How should pragmatic-builder be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this skill.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

Crawler Summary

pragmatic-builder answer-first brief

A builder that generates Agent Skills with a practical focus — one script, inline smoke tests, and usage examples embedded in the SKILL.md. --- name: pragmatic-builder description: A builder that generates Agent Skills with a practical focus — one script, inline smoke tests, and usage examples embedded in the SKILL.md. version: 0.1.0 license: Apache-2.0 --- Pragmatic Builder You are a skill builder agent. Your job is to take an idea prompt and generate a complete Agent Skill that is immediately usable, tested, and self-documenting. Everything a user need Capability contract not published. No trust telemetry is available yet. Last updated 4/15/2026.

Freshness

Last checked 4/15/2026

Best For

pragmatic-builder is best for solve, be, break workflows where OpenClaw compatibility matters.

Not Ideal For

Contract metadata is missing or unavailable for deterministic execution.

Evidence Sources Checked

editorial-content, GITHUB OPENCLEW, runtime-metrics, public facts pack

Card Facts Snapshot Contract Trust

Claim this agent

Agent DossierGitHubSafety: 94/100

pragmatic-builder

OpenClawself-declared

Public facts

Change events

Artifacts

Freshness

Apr 15, 2026

Verifiededitorial-contentNo verified compatibility signals

Capability contract not published. No trust telemetry is available yet. Last updated 4/15/2026.

Trust evidence available

Trust score

Unknown

Compatibility

OpenClaw

Freshness

Apr 15, 2026

Vendor

Bennettphil

Artifacts

Benchmarks

Last release

Unpublished

Executive Summary

Key links, install path, and a quick operational read before the deeper crawl record.

Verifiededitorial-content

Summary

Capability contract not published. No trust telemetry is available yet. Last updated 4/15/2026.

View Source

Setup snapshot

git clone https://github.com/BennettPhil/builder-pragmatic-builder.git

1
Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.
2
Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Evidence Ledger

Everything public we have scraped or crawled about this agent, grouped by evidence type with provenance.

Verifiededitorial-content

Vendor (1)

Vendor

Bennettphil

profilemedium

Observed Apr 15, 2026Source link Provenance

Compatibility (1)

Protocol compatibility

OpenClaw

contractmedium

Observed Apr 15, 2026Source link Provenance

Security (1)

Handshake status

UNKNOWN

trustmedium

Observed unknownSource link Provenance

Integration (1)

Crawlable docs

6 indexed pages on the official domain

search_documentmedium

Observed Apr 15, 2026Source link Provenance

Release & Crawl Timeline

Merged public release, docs, artifact, benchmark, pricing, and trust refresh events.

Self-declaredagent-index

Docs Update

Docs refreshed: Sign in to GitHub · GitHub

search_documentmedium

Fresh crawlable documentation was indexed for the official domain.

Observed Apr 15, 2026

Artifacts Archive

Extracted files, examples, snippets, parameters, dependencies, permissions, and artifact metadata.

Self-declaredGITHUB OPENCLEW

Extracted files

Examples

Snippets

Languages

typescript

Parameters

Executable Examples

yaml

---
name: <kebab-case-name>
description: <one-line summary>
version: 0.1.0
license: Apache-2.0
---

bash

$ ./scripts/run.sh <typical-args>
<expected output>

text

### Example: <description>

\`\`\`bash
$ ./scripts/run.sh <args>
<output>
\`\`\`

bash

#!/usr/bin/env bash
set -euo pipefail
PASS=0; FAIL=0
check() {
  local desc="$1" expected="$2" actual="$3"
  if [ "$expected" = "$actual" ]; then
    ((PASS++)); echo "PASS: $desc"
  else
    ((FAIL++)); echo "FAIL: $desc (expected '$expected', got '$actual')"
  fi
}

# Test cases here
check "description" "expected" "$(./scripts/run.sh args)"

echo "$PASS passed, $FAIL failed"
[ "$FAIL" -eq 0 ]

Docs & README

Full documentation captured from public sources, including the complete README when available.

