SKILLEMALL.ai
GitHub ↗ RU Sign in

BF amphp

Writing non-blocking, async PHP code using the AMPHP framework — revolt/event-loop, amphp/amp ^3, and the full amphp/* ecosystem (http-server, http-client, websocket, mysql, redis, parallel, socket, pipeline, file, cache, sync, dns, process). Always use this skill when PHP code involves: amphp/* packages, the Revolt event loop, Amp\Future, Amp\async(), Amp\delay(), PHP Fibers for async I/O, DeferredFuture, TimeoutCancellation, SocketHttpServer, WebsocketClientHandler, or Worker\Task. Also use when the user wants to replace blocking PHP (curl_exec, file_get_contents, PDO, sleep) with AMPHP async equivalents, build a non-blocking PHP HTTP or WebSocket server, run concurrent PHP I/O without pcntl, or debug Revolt event-loop behavior — even if they don't say "amphp" explicitly but the context clearly points to this ecosystem.

ClawHub Agent Skills author: Sergey Krupkin v1.0.0 MIT-0 30 files body ≈ 1 593 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process F 42/100 · Will not run — References files that are not bundled: templates/http-server.php, templates/websocket-handler.php, templates/parallel-task.php

GeneratorMySQLSoftware developmentInfrastructuretype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
B
77/100
safety, quality, tests
Safety 60%
80
Quality 40%
73
Run on models
none yet
Process rating
F
42/100
Will not run
References files that are not bundled: templates/http-server.php, templates/websocket-handler.php, templates/parallel-task.php
Tools and files w 18
0
Result and completion w 14
0
Inputs and preconditions w 11
0
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Broad scope medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The skill asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.

For the author

Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.

How to improve

  1. The text references files that are not there: add them or drop the references.
For the model run — optional
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 16

✓ No critical or high findings

Medium and low: 16
  • medium Broad scope meta-broad-allowed-tools SKILL.md:1
    Broad tool permissions pre-approved: Bash
    allowed-tools: Read Write Edit Bash Glob Grep Agent
  • low Secrets in code secret-high-entropy-token docs/common-mistakes.md:183
    High-entropy token-like string (may be an id, hash or a credential)
    new Base…eam(new ReadableBuffer($encoded))
  • low Secrets in code secret-high-entropy-token docs/common-mistakes.md:189
    High-entropy token-like string (may be an id, hash or a credential)
    new Base…eam(new ReadableIterableStream([$encoded]))
  • low Secrets in code secret-high-entropy-token docs/constructors.md:86
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    // Use instead of ReadableBuffer as source for Base…eam
    detector
  • low Secrets in code secret-high-entropy-token docs/namespaces.md:60
    High-entropy token-like string (may be an id, hash or a credential)
    use Amp\ByteStream\Base64\Base…eam;     // Base64 encode
  • low Secrets in code secret-high-entropy-token docs/namespaces.md:61
    High-entropy token-like string (may be an id, hash or a credential)
    use Amp\ByteStream\Base64\Base…eam;     // Base64 decode (use ReadableIterableStream as source!)
  • low Secrets in code secret-high-entropy-token examples/byte-stream.md:58
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition; test fixture / example file)
    // Required as source for Base…eam (see below).
    detectorfixture
  • low Secrets in code secret-high-entropy-token examples/byte-stream.md:125
    High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file)
    use Amp\ByteStream\Base64\Base…eam;
    fixture
  • low Secrets in code secret-high-entropy-token examples/byte-stream.md:126
    High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file)
    use Amp\ByteStream\Base64\Base…eam;
    fixture
  • low Secrets in code secret-high-entropy-token examples/byte-stream.md:132
    High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file)
    $encoded = buffer(new Base…eam(new ReadableBuffer("hello world")));
    fixture
  • low Secrets in code secret-high-entropy-token examples/byte-stream.md:135
    High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file)
    // ReadableBuffer closes itself after returning EOF, which causes Base…eam
    fixture
  • low Secrets in code secret-high-entropy-token references/class-examples.md:235
    High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file)
    // calls isClosed() mid-stream (e.g. Base…eam).
    fixture
  • low Secrets in code secret-high-entropy-token references/class-examples.md:247
    High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file)
    ### Base…eam / Base…eam
    fixture
  • low Secrets in code secret-high-entropy-token references/class-examples.md:249
    High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file)
    use Amp\ByteStream\Base64\Base…eam;
    fixture
  • low Secrets in code secret-high-entropy-token references/class-examples.md:250
    High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file)
    use Amp\ByteStream\Base64\Base…eam;
    fixture
  • low Secrets in code secret-high-entropy-token references/class-examples.md:256
    High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file)
    new Base…eam(new ReadableBuffer("hello world"))
    fixture

Files scanned: 28. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning missing-ref reference to a missing file: templates/http-server.php
  • warning missing-ref reference to a missing file: templates/websocket-handler.php
  • warning missing-ref reference to a missing file: templates/parallel-task.php
  • warning missing-ref reference to a missing file: scripts/server-demo.php
  • warning missing-ref reference to a missing file: scripts/http-client-demo.php

Process rating: all ten parameters 42/100

Will not run. References files that are not bundled: templates/http-server.php, templates/websocket-handler.php, templates/parallel-task.php
  • 0Tools and files. 5 referenced file(s) missing: templates/http-server.php, templates/websocket-handler.php, templates/parallel-task.php
  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Failures and branches. Linear process with no failure handling
  • 0Progress reporting. Says nothing while it works
  • 30Running it twice. 4 mutating operations with no state check
  • 100Steps. 5 steps
  • 100When it triggers. States when to use and when not to
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 1593 tokens
  • medium 3 test cases, all positive: not one "should refuse" or "should ask first"

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +5Description has no quoted example phrases that should trigger the skill
  • +4Description does not say when NOT to use the skill (false activations)
  • +3Description length 833: 120–800 characters recommended
  • +3Output format is not stated: the model decides each time
  • +1No license
  • +2Single-language instructions
  • +4Structure: 11 headings
  • +3Step-by-step instructions: 5 items
  • +4Has examples (0 code blocks)
  • +4Reference files are cited in the instructions (7 of 7)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 73.

External checks

ClawHub: suspicious
The skill is a coherent AMPHP coding guide, but several production-oriented examples model unsafe server, credential, and upload handling that users should review before installation.
LLM: suspicious (medium) · VirusTotal: · 29 May 2026