DC hirey-compatible-install
Install Hirey AI (people-to-people matching for jobs, hiring, housing, friendship, dating, founders, investors, lawyers, any human-lead search) on a local OpenClaw host. Use whenever the user wants to install, set up, register, or repair Hi/Hirey AI/Hirey AI on this OpenClaw. CRITICAL — install is structurally a TWO-MESSAGE flow on every OpenClaw version because the LLM's tool inventory is frozen at run start: the same outer LLM run that ran `openclaw plugins install` cannot see hi_* tools (including `hi_agent_install`) and therefore cannot complete registration in a single message. Never fabricate `agent_id`, `hooks_ready`, `connected`, `activated` to make the install look one-shot — that is the most common failure mode and the user discovers the lie the first time they try to actually use Hi.
As a process C 64/100 · Has gaps — weak spots: result and completion, inputs and preconditions, execution cost
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.
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.
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
- 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.
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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 · 7
-
high Concealment
en-hide-from-userSKILL.md:204Instruction to hide actions from the user- during Stage A, do not tell the user you will keep tracking a background package-install process in a later turn; either report the final result from the blocking command, or if the host genuinely r
-
high Concealment
en-hide-from-userSKILL.md:206Instruction to hide actions from the user- if a local read like `/app/skills/hirey-compatible-install/SKILL.md` fails, explain plainly that the host cannot currently see its local skill snapshot; do not tell the user the Hirey AI skill disap
-
high Concealment
en-hide-from-userSKILL.md:285Instruction to hide actions from the user- in the default two-message flow, do not tell the user you are already starting the register step, switching to a new sub-session, or continuing Hi registration while the setup step is ending; the se
Medium and low: 4
-
low Secrets in code
secret-high-entropy-tokenscripts/openclaw-host-installer.mjs:955High-entropy token-like string (may be an id, hash or a credential)function vali…Key(hostSessionKey) { -
low Secrets in code
secret-high-entropy-tokenscripts/openclaw-host-installer.mjs:965High-entropy token-like string (may be an id, hash or a credential)export function buil…oad(args) { -
low Secrets in code
secret-high-entropy-tokenscripts/openclaw-host-installer.mjs:966High-entropy token-like string (may be an id, hash or a credential)const hostSessionKey = vali…Key(args.hostSessionKey);
-
low Secrets in code
secret-high-entropy-tokenscripts/openclaw-host-installer.mjs:1004High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)const installArgs = buil…oad({detector
Files scanned: 6. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
frontmatter-yamlSKILL.md: the frontmatter is not valid YAML (YAML parse error: Nested mappings are not allowed in compact mappings at line 2, column 14: description: Install Hirey AI (people-to-people matching for jobs, hiring, hous… ^ ); fields were read line by line. The usual cause is a colon inside an unquoted value - warning
body-longSKILL.md body ≈ 11404 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 64/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 40Execution cost. Instruction body is 11404 tokens: crowds the task out of the window
- 60Tools and files. Uses tools (bash, web, git, node) that frontmatter does not declare
- 100Steps. 166 steps
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 22 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 (13 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 805: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -2localhost URLs: will not work for another user
- -32 of 3 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +4Structure: 17 headings
- +3Step-by-step instructions: 166 items
- +4Has examples (4 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 56.