New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Elimination Research

by glebis in glebis/claude-skills

This skill should be used for elimination-style research where the user wants to choose from a shortlist of products, tools, services, vendors, or other options using explicit criteria, numeric…

MITAuto-check passed

Install Elimination Research

skills CLI
$ npx skills add glebis/claude-skills --skill elimination-research -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install glebis/claude-skills elimination-research --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/glebis/claude-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/elimination-research .claude/skills/elimination-research && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
elimination-research
GitHub stars
391
Token cost
~1.6k tokens
SKILL.md length
660 words
Files
14 (incl. scripts, references, assets)
Skills in repo
92
Repo updated
First seen
Licence
MIT

At a glance

This skill should be used for elimination-style research where the user wants to choose from a shortlist of products, tools, services, vendors, or other options using explicit criteria, numeric…

  • Works in 7 steps: Read references/workflow.md for the full… → Ask the intake questions before… → Gather candidate, source, price, spec,… → …
  • The user asks to compare options
  • SKILL.md covers Purpose, Workflow, Intake Questions and Output Contract, plus 4 more sections
  • Runs Python scripts from its folder; calls python3; needs GOOGLE_CUSTOM_SEARCH_JSON_API_KEY and GOOGLE_CUSTOM_SEARCH_API_KEY

What it does

Elimination Research is an agent skill from glebis/claude-skills. This skill should be used for elimination-style research where the user wants to choose from a shortlist of products, tools, services, vendors, or other options using explicit criteria, numeric evidence, tournament-style comparison, source/domain classification, image-supported consumer reports, raw data tables, and ownership-cost estimates for replaceable parts. Use this skill whenever the user asks to compare options, buy something, shortlist candidates, rank alternatives, generate a "don't make me think"…

Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 21 other files, including scripts, reference files and assets (for example `assets/examples/consumer_goods_dataset.example.json`, `assets/examples/domain_registry.example.json` and `references/dataset-schema.md`).

The repository describes itself as: Collection of Claude Code skills for enhanced AI workflows. The licence is MIT.

When your agent uses it

  • The user asks to compare options
  • Shortlist candidates
  • Rank alternatives
  • Generate a dont make me think report

Example prompts

  • “t make me think”
  • “/elimination-research”

Requirements

  • Python 3
  • A credential in GOOGLE_CUSTOM_SEARCH_JSON_API_KEY
  • A credential in GOOGLE_CUSTOM_SEARCH_API_KEY

Workflow steps

7 steps, taken from the first numbered list in SKILL.md.

  1. Read references/workflow.md for the full operating procedure.
  2. Ask the intake questions before researching. Prefer cenno popup questions when available. Use closed choices and include a free-text…
  3. Gather candidate, source, price, spec, replacement-part, image, and evidence data.
  4. Save all collected data into a dataset JSON matching references/dataset-schema.md.
  5. Run scripts/generate_elimination_report.py to generate reports.
  6. Verify the quick report and full report in a browser.
  7. Preserve raw data and numeric tables; do not hide or discard evidence just because the quick report is simplified.

What it can do on your machine

Read from SKILL.md and the folder at commit 3b88261. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 8 files in scripts/ (Python, from the files we listed), which the agent can run.

    Shell commands in SKILL.md call:

    • python3

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • GOOGLE_CUSTOM_SEARCH_JSON_API_KEY
    • GOOGLE_CUSTOM_SEARCH_API_KEY

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Elimination Research loads about 1.6k tokens when it runs, and up to ~3.7k if it reads all its reference files. Until then it costs about 149 tokens; SKILL.md has 660 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~149
When it runs · the whole SKILL.md, loaded when a task matches
~1.6k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~3.7k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from glebis/claude-skills at commit 3b88261, republished under its MIT licence (© glebis). 660 words, ~1,621 tokens.

Download SKILL.mdSave it as .claude/skills/elimination-research/SKILL.md (or your agent's skills folder). This skill also uses 13 other files; get the full folder from GitHub.
name
elimination-research
description
This skill should be used for elimination-style research where the user wants to choose from a shortlist of products, tools, services, vendors, or other options using explicit criteria, numeric evidence, tournament-style comparison, source/domain classification, image-supported consumer reports, raw data tables, and ownership-cost estimates for replaceable parts. Use this skill whenever the user asks to compare options, buy something, shortlist candidates, rank alternatives, generate a "don't make me think" report, or produce a full audit report with raw numeric data.

