BD bundle
Vovk.ts `vovk bundle` CLI — packages composed TypeScript client as zero-dep publishable npm package. Covers `bundle.build` async fn, `tsdown@0.23.0` recipe, `outputConfig.origin` / `package` / `reExports` / `imports.validateOnClient: null`, `prebundleOutDir` / `outDir` / `keepPrebundleDir`, `--include`/`--exclude` segments, `--openapi-*` mixin flags. Use when user asks to "publish my API client", "ship an SDK to npm", "build a publishable client package", "bundle the Vovk client", "generate a distributable npm SDK", "use tsdown with vovk", or variations including why bundled package omits `openapi`/`schema` entry points. Note: `vovk bundle` is **TypeScript-only**. For Python/PyPI publishing, hand off to **`python`** skill. For Rust/crates.io publishing, hand off to **`rust`** skill. Does NOT cover in-project client codegen (`@/client`) → **`rpc`** skill.
Skill teaches the agent to package a TypeScript API client into an npm bundle via `vovk bundle`. Promises to cover the whole flow: from `tsdown@0.23.0` config to `--include`/`--exclude` flags and `--openapi-*` mixins. One instruction file with 2994 tokens, no code examples, no sandbox. Grade B (quality 86%, process 43%), no critical issues found. Triggers when users ask to "publish the client to npm" or "build an SDK". Catches only TypeScript; Python clients are out of scope.
Worth installing if your workflow regularly includes Vovk client publishing requests. Otherwise, it's a narrow tool for one job.
Vovk.ts vovk bundle CLI — packages composed TypeScript client as zero-dep publishable npm package. Covers bundle.build async fn, tsdown@0.23.0 recipe…
As a process D 43/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
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 · 0
✓ No critical or high findings
Files scanned: 1. 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 43/100
- 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
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 11 mutating operations with no state check
- 60Tools and files. Uses tools (bash, web, node) that frontmatter does not declare
- 100Steps. 18 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2994 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 866: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 6 example trigger phrases
- +4Structure: 17 headings
- +3Step-by-step instructions: 18 items
- +4Has examples (10 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 86.