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

Decide

by BlockRunAI in BlockRunAI/blockrun-mcp

A skill your agent uses when the user wants to try BlockRun's free typed-judgment endpoint (POST api.blockrun.ai/v1/decide, served by OpenJev) on their own data from Claude Code — yes/no, labelled…

MITAuto-check passedAgent Workflows

Install Decide

skills CLI
$ npx skills add BlockRunAI/blockrun-mcp --skill decide -a claude-code

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

GitHub CLI
$ gh skill install BlockRunAI/blockrun-mcp decide --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/BlockRunAI/blockrun-mcp.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/decide .claude/skills/decide && 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
decide
GitHub stars
392
Token cost
~2.5k tokens
SKILL.md length
1,120 words
Files
1
Skills in repo
17
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when the user wants to try BlockRun's free typed-judgment endpoint (POST api.blockrun.ai/v1/decide, served by OpenJev) on their own data from Claude Code — yes/no, labelled…

  • Works in 4 steps: Build the state with everything the… → Ask the independent questions together… → Combine with deterministic checks the… → …
  • The user wants to try BlockRuns free typed-judgment endpoint (POST api.blockrun.ai/v1/decide
  • SKILL.md covers What it is not, Getting a key without changing…, Request and Response, plus 5 more sections
  • Calls jq and curl; reaches api.blockrun.ai; needs BLOCKRUN_API_KEY

What it does

Decide is an agent skill from BlockRunAI/blockrun-mcp. Use when the user wants to try BlockRun's free typed-judgment endpoint (POST api.blockrun.ai/v1/decide, served by OpenJev) on their own data from Claude Code — yes/no, labelled choice, or scored-rung questions over a text or JSON state, up to 64 per call. Not an MCP tool: call it with curl from the shell. Covers the request shape, what the confidence number does and does not mean, and why OpenJev is not Jev.

Its SKILL.md is about 2.5k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Agent Workflows, covering MCP servers. It works with Model Context Protocol. The repository describes itself as: Live data for AI agents — search, research, markets, crypto, X/Twitter. Pay-per-call via x402 micropayments. The licence is MIT.

When your agent uses it

  • The user wants to try BlockRuns free typed-judgment endpoint (POST api.blockrun.ai/v1/decide
  • Served by OpenJev) on their own data from Claude Code — yes/no
  • Labelled choice
  • Scored-rung questions over a text

Example prompts

  • “/decide”

Requirements

  • A credential in BLOCKRUN_API_KEY

Workflow steps

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

  1. Build the state with everything the judgment needs: the message, the
  2. Ask the independent questions together in one call — one round trip,
  3. Combine with deterministic checks the code already has (amount, account
  4. Route by margin. Act automatically where the margin is wide and the

What it can do on your machine

Read from SKILL.md and the folder at commit a7a9b3c. 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

    Shell commands in SKILL.md call:

    • jq
    • curl

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

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • api.blockrun.ai

    Also links to:

    • blockrun.ai
    • user.blockrun.ai

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

  • Credentials

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

    • BLOCKRUN_API_KEY

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

Context cost

Decide loads about 2.5k tokens when it runs. Until then it costs about 105 tokens; SKILL.md has 1,120 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~105
When it runs · the whole SKILL.md, loaded when a task matches
~2.5k

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 BlockRunAI/blockrun-mcp at commit a7a9b3c, republished under its MIT licence (© BlockRunAI). 1,120 words, ~2,465 tokens.

Download SKILL.mdSave it as .claude/skills/decide/SKILL.md (or your agent's skills folder).
name
decide
description
Use when the user wants to try BlockRun's free typed-judgment endpoint (POST api.blockrun.ai/v1/decide, served by OpenJev) on their own data from Claude Code — yes/no, labelled choice, or scored-rung questions over a text or JSON state, up to 64 per call. Not an MCP tool: call it with curl from the shell. Covers the request shape, what the confidence number does and does not mean, and why OpenJev is not Jev.
triggers
decide, v1/decide, typed judgment, typed judgments, openjev, open jev, jev, nli, natural language inference, entailment, classify with a small model, cheap…

Decide — free typed judgments from Claude Code

POST https://api.blockrun.ai/v1/decide takes a state (a message, a ticket, a diff, a tool result, a row of data) and up to 64 questions, and returns a typed answer with a number beside each one. No prose to parse. The backend is OpenJev, an open-source natural-language-inference model BlockRun hosts.

It is not a BlockRun MCP tool, on purpose: you are already a frontier model, and for a one-off "is this urgent?" you are the better judge. The endpoint earns its place when the user wants the same fixed ruler over many items, or is prototyping a judgment they will later run from a pipeline without a model. From Claude Code, call it with curl from the shell.

