New: 97,000+ 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

Decision Matrix

by iflytek in iflytek/skillhub

Compares options with pros and cons, weighted scoring, pre-mortems, opportunity costs and ICE prioritization, labeling assumptions instead of inventing numbers.

MITAuto-check passedProduct & Project Management

Install Decision Matrix

skills CLI
$ npx skills add iflytek/skillhub --skill decision-matrix -a claude-code

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

GitHub CLI
$ gh skill install iflytek/skillhub decision-matrix --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/iflytek/skillhub.git skills-src && mkdir -p .claude/skills && cp -r skills-src/builtin-skills/skills/decision-matrix .claude/skills/decision-matrix && 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
decision-matrix
GitHub stars
5.2k
Token cost
~2.3k tokens
SKILL.md length
1,184 words
Files
3
Skills in repo
29
Repo updated
First seen
Licence
MIT

At a glance

Compares options with pros and cons, weighted scoring, pre-mortems, opportunity costs and ICE prioritization, labeling assumptions instead of inventing numbers.

  • Works in 12 steps: Classic Pros & Cons (Benjamin Franklin… → Weighted Decision Matrix (Pugh Matrix) → Pre-Mortem → …
  • Choosing between job offers, tools or vendors against weighted criteria
  • SKILL.md covers What It Does, Frameworks Available, Trigger Phrases and Step-by-Step Instructions, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

The skill applies a transparent framework to a choice so trade-offs show up and the facts that could change the answer are named. Every score is treated as an expression of your stated preferences, not objective truth, estimates are labeled, and missing costs, probabilities or constraints are never made up. For medical, legal, financial or safety-critical decisions it only organizes questions and trade-offs and points you to a qualified professional.

The frameworks include a weighted pros and cons list, scored from +1 to +5 and -1 to -5, and a Pugh-style matrix where criteria get weights of 1 to 5, options are scored 1 to 10 and the products are summed, with the top total treated as a starting point to test against assumptions, uncertainty, must-haves and reversibility. A pre-mortem imagines the decision failing after 12 months and works backward to failure modes and fixes. Opportunity cost and ICE ranking are also listed.

When your agent uses it

  • Choosing between job offers, tools or vendors against weighted criteria
  • Stress-testing a high-stakes plan with a pre-mortem
  • Ranking a list of ideas or features with ICE scoring
  • Surfacing hidden assumptions before committing to a decision

Example prompts

  • “Compare these three laptops on price, weight and battery life with a weighted matrix.”
  • “Run a pre-mortem on our plan to move billing to a new payment provider.”
  • “Help me rank these five feature ideas using ICE.”
  • “Give me a pros and cons list for moving to a new city, weighted by importance.”

Workflow steps

12 steps, taken from the step headings in SKILL.md.

  1. Classic Pros & Cons (Benjamin Franklin Method)
  2. Weighted Decision Matrix (Pugh Matrix)
  3. Pre-Mortem
  4. Opportunity Cost Frame
  5. ICE Score (Impact, Confidence, Ease)
  6. The 10/10/10 Rule
  7. Define the Decision Clearly
  8. Identify the Decision Type
  9. Collect the Data
  10. Apply the Framework
  11. Check for Bias
  12. Decide and Commit

What it can do on your machine

Read from SKILL.md and the folder at commit 7352597. 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

    No scripts in the folder and no shell commands in SKILL.md.

    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 no API keys, tokens, secrets or passwords.

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

Context cost

Decision Matrix loads about 2.3k tokens when it runs. Until then it costs about 54 tokens; SKILL.md has 1,184 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~54
When it runs · the whole SKILL.md, loaded when a task matches
~2.3k

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); files beside SKILL.md are not scanned.

SKILL.md

The full file from iflytek/skillhub at commit 7352597, republished under its MIT licence (© iflytek). 1,184 words, ~2,332 tokens.

Download SKILL.mdSave it as .claude/skills/decision-matrix/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
decision-matrix
description
Compare options with weighted scoring, pros and cons, pre-mortems, opportunity costs, and ICE prioritization. Use when a user wants to reason through a choice, expose assumptions, or rank alternatives.
version
1.0.0
license
MIT

Decision Matrix

What It Does

Apply a transparent framework to compare options, expose trade-offs, and identify what information could change a choice.

Treat every score as a transparent expression of the user's stated preferences, not as objective truth. Clearly label estimates and assumptions, and never invent missing costs, probabilities, constraints, or preferences.

For medical, legal, financial, safety-critical, or other high-impact decisions, use the frameworks only to organize questions and trade-offs. Do not present the highest score as professional advice or a final decision. Encourage the user to verify material facts and consult an appropriately qualified professional.

