, specific-uncertainty. - "I do not know" (full sentence) — writer's signature. - "I am not claiming…" — explicit scope. - "On my 3B-param run…" — sample caveat. - "n=1 may not replicate." - "I have only tested this on 3 teams." **Epistemic-weakness hedge (FLAG)**: softens without adding information. - "I think" (when followed by a claim). - "Perhaps" (standalone). - "Arguably" — deniability. - "It could be argued" — auto-deniability. - "Somewhat" — weakening adverb. - "Seems" (when no sensing is happening). - "It seems clear that" — worst-of-both-worlds. ## Workflow ``` For each hedge in the draft: - [ ] Step 1: Detect hedge markers (modal verbs + phrase list above) - [ ] Step 2: Classify as precision or weakness - [ ] Step 3: For weakness, suggest a commit OR a specific hedge (both, as 2 rewrite options) - [ ] Step 4: For precision, leave alone (note in the "calibrated hedges kept" count) - [ ] Step 5: Emit the hedge audit with both lists ``` ### Step 2: Classifier
Details
- Skill name
hedge-detector- Repository
- lyndonkl/claude
- Path
skills/hedge-detector/SKILL.md- Repo updated
- 1 September 2026
FAQ
What does the Hedge Detector skill do?
Classifies every hedge in a substacker draft as either a precision hedge (keep — "n=1 may not replicate", "I do not know") or an epistemic-weakness hedge (flag — "I think", "perhaps", "arguably", "it could be argued"). Only flags weakness hedges; suggests either a commit (remove hedge, take position) or a specific hedge (name the uncertainty). Use when a draft feels wishy-washy or when a cluster of modal verbs appears. Trigger keywords — hedging, I think, perhaps, arguably, uncertainty, weak claim, wishy-washy.
How do I install the Hedge Detector 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 Hedge Detector popular?
It lives in lyndonkl/claude, which has 200 GitHub stars and 25 forks.
Related skills
Abstraction Concrete Examples
200lyndonkl/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.
Academic Letter Architect
200lyndonkl/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.
Adr Architecture
200lyndonkl/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.
Hello Skill Inline
117Peiiii/skild
Minimal bundled skill (inline dependency) for kitchen-sink skillset.
Gdpr Compliance
213TerminalSkills/skills
Automate GDPR and privacy compliance for web applications. Use when someone asks to "make the app GDPR compliant", "add cookie consent", "handle data deletion requests", "audit PII", "data subject access request", or "privacy policy generator". Covers PII auditing, consent management, data subject request endpoints, retention policies, and privacy policy generation.
Matchup Win Probability Sim
200lyndonkl/claude
Computes P(we win at least K of N categories) for a head-to-head categorical matchup via Monte-Carlo simulation or Poisson-binomial approximation. Domain-neutral — works for any fantasy sport with H2H Categories scoring (MLB, NBA, NHL) or any zero-sum per-category competition. Use when you need matchup_win_probability, per_cat_win_probability, expected_cats_won, or variance_estimate; or when user mentions "matchup win probability", "head to head simulation", "Monte Carlo matchup", "Poisson binomial matchup", "P win 6 of 10", "category matchup simulation", or "weekly win probability".
Browse the most popular Claude skills, all other skills, or write your own with the skills generator.