SKILLEMALL.ai
GitHub ↗ RU Sign in

BF group-debug-deploy-expert

Universal debug & deploy expert for multi-project instances. Invoke when debugging services, deploying backend/frontend/mobile, troubleshooting bugs, or any ops task. Enforces 21 iron principles with project absolute isolation (ZERO-TH LAW). Use when debugging, deploying, CI/CD, testing, error handling, or any DevOps task.

ClawHub Hermes author: xuanji-ai-2026 v1.0.2 MIT-0 3 files body ≈ 46 669 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process F 53/100 · Will not run — References files that are not bundled: ../rules/core_file_protection.md, ../rules/project_rules.md

ReferenceSoftware developmentInfrastructuretype and topics are labelled automatically from the skill text
Runs in: OpenClaw Hermes Agent
JSON
Technical rating
B
82/100
safety, quality, tests
Safety 60%
98
Quality 40%
58
Run on models
none yet
Process rating
F
53/100
Will not run
References files that are not bundled: ../rules/core_file_protection.md, ../rules/project_rules.md
Tools and files w 18
0
Inputs and preconditions w 11
0
Execution cost w 6
10
the three weakest of ten parameters · all ten

How to improve

  1. For Hermes the description must be one sentence under 60 characters; move the conditions to a "When to Use" section.
  2. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
  3. The text references files that are not there: add them or drop the references.
For the model run — optional
  • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 2

✓ No critical or high findings

Medium and low: 2
  • low Dangerous commands cmd-background-process SKILL.md:2547
    Starts a background / autostarted process (documentation table row)
    | systemctl | Service management | `systemctl status nginx` | `systemctl start/stop/restart service`, `systemctl enable service` |
    table
  • low Risky intent intent-wallet-secrets SKILL.md:2584
    Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (documentation table row)
    | keytool | Keystore management | `keytool` | `keytool -list -v -keystore file.jks`, `keytool -genkeypair -alias name -keystore file.jks` |
    table

Files scanned: 3. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-long-hermes description is 324 chars; the Hermes authoring standard requires ≤ 60 (one sentence, ending with a period)
  • warning body-long SKILL.md body ≈ 46669 tokens (recommended < 5000); move details to references/
  • warning missing-ref reference to a missing file: ../rules/core_file_protection.md
  • warning missing-ref reference to a missing file: ../rules/project_rules.md
  • note frontmatter-key unknown frontmatter key "homepage"

Process rating: all ten parameters 53/100

Will not run. References files that are not bundled: ../rules/core_file_protection.md, ../rules/project_rules.md
  • 0Tools and files. 2 referenced file(s) missing: ../rules/core_file_protection.md, ../rules/project_rules.md
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 10Execution cost. Instruction body is 46669 tokens: crowds the task out of the window
  • 20When it triggers. No condition that starts the skill
  • 60Consistency. The Hermes dialect needs category and tags
  • 100Steps. 252 steps
  • 100Result and completion. Output format and completion criterion are stated
  • 100Failures and branches. 6 branches, has a failure section
  • 100Running it twice. Mutating operations check current state
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 20 top-level sections: this looks like several domains in one skill

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)
  • -2localhost URLs: will not work for another user
  • -235 emoji in the instructions: noise for the model
  • +2Single-language instructions
  • +3Description length 324: enough signal without eating the budget
  • +4Structure: 113 headings
  • +3Step-by-step instructions: 252 items
  • +3Output format is stated explicitly
  • +4Has examples (55 code blocks)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 58.

External checks

ClawHub: suspicious
This skill is a powerful DevOps assistant with coherent goals, but it asks for broad command authority and persistent project memory in ways users should review before installing.
LLM: suspicious (high) · VirusTotal: · 29 May 2026