Frameworks Available

1. Classic Pros & Cons (Benjamin Franklin Method)

Best for: Quick decisions with low-to-moderate stakes

StepAction
1Draw two columns: PROS and CONS
2List every reason for and against — no filtering
3Weigh each item (not all pros are equal). Assign +1 to +5 for pros, -1 to -5 for cons
4Sum the scores, then inspect the strongest items, uncertainty, and any non-negotiables

Guardrail: Pros/cons alone miss hidden assumptions. Always follow with: "What am I not considering?"

2. Weighted Decision Matrix (Pugh Matrix)

Best for: Comparing multiple options against multiple criteria

| Criteria               | Weight (1-5) | Option A | Option B | Option C |
|------------------------|-------------|----------|----------|----------|
| Cost                   |      4      |   8/10   |   6/10   |   9/10   |
| Time to Market         |      3      |   7/10   |   9/10   |   5/10   |
| Strategic Fit          |      5      |   9/10   |   4/10   |   7/10   |
| Team Capacity          |      2      |   6/10   |   8/10   |   4/10   |
| **Weighted Total**     |             |   110    |   87     |   94     |

Steps:

  1. List all viable options (columns in the example)
  2. Define criteria that matter (rows in the example)
  3. Assign a weight (1-5) to each criterion based on importance
  4. Score each option per criterion (1-10)
  5. Multiply score × weight, sum across criteria
  6. Use the highest total as a starting point, then inspect assumptions, uncertainty, must-haves, and reversibility
3. Pre-Mortem

Best for: High-stakes decisions where risk mitigation is critical

"It's 12 months from now and our decision has failed spectacularly. How did it happen?"

StepTechnique
1Assume the decision was made and led to disaster
2Fast-forward and write the "post-mortem" — what went wrong?
3Generate 5-10 plausible failure modes
4For each failure, ask: "What could prevent this?"
5Incorporate those safeguards into the decision

Use this to surface plausible failure modes that an ordinary comparison may miss. Do not treat an imagined failure as a prediction.

4. Opportunity Cost Frame

Best for: Deciding between two good options (where saying yes to A means saying no to B)

FrameQuestion
Cost of yesWhat do I give up by choosing this?
Cost of noWhat do I give up by not choosing this?
Regret testIf I look back in 5 years, which "no" would I regret more?
Opportunity comparisonIf Option A didn't exist, would I choose Option B?

Use the answers as discussion prompts, not an automatic selection rule.

5. ICE Score (Impact, Confidence, Ease)

Best for: Prioritizing many options quickly (features, ideas, experiments)

CriterionScaleQuestion
Impact1-10How significant will the result be if successful?
Confidence1-10How sure are we about the expected outcome?
Ease1-10How easy/simple is this to execute?

Formula: ICE Score = Impact × Confidence × Ease

Sort by score to create a shortlist. Check dependencies, risk, and confidence before selecting work, and re-score when new data emerges.

6. The 10/10/10 Rule

Best for: Emotional or high-stakes personal decisions

Time HorizonQuestion
10 minutesHow will I feel about this decision in 10 minutes?
10 monthsHow will I feel about it in 10 months?
10 yearsHow will I feel about it in 10 years?

Purpose: Shifts perspective from short-term emotion to long-term impact. If the horizons conflict, explain the conflict instead of automatically favoring one horizon.

Trigger Phrases

PhraseAction
"Help me decide between..."Starts a structured comparison of options
"Pros and cons of..."Generates a weighted pros/cons table
"Should I [X] or [Y]?"Runs a decision matrix or opportunity cost analysis
"What am I not considering?"Surfaces blind spots and hidden assumptions
"Run a pre-mortem on..."Scenarios worst-case outcomes to de-risk the decision
"Prioritize these for me..."Uses ICE or weighted scoring to rank options
"Help me think this through..."Combines frameworks layered for clarity

Step-by-Step Instructions

Step 1: Define the Decision Clearly

A fuzzy question gets a fuzzy answer. Be specific:

  • ❌ "Should I change jobs?"
  • ✅ "Should I accept the offer at Company X ($120k, hybrid, startup) or stay at my current role ($110k, remote, corporate)?"
Show full SKILL.md (494 more words)Show less
Step 2: Identify the Decision Type
Decision TypeRecommended Framework
Low stakes, 2 optionsPros & Cons (weighted)
Multiple options, many criteriaWeighted Decision Matrix
High risk, irreversiblePre-mortem
Scarcity (time/money focus)Opportunity Cost Frame
Prioritizing a long listICE Score
Emotional/personal10/10/10 Rule
Step 3: Collect the Data

Gather:

  • All realistic options (at least 2, rarely more than 5)
  • All relevant criteria
  • Objective data where possible (numbers, dates, facts)
  • Subjective preferences (gut feel, values, identity)

Ask for critical missing information when it could change the outcome. Otherwise, proceed with clearly labeled assumptions and show how changing them affects the result.