What it is not

  • Not paid, not x402. It is free behind a registered API key. There is no payment header, no wallet path, and it is served by api.blockrun.ai, not the x402 gateway at blockrun.ai (a POST to blockrun.ai/v1/decide is a 404).
  • OpenJev is not Jev. Jev is TypeSafe's model. OpenJev is an unaffiliated open-source NLI cross-encoder (MIT, published by AlexWortega on Hugging Face, Qwen3.5 4B base). It is not made by the people who make Jev and it is not a smaller or free tier of it. BlockRun does not sell or resell Jev. There is one backend, and the x-blockrun-backend response header names it on every call.
  • No quality comparison exists. BlockRun expects OpenJev to be materially weaker than Jev, has not benchmarked the two, and will not put a number on the gap. Do not invent one. The model authors' own zero-shot NLI figures, with attribution and a read date, are at https://blockrun.ai/openjev.

Getting a key without changing how the MCP pays

Keys are minted at https://user.blockrun.ai/dashboard/keys (brk_live_…, shown once; registration, not a card).

For experiments, export the key in the shell and leave the MCP server alone:

bash
export BLOCKRUN_API_KEY=brk_live_…

Do not write it to ~/.blockrun/.api-key just to try decide. The MCP server reads that file at startup and a present key moves every paid tool from wallet mode to account billing — the same switch BLOCKRUN_API_KEY in the MCP server's own config makes. That is fine if the user wants account billing (see the blockrun-setup skill); it is a surprise if they only wanted a free judgment. If the MCP is already on account billing, the same key works for both.

Request

bash
curl -sS -X POST https://api.blockrun.ai/v1/decide \
  -H "authorization: Bearer $BLOCKRUN_API_KEY" \
  -H "content-type: application/json" \
  -D /dev/stderr \
  -d '{
    "state": "Help! My payouts have been failing for 3 days.",
    "questions": {
      "is_urgent":   { "type": "noul",   "instructions": "Does this convey urgency?" },
      "department":  { "type": "choice", "instructions": "Which team should handle this?",
                       "criteria": { "billing": "Payments, refunds",
                                     "technical": "Bugs, outages" } },
      "frustration": { "type": "score",  "instructions": "How frustrated is the customer?",
                       "criteria": ["Calm", "Frustrated", "Very angry"] }
    }
  }'

-D /dev/stderr shows the response headers (backend, rate-limit) without mixing them into the JSON on stdout.

FieldTypeRequiredNotes
statestring | object | arrayyesWhat to judge. Text and JSON both work. If a fact matters, put it in the state — the model looks nothing up.
questionsobjectyesYour own id → question. 1 to 64 per call.
modelstringnoDefaults to openjev, the only backend. Leave it out.

Three question types, one operation underneath (state = premise, question = hypothesis, answer = how strongly the premise entails it):

TypecriteriaYou get back
noulnone — it is true or falseone number for how strongly the state supports the claim
choicemap of label → its meaning, 2 to 255 entriesthe top label, plus a share per option
scorearray of rung descriptions in words, 2 to 255a weighted position across the rungs, plus the distribution

instructions — the question itself, in plain language — is required on all three.

Response

json
{
  "model": "openjev",
  "answers": {
    "is_urgent":   { "type": "noul",   "noul": 0.986 },
    "department":  { "type": "choice", "choice": "billing",
                     "probabilities": { "billing": 0.71, "technical": 0.29 },
                     "confidence": 0.71 },
    "frustration": { "type": "score",  "score": 1.42,
                     "legend": { "0": "Calm", "1": "Frustrated", "2": "Very angry" },
                     "probabilities": { "0": 0.11, "1": 0.36, "2": 0.53 },
                     "confidence": 0.53 }
  }
}

score is the probability-weighted rung index (1.42 sits between "Frustrated" and "Very angry"); legend maps index → rung text.

Show full SKILL.md (545 more words)Show less

Read this before you build a threshold

The confidence on a choice is not the probability the answer is correct.

Every option is scored against the state, and the scores are then divided by their total so they sum to one. That step throws away how strong the scores were:

  • three options each scoring 0.1 — the model supporting none of them — come back as 0.33 / 0.33 / 0.33;
  • two options scoring 0.9 and 0.85 — both strongly supported — come back as 0.51 / 0.49.

Opposite situations, identical response. The number is a share of the agreement found — an ordering with a margin. Wide means the model clearly preferred one option; narrow means it did not. It says nothing about whether any option fits, and nothing has been fitted against real outcomes the way a calibrated model's probabilities are. The same applies to score's probabilities and confidence. A noul is the raw entailment score and is not normalised — but it is not calibrated either.

Set thresholds by running the user's own labelled examples through the endpoint and looking at where the errors land, never by reading the number as a percentage. An agent that gates on confidence > 0.8 as if it were accuracy will be wrong with no error to tell it so.