Self-declaredGITHUB OPENCLEW

Docs source

GITHUB OPENCLEW

Editorial quality

ready

Full README

name: pragmatic-builder description: A builder that generates Agent Skills with a practical focus — one script, inline smoke tests, and usage examples embedded in the SKILL.md. version: 0.1.0 license: Apache-2.0

Pragmatic Builder

You are a skill builder agent. Your job is to take an idea prompt and generate a complete Agent Skill that is immediately usable, tested, and self-documenting. Everything a user needs lives in two files: SKILL.md and the implementation script.

Philosophy

Most skills fail for three reasons: they lack working examples, they have no tests, and their docs are separated from the code. This builder fixes all three by putting examples and test commands directly in the SKILL.md, so the skill is self-contained and verifiable.

When to Use

Use this builder for any idea where a single script can solve the problem. If the idea requires more than one script, consider whether it can be simplified into one entry point with subcommands.

Instructions

Given an idea prompt, generate exactly these files:

1. SKILL.md

The SKILL.md is the single source of truth. It must contain YAML frontmatter plus these sections in order:

---
name: <kebab-case-name>
description: <one-line summary>
version: 0.1.0
license: Apache-2.0
---

Section: Purpose (2-3 sentences)

What the skill does and why someone would use it.

Section: Quick Start

A single fenced code block showing the most common invocation and its expected output:

$ ./scripts/run.sh <typical-args>
<expected output>

This must be copy-paste runnable. No placeholders except where the user's input goes.

Section: Usage Examples

Three to five examples showing different use cases. Each example has:

A one-line description
The command
The expected output

Format:

### Example: <description>

\`\`\`bash
$ ./scripts/run.sh <args>
<output>
\`\`\`

Use realistic data, not foo/bar. Show the most useful combinations of flags.

Section: Smoke Tests

A fenced bash code block that can be run to verify the skill works. This block should:

Run 3-5 quick assertions
Print PASS or FAIL for each
Exit non-zero if any fail

#!/usr/bin/env bash
set -euo pipefail
PASS=0; FAIL=0
check() {
  local desc="$1" expected="$2" actual="$3"
  if [ "$expected" = "$actual" ]; then
    ((PASS++)); echo "PASS: $desc"
  else
    ((FAIL++)); echo "FAIL: $desc (expected '$expected', got '$actual')"
  fi
}

# Test cases here
check "description" "expected" "$(./scripts/run.sh args)"

echo "$PASS passed, $FAIL failed"
[ "$FAIL" -eq 0 ]

Section: Options Reference

A markdown table listing every flag, its default, and a one-line description:

| Flag | Default | Description | |------|---------|-------------| | ... | ... | ... |

Section: Error Handling

List the exit codes and what they mean. At minimum: 0 = success, 1 = usage error, 2 = runtime error.

2. scripts/run.sh

A single executable bash script (or Python/Node if the idea demands it). Requirements:

Starts with #!/usr/bin/env bash and set -euo pipefail
Accepts --help and prints usage to stderr
Validates all inputs before doing work
Exits with documented exit codes
Reads from stdin or accepts file arguments (never hardcoded paths)
Outputs to stdout (errors to stderr)
Is under 200 lines (split subcommands with functions, not files)

3. README.md

Exactly 3 sections:

Name + one-line description (as the title)
Quick Start — copy the Quick Start from SKILL.md
Full Documentation — a single link to SKILL.md

Nothing else. The README is a pointer, not documentation.

Guidelines

Every example in SKILL.md must produce the exact output shown when run against the implementation.
The smoke test section must pass against the implementation before the skill is considered complete.
Prefer bash unless the idea genuinely requires another language (e.g., JSON parsing → Python).
No unnecessary files. No .github/, no Makefile, no LICENSE file (the license is in the frontmatter).
If the idea is too vague, generate the most useful interpretation. If the idea is too ambitious, generate the simplest useful subset.
Keep the total file count to 3 (SKILL.md, scripts/run.sh, README.md). More files means more to maintain and more that can break.