Step 4: Apply the Framework

Run the framework step by step. Document scores, weights, and reasoning.

Step 5: Check for Bias
BiasMitigation
Confirmation biasActively list reasons against your preferred option first
Recency biasConsider decisions from 6+ months ago — does this feel different?
Sunk cost"If I had no prior investment in this, would I still choose it?"
Status quo bias"If this weren't the default, would I pick it?"
Step 6: Decide and Commit
  • If the evidence strongly favors an option, explain why and identify the remaining uncertainty.
  • If scores are close, compare reversibility, information gaps, and the cost of a small experiment. Do not impose an arbitrary 10% threshold.
  • Let the user make the final choice, especially for consequential decisions.
  • Offer to write down the decision and reasoning; do not persist it unless the user asks.
Step 7: Review the Outcome

After the decision plays out, revisit your framework. Did your weights reflect reality? Did you miss a criterion? Retrospect improves future decisions.

Examples

Example 1: Freelancer Deciding Between Two Clients

Input: "Should I take Client A ($5k, urgent, boring) or Client B ($3k, flexible, exciting project)?"

Process: Weighted Decision Matrix

CriteriaWeightClient AClient B
Income49 (36)5 (20)
Enjoyment33 (9)9 (27)
Time Pressure23 (6)9 (18)
Portfolio Value44 (16)9 (36)
Total67101

Result: Under these stated weights and scores, Client B leads because portfolio value and enjoyment outweigh the income gap. Verify workload, payment risk, and any non-negotiables before choosing.

Example 2: Solopreneur — "Should I Build Feature X?"

Input: "Should I prioritize building a mobile app or improving onboarding?"

Process: ICE + Pre-mortem

ICE:

  • Mobile App: Impact 8, Confidence 4, Ease 2 → ICE = 64
  • Onboarding: Impact 6, Confidence 8, Ease 8 → ICE = 384

Pre-mortem on mobile app decision: "We built the app but no one used it because onboarding was broken." → Clear signal to fix onboarding first.

Quality checks

  • Show the arithmetic and retain the user's original units, weights, and scores.
  • Identify must-haves before ranking options.
  • Label estimates and distinguish evidence from preferences.
  • Test whether a modest change in an uncertain weight or score changes the result.
  • For close results, compare reversibility and the value of gathering more information.
  • Leave consequential choices to the user; do not persist or act on a decision without a separate request.

© iflytek, 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 2 other files in builtin-skills/skills/decision-matrix of iflytek/skillhub.

  • SKILL.md
  • LICENSE.txt
  • NOTICE.md

Open the folder on GitHubat commit 7352597

Compare with similar skills

Decision Matrix 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.

Decision Matrix compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Decision Matrix this skilliflytek/skillhub5.2k—~2.3kAutomated safety check: PassMIT
Strategy Planningandreaskelm/pm-brain234—~1.2kAutomated safety check: PassCustom licence
Feature Investment Advisordeanpeters/Product-Manager-Skills7.2k1 repos~5.6kAutomated safety check: PassCustom licence
CEO Plan Reviewgarrytan/gstack136k—~20kAutomated safety check: NotesMIT
Research Financeborghei/Claude-Skills874—~3.4kAutomated safety check: PassMIT
Outcome Trackermohitagw15856/pm-claude-skills1.4k—~1.6kAutomated safety check: PassMIT

Similar skills

  • Strategy Planning

    andreaskelm/pm-brain

    Support strategy, OKR, roadmap, and prioritization work using PM Brain’s strategy frameworks.

    234 GitHub stars~1.2k tokensUpdated 3 mo ago
    Product & Project ManagementAuto-check passed

  • Feature Investment Advisor

    deanpeters/Product-Manager-Skills

    Evaluates whether a feature deserves investment by weighing revenue connection, cost structure, ROI and strategic value, then gives a build or don't-build recommendation.

    7.2k GitHub starsUsed in 1 repo~5.6k tokens
    Product & Project ManagementAuto-check passed

  • CEO Plan Review

    garrytan/gstack

    Reviews a plan from a founder's point of view, questioning premises and scope in one of four modes that run from expansion to reduction.

    136k GitHub stars~20k tokensUpdated today
    Product & Project ManagementAuto-check: notes

  • Research Finance

    borghei/Claude-Skills

    Research budgeting and funding operations — study budget construction, cost per participant and per insight, burn against milestones, and portfolio prioritisation by decision value.

    874 GitHub stars~3.4k tokensUpdated today
    Product & Project ManagementAuto-check passed

  • Outcome Tracker

    mohitagw15856/pm-claude-skills

    Record the testable predictions inside a decision, then score them against reality later — so frameworks earn trust from outcomes, not vibes.