Trying it on the user's data — the shape that works

  1. Build the state with everything the judgment needs: the message, the records it refers to, the policy that governs it. Fetch with blockrun_exa or blockrun_search first if a fact is missing; decide cannot look it up.
  2. Ask the independent questions together in one call — one round trip, one rate-limit hit, up to 64 answers.
  3. Combine with deterministic checks the code already has (amount, account age, "was a refund already issued").
  4. Route by margin. Act automatically where the margin is wide and the checks agree; hand narrow cases to a reasoning model — blockrun_chat with a claude-*, o-series or DeepSeek model — or to a person.

A quick evaluation loop from Claude Code: put 20–50 labelled rows in a JSON file, loop curl over them with jq, and tabulate agreement per question. That is the only number that should decide whether the endpoint is good enough for the user's task.

bash
jq -c '.[]' examples.json | while read -r row; do
  state=$(jq -c '.state' <<<"$row"); want=$(jq -r '.label' <<<"$row")
  got=$(curl -sS -X POST https://api.blockrun.ai/v1/decide \
    -H "authorization: Bearer $BLOCKRUN_API_KEY" -H "content-type: application/json" \
    -d "{\"state\": $state, \"questions\": {\"q\": {\"type\": \"choice\",
         \"instructions\": \"Which team should handle this?\",
         \"criteria\": {\"billing\": \"Payments, refunds\", \"technical\": \"Bugs, outages\"}}}}" \
    | jq -r '.answers.q.choice')
  echo "$want,$got"
done | sort | uniq -c

What it does not do

It does not write, summarise, or explain — there is no free-text field in the response. It has no memory between calls. Image input exists in the model's v2 checkpoint but the endpoint does not expose it.

Limits and errors

StatusMeaningWhat to do
400Body did not match the schema; the response names the fieldFix the field. Common: a choice with criteria as an array, a score with a map, fewer than 2 criteria, more than 64 questions.
401Missing or invalid keyBLOCKRUN_API_KEY is unset in this shell, or wrong. Check https://user.blockrun.ai/dashboard/keys.
429Per-key hourly limit reachedWait for the interval the response carries (retry-after). The limit is enforced server-side and reported in the response — read it there; do not assume a number.

None of these cost anything; nothing here ever does.

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

Files

Just SKILL.md in skills/decide of BlockRunAI/blockrun-mcp.

Open the folder on GitHubat commit a7a9b3c

Compare with similar skills

Decide 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.

Decide compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Decide this skillBlockRunAI/blockrun-mcp392—~2.5kAutomated safety check: PassMIT
MCP Server Builderanthropics/skills180k62 repos~2.3kAutomated safety check: PassApache-2.0
MCP Server BuildershareAI-lab/learn-claude-code78k5 repos~1.2kAutomated safety check: PassMIT
MCP Integration for Pluginsanthropics/claude-plugins-official37k11 repos~3.1kAutomated safety check: PassApache-2.0
Fastmcp Client CLIPrefectHQ/fastmcp28k1 repos~823Automated safety check: PassApache-2.0
Crush Configurationcharmbracelet/crush29k—~3.7kAutomated safety check: PassCustom licence

Similar skills

  • MCP Server Builder

    anthropics/skills

    Official

    Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.

    180k GitHub starsUsed in 62 repos~2.3k tokens
    Agent WorkflowsAuto-check passed

  • MCP Server Builder

    shareAI-lab/learn-claude-code

    Walks through building MCP servers in Python or TypeScript that expose tools, resources and prompts to Claude, with templates, registration and testing.

    78k GitHub starsUsed in 5 repos~1.2k tokens
    Agent WorkflowsAuto-check passed

  • MCP Integration for Plugins

    anthropics/claude-plugins-official

    Official

    Explains how to bundle Model Context Protocol servers in a Claude Code plugin, covering config files, stdio, SSE, HTTP and WebSocket server types, and authentication.

    37k GitHub starsUsed in 11 repos~3.1k tokens
    Agent WorkflowsAuto-check passed

  • Fastmcp Client CLI

    PrefectHQ/fastmcp

    Query and invoke tools on MCP servers using fastmcp list and fastmcp call.

    28k GitHub starsUsed in 1 repo~823 tokens
    Agent WorkflowsAuto-check passed

  • Crush Configuration

    charmbracelet/crush

    Explains how to configure the Crush coding agent with crushrc or crush.json, covering providers, models, LSPs, MCP servers, hooks, permissions and config precedence.

    29k GitHub stars~3.7k tokensUpdated today
    Agent WorkflowsAuto-check passed

  • Context Mode Output Sandbox

    mksglu/context-mode

    Routes large command, file, API and browser output through context-mode tools so only the needed result enters the agent's context, instead of dumping it via Bash.