Anti-Patterns (Avoid These)

Separate docs directory with files nobody reads
Test scripts that require external setup
Examples that say "output will vary" — always pin expected output
Scripts that silently succeed when they should error
README.md that duplicates SKILL.md content

Example

If the idea prompt is: "A tool that counts lines of code by language in a directory"

You would generate:

SKILL.md with inline examples showing ./scripts/run.sh ./src producing a language breakdown table, smoke tests verifying the counts, and an options table for --exclude, --format
scripts/run.sh — a bash script using find + wc with language detection by extension
README.md — title, quick start, link to SKILL.md

Contract & API

Machine endpoints, protocol fit, contract coverage, invocation examples, and guardrails for agent-to-agent use.

MissingGITHUB OPENCLEW

Endpoints

Dossier API Snapshot API Contract API Trust API

Contract coverage

Status

missing

Auth

None

Streaming

Data region

Unspecified

Protocol support

OpenClaw: self-declared

Requires: none

Forbidden: none

Guardrails

Operational confidence: low

No positive guardrails captured.

Invocation examples

curl -s "https://xpersona.co/api/v1/agents/bennettphil-builder-pragmatic-builder/snapshot"

curl -s "https://xpersona.co/api/v1/agents/bennettphil-builder-pragmatic-builder/contract"

curl -s "https://xpersona.co/api/v1/agents/bennettphil-builder-pragmatic-builder/trust"

Reliability & Benchmarks

Trust and runtime signals, benchmark suites, failure patterns, and practical risk constraints.

Missingruntime-metrics

Trust signals

Handshake

UNKNOWN

Confidence

unknown

Attempts 30d

unknown

Fallback rate

unknown

Runtime metrics

Observed P50

unknown

Observed P95

unknown

Rate limit

unknown

Estimated cost

unknown

Do not use if

Contract metadata is missing or unavailable for deterministic execution.

No benchmark suites or observed failure patterns are available.

Media & Demo

Every public screenshot, visual asset, demo link, and owner-provided destination tied to this agent.

Missingno-media

No screenshots, media assets, or demo links are available.

Related Agents

Neighboring agents from the same protocol and source ecosystem for comparison and shortlist building.

Self-declaredprotocol-neighbors

GITHUB_REPOSactivepieces

Rank

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

Traction

No public download signal

Freshness

Updated 2d ago

OPENCLAW

GITHUB_REPOScherry-studio

Rank

AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs

Traction

No public download signal

Freshness

Updated 6d ago

MCPOPENCLAW

GITHUB_REPOSAionUi

Rank

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

Traction

No public download signal

Freshness

Updated 6d ago

MCPOPENCLAW

GITHUB_REPOSCopilotKit

Rank

The Frontend for Agents & Generative UI. React + Angular

Traction

No public download signal

Freshness

Updated 23d ago

OPENCLAW

Machine Appendix

Contract JSON

{
  "contractStatus": "missing",
  "authModes": [],
  "requires": [],
  "forbidden": [],
  "supportsMcp": false,
  "supportsA2a": false,
  "supportsStreaming": false,
  "inputSchemaRef": null,
  "outputSchemaRef": null,
  "dataRegion": null,
  "contractUpdatedAt": null,
  "sourceUpdatedAt": null,
  "freshnessSeconds": null
}

Invocation Guide

{
  "preferredApi": {
    "snapshotUrl": "https://xpersona.co/api/v1/agents/bennettphil-builder-pragmatic-builder/snapshot",
    "contractUrl": "https://xpersona.co/api/v1/agents/bennettphil-builder-pragmatic-builder/contract",
    "trustUrl": "https://xpersona.co/api/v1/agents/bennettphil-builder-pragmatic-builder/trust"
  },
  "curlExamples": [
    "curl -s \"https://xpersona.co/api/v1/agents/bennettphil-builder-pragmatic-builder/snapshot\"",
    "curl -s \"https://xpersona.co/api/v1/agents/bennettphil-builder-pragmatic-builder/contract\"",
    "curl -s \"https://xpersona.co/api/v1/agents/bennettphil-builder-pragmatic-builder/trust\""
  ],
  "jsonRequestTemplate": {
    "query": "summarize this repo",
    "constraints": {
      "maxLatencyMs": 2000,
      "protocolPreference": [
        "OPENCLEW"
      ]
    }
  },
  "jsonResponseTemplate": {
    "ok": true,
    "result": {
      "summary": "...",
      "confidence": 0.9
    },
    "meta": {
      "source": "GITHUB_OPENCLEW",
      "generatedAt": "2026-04-17T05:34:10.456Z"
    }
  },
  "retryPolicy": {
    "maxAttempts": 3,
    "backoffMs": [
      500,
      1500,
      3500
    ],
    "retryableConditions": [
      "HTTP_429",
      "HTTP_503",
      "NETWORK_TIMEOUT"
    ]
  }
}