Elimination Research

Purpose

Generate a reproducible elimination-research package: a shortlist dataset, numeric scoring model, quick consumer report, full audit report, raw data JSON, source/domain audit, purchase/info links, contextual images, and ownership-cost estimates.

Use this skill to turn fuzzy "which one should I choose?" requests into a clean decision workflow with explicit criteria and inspectable data.

Workflow

Follow this sequence for new comparisons:

  1. Read references/workflow.md for the full operating procedure.
  2. Ask the intake questions before researching. Prefer cenno popup questions when available. Use closed choices and include a free-text comment field.
  3. Gather candidate, source, price, spec, replacement-part, image, and evidence data.
  4. Save all collected data into a dataset JSON matching references/dataset-schema.md.
  5. Run scripts/generate_elimination_report.py to generate reports.
  6. Verify the quick report and full report in a browser.
  7. Preserve raw data and numeric tables; do not hide or discard evidence just because the quick report is simplified.

Intake Questions

Ask these at the start of a new comparison, not inside the final report:

  • What matters most: overall quality, lowest price, sensitive-skin/user-fit, low maintenance, or travel/portability?
  • What is the hard limit: budget ceiling, must-have features, excluded brands, or purchase country?
  • How much evidence is needed: quick consumer view, full audit report, or both?
  • Which source types are allowed: manufacturer, retailer, price aggregator, expert review, forum, or all with flags?

Always include a comment field for constraints that do not fit the closed choices.

Output Contract

Produce these files in the chosen output directory:

  • quick_report.html — consumer-facing "don't make me think" report with cards/table switch, images in context, rounded prices, links, and visible ownership summaries.
  • report.html — full audit report with task, criteria, scoring, raw numeric data, source/domain tables, tournament, and embedded JSON.
  • report.md — markdown version of the full audit report.
  • final_report.json — normalized report payload.
  • raw_research_data.json — collected dataset before rendering.
  • image_search_results.json — cached Google image-search output when image refresh is used.

The quick report should keep numeric detail behind expandable evidence links, but the full report must expose all numeric data as tables.

Generator

Run the bundled generator from the skill directory:

bash
python3 scripts/generate_elimination_report.py \
  --dataset assets/examples/consumer_goods_dataset.example.json \
  --output-dir /tmp/elimination-report \
  --max-price-eur 200

Common options:

bash
--dataset PATH             Structured shortlist dataset JSON
--output-dir PATH          Output directory
--max-price-eur NUMBER     Purchase-price ceiling override
--price-limit-basis FIELD  Usually device_price_eur or three_year_cost_eur
--question TEXT            Override report task question
--market TEXT              Purchase market/country
--currency TEXT            Currency label
--domain-registry PATH     Optional domain registry JSON
--refresh-images           Refresh Google Custom Search image data
--image-results NUMBER     Image results per candidate when refreshing

For Google Images, load keys only from environment variables or SOPS-encrypted dotenv files. Never commit plaintext keys. The image helper checks GOOGLE_CUSTOM_SEARCH_JSON_API_KEY, GOOGLE_CUSTOM_SEARCH_API_KEY, GOOGLE_CUSTOM_SEARCH_CX, and GOOGLE_IMAGE_SEARCH_ENV_FILE.

Show full SKILL.md (291 more words)Show less

Data Rules

Read references/dataset-schema.md before creating or editing the dataset.

Key requirements:

  • Use stable candidate IDs.
  • Keep every numeric observation as a number, not prose.
  • Store prices in explicit currency fields such as device_price_eur.
  • For replaceable parts, include rough replacement_unit_price_eur, replacement_quantity_3y, replacement_interval_months, and replacement_part_name.
  • Include item_links or source references so each item has 1-3 purchase/info links.
  • Classify source domains by role and trust tier. Manufacturer/spec, retailer, price aggregator, expert review, forum, and affiliate sources should remain distinct.
  • Store caveats explicitly. Do not silently remove weak assumptions.

Report Design Rules

For consumer reports:

  • Let product images illustrate the options in context; do not create a standalone image-source section.
  • Keep image blocks on a light neutral background.
  • Hide image host/score/dimensions from the consumer report; keep them in JSON.
  • Round visible prices in the quick report.
  • Avoid eyebrow labels.
  • Provide a card/table switch where cards and table are mutually exclusive views.
  • Show ownership cost directly on each option card/table row when replaceable parts exist.
  • Keep source links as short action chips: price, official, review, parts, or head price.

