AB zerodha-kite-cli-router
Route natural-language trading/account queries to the correct `zerodha` CLI command with exact flags, validation constraints, and synonym mapping. Use when a user asks to view prices, place/modify/cancel orders, manage auth/profile/config, work with holdings/positions/margins/GTT/MF flows, or asks "which zerodha command should I run?"
As a process B 68/100 · Nearly there — weak spots: consistency, running it twice, progress reporting
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 · 4
✓ No critical or high findings
Medium and low: 4
-
low Dangerous commands
cmd-pipe-to-shell-known-hostSKILL.md:20Pipe-to-shell installer from a well-known host (still executes remote code) (quoted — discussed, not commanded)- Linux/macOS (`curl`): `curl -fsSL https://raw.githubusercontent.com/jati…998/zerodha-kite-cli/main/scripts/install.sh | sh`
quoted -
low Dangerous commands
cmd-pipe-to-shell-known-hostSKILL.md:21Pipe-to-shell installer from a well-known host (still executes remote code) (quoted — discussed, not commanded)- Linux/macOS (`wget`): `wget -qO- https://raw.githubusercontent.com/jati…998/zerodha-kite-cli/main/scripts/install.sh | sh`
quoted -
low Dangerous commands
cmd-execpolicy-bypassSKILL.md:23Runs PowerShell with execution policy bypassed (quoted — discussed, not commanded)- Windows CMD: `powershell -NoProfile -ExecutionPolicy Bypass -Command "irm https://raw.githubusercontent.com/jati…998/zerodha-kite-cli/main/scripts/install.ps1 | iex"`
quoted -
low Dangerous commands
cmd-pipe-to-shell-known-hostSKILL.md:343Pipe-to-shell installer from a well-known host (still executes remote code) (quoted — discussed, not commanded)- Linux/macOS: `curl -fsSL https://raw.githubusercontent.com/jati…998/zerodha-kite-cli/main/scripts/install.sh | sh`
quoted
Files scanned: 2. 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 68/100
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 9 mutating operations with no state check
- 40Consistency. Frontmatter name (zerodha-kite-cli-router) differs from the folder (zerodha-kite)
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Failures and branches. 23 branches
- 100Steps. 189 steps
- 100Execution cost. Instruction body is 3780 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 21 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (38 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)
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +3Description length 336: enough signal without eating the budget
- +4Structure: 33 headings
- +3Step-by-step instructions: 189 items
- +3Output format is stated explicitly
Quality base 70; lint remarks subtract, signals add up to 100. Result: 83.