Trust JSON

{
  "status": "unavailable",
  "handshakeStatus": "UNKNOWN",
  "verificationFreshnessHours": null,
  "reputationScore": null,
  "p95LatencyMs": null,
  "successRate30d": null,
  "fallbackRate": null,
  "attempts30d": null,
  "trustUpdatedAt": null,
  "trustConfidence": "unknown",
  "sourceUpdatedAt": null,
  "freshnessSeconds": null
}

Capability Matrix

{
  "rows": [
    {
      "key": "OPENCLEW",
      "type": "protocol",
      "support": "unknown",
      "confidenceSource": "profile",
      "notes": "Listed on profile"
    },
    {
      "key": "solve",
      "type": "capability",
      "support": "supported",
      "confidenceSource": "profile",
      "notes": "Declared in agent profile metadata"
    },
    {
      "key": "be",
      "type": "capability",
      "support": "supported",
      "confidenceSource": "profile",
      "notes": "Declared in agent profile metadata"
    },
    {
      "key": "break",
      "type": "capability",
      "support": "supported",
      "confidenceSource": "profile",
      "notes": "Declared in agent profile metadata"
    }
  ],
  "flattenedTokens": "protocol:OPENCLEW|unknown|profile capability:solve|supported|profile capability:be|supported|profile capability:break|supported|profile"
}

Facts JSON

[
  {
    "factKey": "docs_crawl",
    "category": "integration",
    "label": "Crawlable docs",
    "value": "6 indexed pages on the official domain",
    "href": "https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar",
    "sourceUrl": "https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar",
    "sourceType": "search_document",
    "confidence": "medium",
    "observedAt": "2026-04-15T05:03:46.393Z",
    "isPublic": true
  },
  {
    "factKey": "vendor",
    "category": "vendor",
    "label": "Vendor",
    "value": "Bennettphil",
    "href": "https://github.com/BennettPhil/builder-pragmatic-builder",
    "sourceUrl": "https://github.com/BennettPhil/builder-pragmatic-builder",
    "sourceType": "profile",
    "confidence": "medium",
    "observedAt": "2026-04-15T02:14:34.104Z",
    "isPublic": true
  },
  {
    "factKey": "protocols",
    "category": "compatibility",
    "label": "Protocol compatibility",
    "value": "OpenClaw",
    "href": "https://xpersona.co/api/v1/agents/bennettphil-builder-pragmatic-builder/contract",
    "sourceUrl": "https://xpersona.co/api/v1/agents/bennettphil-builder-pragmatic-builder/contract",
    "sourceType": "contract",
    "confidence": "medium",
    "observedAt": "2026-04-15T02:14:34.104Z",
    "isPublic": true
  },
  {
    "factKey": "handshake_status",
    "category": "security",
    "label": "Handshake status",
    "value": "UNKNOWN",
    "href": "https://xpersona.co/api/v1/agents/bennettphil-builder-pragmatic-builder/trust",
    "sourceUrl": "https://xpersona.co/api/v1/agents/bennettphil-builder-pragmatic-builder/trust",
    "sourceType": "trust",
    "confidence": "medium",
    "observedAt": null,
    "isPublic": true
  }
]

Change Events JSON

[
  {
    "eventType": "docs_update",
    "title": "Docs refreshed: Sign in to GitHub · GitHub",
    "description": "Fresh crawlable documentation was indexed for the official domain.",
    "href": "https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar",
    "sourceUrl": "https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar",
    "sourceType": "search_document",
    "confidence": "medium",
    "observedAt": "2026-04-15T05:03:46.393Z",
    "isPublic": true
  }
]