For audit reports:

  • Start with the task and criteria so the report is understandable without conversation context.
  • Show all numeric data as tables.
  • Include the full candidate dataset, domain/source audit, score formula, tournament rows, sensitivity rankings, and caveats.

Verification

Before handing off:

  • Run the generator on the dataset.
  • Validate JSON with python3 -m json.tool.
  • Open quick_report.html and verify the card/table switch replaces the options view rather than stacking table below cards.
  • Check mobile width for text overflow, low contrast, and touch targets under 44px.
  • Confirm report.html includes raw numeric columns for device price, replacement allowance, part unit price, interval, quantity, and three-year cost.
  • Commit and push changes when editing the skills repo or generated report project.

© glebis, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 13 other files (scripts, references, assets) in elimination-research of glebis/claude-skills.

  • SKILL.md
  • assets/examples/consumer_goods_dataset.example.json
  • assets/examples/domain_registry.example.json
  • references/dataset-schema.md
  • references/workflow.md
  • scripts/elimination_research_lib/application/__init__.py
  • scripts/elimination_research_lib/application/report_generator.py
  • scripts/elimination_research_lib/domain/__init__.py
  • scripts/elimination_research_lib/domain/domain_classifier.py
  • scripts/elimination_research_lib/domain/evidence_normalizer.py
  • scripts/elimination_research_lib/domain/scoring_engine.py
  • scripts/elimination_research_lib/infrastructure/__init__.py
  • scripts/elimination_research_lib/infrastructure/google_image_search.py
  • … and 1 more

Open the folder on GitHubat commit 3b88261

Compare with similar skills

Elimination Research next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Elimination Research compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Elimination Research this skillglebis/claude-skills391—~1.6kAutomated safety check: PassMIT
Eliminate Visual Cluttergnurio/refactoring-ui-plugin443—~1kAutomated safety check: PassCustom licence
Routing Subtour EliminationRaidriar7170/hermes-skilleval1251 repos~2.2kAutomated safety check: PassMIT
Dead Code EliminatorArabelaTso/Skills-4-SE253—~3.3kAutomated safety check: PassApache-2.0
Swift Actor Persistenceaffaan-m/ECC276k4 repos~1.2kAutomated safety check: PassMIT
Render Blockingthedaviddias/Front-End-Checklist74k—~430Automated safety check: PassMIT

Similar skills

  • Eliminate Visual Clutter

    gnurio/refactoring-ui-plugin

    Remove unnecessary borders, backgrounds, shadows, decorations

    443 GitHub stars~1k tokensUpdated 5 mo ago
    DevelopmentAuto-check passed

  • Routing Subtour Elimination

    Raidriar7170/hermes-skilleval

    Subtour-elimination methods for TSP, VRP, pickup/dropoff routing, and routing MIPs with binary arc variables.

    125 GitHub starsUsed in 1 repo~2.2k tokens
    Data & AnalyticsAuto-check passed

  • Dead Code Eliminator

    ArabelaTso/Skills-4-SE

    Identify and analyze unused or redundant code including unused functions/methods, unused variables/imports, unreachable code, and redundant conditions.

    253 GitHub stars~3.3k tokensUpdated 1 mo ago
    DevelopmentAuto-check passed

  • Swift Actor Persistence

    affaan-m/ECC

    Thread-safe data persistence in Swift using actors — in-memory cache with file-backed storage, eliminating data races by design.

    276k GitHub starsUsed in 4 repos~1.2k tokens
    MobileAuto-check passed

  • Render Blocking

    thedaviddias/Front-End-Checklist

    A skill your agent uses when auditing slow page loads, heavy assets, or rendering delays related to Eliminate render-blocking resources.

    74k GitHub stars~430 tokensUpdated 4 days ago
    Frontend & DesignAuto-check passed

  • Anti Sycophancy

    sickn33/agentic-awesome-skills

    Eliminate sycophantic agreement patterns in AI responses. An agent skill from sickn33/agentic-awesome-skills.

    47k GitHub starsUsed in 1 repo~370 tokens
    Auto-check passed

More from glebis/claude-skills

All 92 skills in this repo

  • PII Annotation and Agreement Scorer

    glebis/claude-skills

    Runs a human-first workflow for labeling PII spans in a transcript, then scores inter-annotator agreement and drafts an adjudicated gold set.

