BC typescript-package-manager
Expert 10x Software engineer specializing in TypeScript with deep knowledge of all popular package management tools including npm, yarn, pnpm, bun, and deno. Use when asked to configure package managers, manage dependencies, set up workspaces, resolve package conflicts, optimize package.json files, troubleshoot installation issues, or work with monorepos. Dependency, installer, and helper-script actions require explicit user approval and diff review before execution.
As a process C 56/100 · Has gaps — weak spots: result and completion, when it triggers, running it twice
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
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
- 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
✓ No critical or high findings
Medium and low: 7
-
medium Dangerous commands
cmd-pipe-to-shell-known-hostscripts/bun-workflow.md:14Pipe-to-shell installer from a well-known host (still executes remote code)curl -fsSL https://bun.sh/install | bash
-
medium Dangerous commands
cmd-pipe-to-shell-known-hostscripts/bun-workflow.md:530Pipe-to-shell installer from a well-known host (still executes remote code)curl -fsSL https://bun.sh/install | bash
-
medium Dangerous commands
cmd-pipe-to-shell-known-hostscripts/pnpm-workflow.md:51Pipe-to-shell installer from a well-known host (still executes remote code)curl -fsSL https://get.pnpm.io/install.sh | sh -
-
medium Dangerous commands
cmd-pipe-to-shellSKILL.md:309Downloads and executes remote code from an unrecognised host (pipe to shell) (quoted — discussed, not commanded)- **bun-workflow.md** / **bun-workflow.js.txt** - Complete bun workflow for ultra-fast package management (rename to `.js` before running). The documented Bun installer one-liners (`curl … | bash`, `i
quoted -
low Dangerous commands
cmd-pipe-to-shell-known-hostscripts/bun-workflow.js.txt:195Pipe-to-shell installer from a well-known host (still executes remote code) (quoted — discussed, not commanded)cmd: 'curl -fsSL https://bun.sh/install | bash # macOS/Linux\n powershell -c "irm bun.sh/install.ps1 | iex" # Windows',
quoted -
low Dangerous commands
cmd-pipe-to-shell-known-hostscripts/bun-workflow.js.txt:264Pipe-to-shell installer from a well-known host (still executes remote code) (quoted — discussed, not commanded)console.log(` ${c.cyan('curl -fsSL https://bun.sh/install | bash')} # macOS/Linux`);quoted -
low Dangerous commands
cmd-pipe-to-shell-known-hostSKILL.md:13Pipe-to-shell installer from a well-known host (still executes remote code) (security demo / example; quoted — discussed, not commanded)- **Verify remote installers.** Any documented one-liner that fetches code from the network (for example `curl -fsSL https://bun.sh/install | bash` or `powershell -c "irm bun.sh/install.ps1 | iex"`) e
demoquoted
Files scanned: 14. 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 56/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 5 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 128 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3066 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 13 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)
- +3Output format is not stated: the model decides each time
- -225 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +3Description length 471: enough signal without eating the budget
- +4Structure: 27 headings
- +3Step-by-step instructions: 128 items
- +4Has examples (8 code blocks)
- +4Reference files are cited in the instructions (2 of 2)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 86.