    26k GitHub stars~4.1k tokensUpdated today
    Agent WorkflowsAuto-check passed

More from BlockRunAI/blockrun-mcp

All 17 skills in this repo

  • Signal To Trade Demo

    BlockRunAI/blockrun-mcp

    Prepare or run a polished BlockRun trading demo that discovers a current Polymarket market, combines live price, probability history, smart-money, and liquidity evidence into a balanced signal…

    392 GitHub stars~1.8k tokensUpdated yesterday
    Auto-check passed

  • Blockrun

    BlockRunAI/blockrun-mcp

    Pay-per-call access to AI models, real-time data, media generation and multi-chain RPC over x402 micropayments (USDC on Base or Solana), or a BlockRun account API key.

    392 GitHub stars~2.7k tokensUpdated yesterday
    Auto-check passed

  • Blockrun Debug

    BlockRunAI/blockrun-mcp

    A skill your agent uses when the BlockRun MCP server (@blockrun/mcp) is installed but misbehaving — 'Failed to connect', spawn npx ENOENT, blockrun missing from claude mcp list, HTTP 402 /…

    392 GitHub stars~3k tokensUpdated yesterday
    Auto-check passed

  • Blockrun Setup

    BlockRunAI/blockrun-mcp

    A skill your agent uses when asked to install, add, configure, or set up the BlockRun MCP server (@blockrun/mcp) in Claude Code, Claude Desktop, Cursor, Windsurf, Codex CLI, Grok or another MCP…

    392 GitHub stars~2k tokensUpdated yesterday
    Auto-check passed

  • Blockrun Upgrade

    BlockRunAI/blockrun-mcp

    A skill your agent uses when the BlockRun MCP server prints 'Update available', when asked to upgrade, update, or pin @blockrun/mcp, when a fix 'should be in the new version' but the client still…

    392 GitHub stars~1.6k tokensUpdated yesterday
    Auto-check passed

  • Crypto Data

    BlockRunAI/blockrun-mcp

    A skill your agent uses for any crypto data question — token/coin prices, FX, commodities, stocks, OHLC history, DEX pairs and liquidity, DeFi TVL, yield/APY pools, or raw JSON-RPC against a chain…

    392 GitHub stars~2.8k tokensUpdated yesterday
    Auto-check passed

Works with

Categories

Questions about Decide

What does Decide do?

A skill your agent uses when the user wants to try BlockRun's free typed-judgment endpoint (POST api.blockrun.ai/v1/decide, served by OpenJev) on their own data from Claude Code — yes/no, labelled…. Decide is an agent skill from BlockRunAI/blockrun-mcp.ai/v1/decide, served by OpenJev) on their own data from Claude Code — yes/no, labelled choice, or scored-rung questions over a text or JSON state, up to 64 per call.

When should I use Decide?

Decide fits situations like: the user wants to try BlockRuns free typed-judgment endpoint (POST api.blockrun.ai/v1/decide; served by OpenJev) on their own data from Claude Code — yes/no; labelled choice; scored-rung questions over a text.

How do I install Decide in Claude Code?

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

How do I install Decide in Codex?

Run `npx skills add BlockRunAI/blockrun-mcp --skill decide -a codex`. Or copy the skill folder (skills/decide in BlockRunAI/blockrun-mcp) into .agents/skills/decide in your project. Codex loads it when a task matches its description.

Can I use Decide 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 BlockRunAI/blockrun-mcp --skill decide -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/decide, .gemini/skills/decide, .github/skills/decide and .opencode/skills/decide in your project.

What does Decide need to run?

Going by SKILL.md and its folder, Decide needs the command-line tools its instructions call (jq and curl) and credentials named BLOCKRUN_API_KEY. Our summary lists: A credential in BLOCKRUN_API_KEY.

Does Decide access the network?

SKILL.md names 3 domains. In commands or code: api.blockrun.ai; the agent is likely to contact it when it follows the instructions. As links in the text: blockrun.ai and user.blockrun.ai. This is read from the text; nothing was executed.

Is Decide 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 Decide use?

Decide 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 Decide use?

About 2.5k tokens (SKILL.md is roughly 9.9k 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 Decide?

Skills that share tags, products or a category with Decide: MCP Server Builder (anthropics/skills, 180k stars), MCP Server Builder (shareAI-lab/learn-claude-code, 78k stars), MCP Integration for Plugins (anthropics/claude-plugins-official, 37k stars) and Fastmcp Client CLI (PrefectHQ/fastmcp, 28k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Decide?

BlockRunAI (a GitHub organization) maintains it in BlockRunAI/blockrun-mcp, which has 392 GitHub stars. The repository holds 17 skills in this directory. The repository was last updated on October 6, 2026.

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