    391 GitHub stars~1.3k tokensUpdated 2 days ago
    Auto-check passed

  • Non-Destructive Chrome Automation

    glebis/claude-skills

    Automates a dedicated, logged-in Chrome instance per profile without ever closing the user's own open tabs or browser windows.

    391 GitHub stars~973 tokensUpdated 2 days ago
    Auto-check passed

  • Deep Research

    glebis/claude-skills

    This skill should be used when conducting comprehensive research on any topic using the OpenAI Deep Research API.

    391 GitHub stars~2.6k tokensUpdated 2 days ago
    Auto-check: notes

  • Narrated HTML Presentations

    glebis/claude-skills

    Generates a self-contained HTML presentation with article and slides modes, ElevenLabs voiceover narration and optional GPT Image 2 illustrations.

    391 GitHub stars~2.3k tokensUpdated 2 days ago
    Auto-check: notes

  • Synthetic Coaching Session Generator

    glebis/claude-skills

    Writes fictional but realistic coaching or therapy session transcripts for evals, demos and few-shot examples, in several modalities and export formats.

    391 GitHub stars~2.9k tokensUpdated 2 days ago
    Auto-check passed

  • The Goal Automation Diagnostic

    glebis/claude-skills

    Walks through Goldratt's Five Focusing Steps to find the real bottleneck in your work, then recommends one automation aimed at it and a list of what not to automate.

    391 GitHub stars~2k tokensUpdated 2 days ago
    Auto-check passed

Questions about Elimination Research

What does Elimination Research do?

This skill should be used for elimination-style research where the user wants to choose from a shortlist of products, tools, services, vendors, or other options using explicit criteria, numeric…. Elimination Research is an agent skill from glebis/claude-skills. This skill should be used for elimination-style research where the user wants to choose from a shortlist of products, tools, services, vendors, or other options using explicit criteria, numeric evidence, tournament-style comparison, source/domain classification, image-supported consumer reports, raw data tables, and ownership-cost estimates for replaceable parts.

When should I use Elimination Research?

Elimination Research fits situations like: the user asks to compare options; shortlist candidates; rank alternatives; generate a dont make me think report.

How do I install Elimination Research in Claude Code?

Run `npx skills add glebis/claude-skills --skill elimination-research -a claude-code`. Or copy the skill folder (elimination-research in glebis/claude-skills) into .claude/skills/elimination-research in your project. Claude Code loads it when a task matches its description.

How do I install Elimination Research in Codex?

Run `npx skills add glebis/claude-skills --skill elimination-research -a codex`. Or copy the skill folder (elimination-research in glebis/claude-skills) into .agents/skills/elimination-research in your project. Codex loads it when a task matches its description.

Can I use Elimination Research in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add glebis/claude-skills --skill elimination-research -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/elimination-research, .gemini/skills/elimination-research, .github/skills/elimination-research and .opencode/skills/elimination-research in your project.

What does Elimination Research need to run?

Going by SKILL.md and its folder, Elimination Research needs Python for the scripts in its folder, the command-line tools its instructions call (python3) and credentials named GOOGLE_CUSTOM_SEARCH_JSON_API_KEY and GOOGLE_CUSTOM_SEARCH_API_KEY. Our summary lists: Python 3; A credential in GOOGLE_CUSTOM_SEARCH_JSON_API_KEY; A credential in GOOGLE_CUSTOM_SEARCH_API_KEY.

Does Elimination Research access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Elimination Research safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Elimination Research use?

Elimination Research is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Elimination Research use?

About 1.6k tokens (SKILL.md is roughly 6.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 2.1k tokens, read only when the agent opens those files.

What are the alternatives to Elimination Research?

Skills that share tags, products or a category with Elimination Research: Eliminate Visual Clutter (gnurio/refactoring-ui-plugin, 443 stars), Routing Subtour Elimination (Raidriar7170/hermes-skilleval, 125 stars), Dead Code Eliminator (ArabelaTso/Skills-4-SE, 253 stars) and Swift Actor Persistence (affaan-m/ECC, 276k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Elimination Research?

glebis (a GitHub user) maintains it in glebis/claude-skills, which has 391 GitHub stars. The repository holds 92 skills in this directory. The repository was last updated on October 8, 2026.

Source: glebis/claude-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.