SKILLEMALL.ai
GitHub ↗ RU Sign in

CB hirey-compatible-use

Use this skill on an OpenClaw host where the already-installed Hi is healthy to do people-to-people matching — publish, update, pause, close, or inspect listings; find or be found by the right people for hiring, jobs, housing, friendship, dating or marriage, founder/investor outreach, lawyer search, or any other human-lead goal; contact promising matches, continue an existing pairing, and coordinate the next call or meeting through Hi's high-level tools. Activate even when the user does not say "Hi" by name but mentions any people-finding intent (looking for a job, hiring, finding roommates, looking for cofounders, etc.). Do not use for first-time install or repair (hand off to hirey-compatible-install instead), when the host is not OpenClaw, or when Hi tools are unavailable due to an unhealthy install/runtime; if the install likely just succeeded but the current LLM run has not materialized Hi tools yet, tell the user to continue in the next fresh turn rather than re-entering install or generic CLI debugging.

Not recommendedcritical or high security findings
ClawHub Agent Skills author: yzlee v0.1.61 MIT-0 2 files body ≈ 6 138 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process B 69/100 · Nearly there — weak spots: result and completion, inputs and preconditions

IntegrationPeople and hiringAI and agentsInfrastructuretype 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
C
68/100
safety, quality, tests
Safety 60%
82
Quality 40%
46
Run on models
none yet
Process rating
B
69/100
Nearly there
Inputs and preconditions w 11
0
Result and completion w 14
40
Tools and files w 18
60
the three weakest of ten parameters · all ten

What is at stake

The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.

Concealment
If you install

The skill tells the agent to hide things from you: not to show errors, not to mention actions, to report differently from what was done. You lose the ability to see what the agent really did.

For the author

Transparency beats a smooth answer. If the goal is to hide technical noise, ask the agent to "summarise briefly", not to "not mention".

How to improve

  1. Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
  2. Shorten the description to 1024 characters.
  3. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
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 · 1

  • high Concealment en-hide-from-user SKILL.md:109
    Instruction to hide actions from the user
    - do not invent meeting provider details or Zoom links that have not actually been scheduled — specifically, do not tell the user "the other side has the link / number" until the thread action reaches

Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • error description-long description is 1025 chars, limit 1024
  • warning body-long SKILL.md body ≈ 6138 tokens (recommended < 5000); move details to references/

Process rating: all ten parameters 69/100

  • 0Inputs and preconditions. Does not say what the process needs to start
  • 40Result and completion. Does not say what the result is
  • 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
  • 70Execution cost. Instruction body is 6138 tokens
  • 85Steps. 96 steps, 1 vague phrases
  • 100When it triggers. States when to use and when not to
  • 100Failures and branches. 14 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 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 The response is described with custom markup (5 tags): a typed call is more reliable

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
  • +3Description length 1025: 120–800 characters recommended
  • +3Output format is not stated: the model decides each time
  • +4No input/output examples
  • +1No license
  • +2Single-language instructions
  • +4Description says when NOT to use the skill
  • +4Structure: 5 headings
  • +3Step-by-step instructions: 96 items

Quality base 70; lint remarks subtract, signals add up to 100. Result: 46.

External checks

ClawHub: suspicious
The skill is mostly a disclosed Hi people-matching workflow, but it also tells the agent to silently install plugin updates and restart the OpenClaw gateway from release webhooks without user approval.
LLM: suspicious (high) · VirusTotal: · 29 May 2026