AD fx-cli-shape
Choose the mechanism and the names for any user-facing control in fx, and check changes against the agreed shape. Covers subcommands, arguments, flags and options, settings keys in settings.json and .fx.json, environment variables (FX_ env vars), slash commands, JSON output, and exit codes. Use when adding, renaming, deprecating, removing, or reviewing one, for example "add a flag", "add an option", "new env var", "make this configurable", "let users turn on X", "add a slash command", "remove this command", "what should this flag be called", "deprecate this flag", "should this be a flag or a setting", or a diff that touches src/builtins/commands.zig, src/core/cli/, src/core/config/, or adds an FX_ env read. Not for parser internals or writing documentation prose.
Choose the mechanism and the names for any user-facing control in fx, and check changes against the agreed shape.
As a process D 39/100 · Unfinished process — References files that are not bundled: scripts/cli_shape_registry.json
How to improve
- The text references files that are not there: add them or drop the references.
- 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 · 0
✓ No critical or high findings
Files scanned: 4. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: scripts/cli_shape_registry.json - note
edit-residuethe text marks something as outdated (lines 64, 103, 106): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 39/100
- 0Tools and files. 1 referenced file(s) missing: scripts/cli_shape_registry.json
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 50When it triggers. No condition that starts the skill
- 70Execution cost. Instruction body is 4225 tokens
- 100Steps. 48 steps
- 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 (6 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
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 10 example trigger phrases
- +4Description says when NOT to use the skill
- +3Description length 773: enough signal without eating the budget
- +4Structure: 9 headings
- +3Step-by-step instructions: 48 items
- +4Has examples (0 code blocks)
- +4Reference files are cited in the instructions (2 of 2)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 94.