    1.4k GitHub stars~1.6k tokensUpdated yesterday
    Product & Project ManagementAuto-check passed

  • Product Frameworks

    yonatangross/orchestkit

    Product management frameworks for business cases, market analysis, strategy, prioritization, OKRs/KPIs, personas, requirements, and user research.

    288 GitHub stars~1.1k tokensUpdated yesterday
    Product & Project ManagementAuto-check passed

More from iflytek/skillhub

All 29 skills in this repo

  • Orca Run Replay

    iflytek/skillhub

    Answers questions about a past agent run from its recording, using causal graphs and replay, instead of reconstructing events from memory.

    5.2k GitHub starsUsed in 4 repos~3k tokens
    Auto-check passed

  • Zero Slop Prose Editor

    iflytek/skillhub

    Audits and rewrites formulaic, AI-sounding prose while keeping facts, voice and format, using a local Python scorer and inspect-only, rewrite or embedded-gate modes.

    5.2k GitHub stars~1.5k tokensUpdated 6 days ago
    Auto-check passed

  • Sandbase

    iflytek/skillhub

    Access 2,000+ AI models and API tools through one MCP interface for inference, media generation, search, scraping, embeddings, social data, and structured retrieval.

    5.2k GitHub starsUsed in 2 repos~2.1k tokens
    Auto-check passed

  • LinkedIn Post Formatter

    iflytek/skillhub

    Drafts a copy-paste-ready LinkedIn post from your facts and ideas, choosing the smallest structure that fits and keeping an accessible plain-text fallback for any styled text.

    5.2k GitHub stars~901 tokensUpdated 6 days ago
    Auto-check passed

  • SkillHub CLI

    iflytek/skillhub

    Connects an agent to a SkillHub registry and uses the official SkillHub CLI to search, install, list and explicitly upgrade skills from that registry.

    5.2k GitHub stars~2.3k tokensUpdated 6 days ago
    Auto-check passed

  • AI Claim Checker

    iflytek/skillhub

    Breaks AI-generated text into checkable claims, verifies them against independent sources and labels each one, with an optional exercise for learners.

    5.2k GitHub stars~1.2k tokensUpdated 6 days ago
    Auto-check passed

Categories

Questions about Decision Matrix

What does Decision Matrix do?

Compares options with pros and cons, weighted scoring, pre-mortems, opportunity costs and ICE prioritization, labeling assumptions instead of inventing numbers. The skill applies a transparent framework to a choice so trade-offs show up and the facts that could change the answer are named. Every score is treated as an expression of your stated preferences, not objective truth, estimates are labeled, and missing costs, probabilities or constraints are never made up.

When should I use Decision Matrix?

Decision Matrix fits situations like: choosing between job offers, tools or vendors against weighted criteria; stress-testing a high-stakes plan with a pre-mortem; ranking a list of ideas or features with ICE scoring; surfacing hidden assumptions before committing to a decision.

How do I install Decision Matrix in Claude Code?

Run `npx skills add iflytek/skillhub --skill decision-matrix -a claude-code`. Or copy the skill folder (builtin-skills/skills/decision-matrix in iflytek/skillhub) into .claude/skills/decision-matrix in your project. Claude Code loads it when a task matches its description.

How do I install Decision Matrix in Codex?

Run `npx skills add iflytek/skillhub --skill decision-matrix -a codex`. Or copy the skill folder (builtin-skills/skills/decision-matrix in iflytek/skillhub) into .agents/skills/decision-matrix in your project. Codex loads it when a task matches its description.

Can I use Decision Matrix 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 iflytek/skillhub --skill decision-matrix -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/decision-matrix, .gemini/skills/decision-matrix, .github/skills/decision-matrix and .opencode/skills/decision-matrix in your project.

What does Decision Matrix need to run?

SKILL.md names no scripts, command-line tools or credentials: Decision Matrix is instructions for the agent only.

Does Decision Matrix 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 Decision Matrix 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. Review the folder before installing.

What licence does Decision Matrix use?

Decision Matrix is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Decision Matrix use?

About 2.3k tokens (SKILL.md is roughly 9.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Decision Matrix?

Skills that share tags, products or a category with Decision Matrix: Strategy Planning (andreaskelm/pm-brain, 234 stars), Feature Investment Advisor (deanpeters/Product-Manager-Skills, 7.2k stars), CEO Plan Review (garrytan/gstack, 136k stars) and Research Finance (borghei/Claude-Skills, 874 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Decision Matrix?

iflytek (a GitHub organization) maintains it in iflytek/skillhub, which has 5,152 GitHub stars. The repository holds 29 skills in this directory. The repository was last updated on October 1, 2026.

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