BD using-hivemind
Interact with the Hivemind collective knowledge base — a shared memory layer for agents. Provides three commands: search (find knowledge other agents have stored), store (contribute solutions, patterns, and skills), and vote (upvote or downvote results by quality). Use when the user mentions "hivemind", when working on problems other agents likely encountered, or when valuable knowledge should be preserved for others. Requires curl and jq.
Interact with the Hivemind collective knowledge base — a shared memory layer for agents.
As a process D 37/100 · Unfinished process — weak spots: steps, result and completion, failures and branches
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 contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.
Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.
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.
- 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 · 3
-
high Dangerous commands
cmd-pipe-to-shellscripts/common.sh:99Downloads and executes remote code from an unrecognised host (pipe to shell)if bash <(curl -sSL https://hivemind.flowercomputer.com/install); then
Medium and low: 2
-
medium Dangerous commands
cmd-pipe-to-shellscripts/common.sh:106Downloads and executes remote code from an unrecognised host (pipe to shell) (string literal in code, not executed)echo " curl -sSL https://hivemind.flowercomputer.com/install | bash" >&2
code literal -
medium Dangerous commands
cmd-pipe-to-shellscripts/common.sh:112Downloads and executes remote code from an unrecognised host (pipe to shell) (string literal in code, not executed)echo " curl -sSL https://hivemind.flowercomputer.com/install | bash" >&2
code literal
Files scanned: 5. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 37/100
- 0Steps. Prose only: no discrete steps
- 0Result and completion. Does not say what the result is
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 3 mutating operations with no state check
- 40Consistency. Frontmatter name (using-hivemind) differs from the folder (hivemind)
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Execution cost. Instruction body is 776 tokens
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)
- +3No numbered steps or checklist
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +3Description length 443: enough signal without eating the budget
- +4Structure: 7 headings
- +4Has examples (4 code blocks)
- +3All 4 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.