CD pro-launch
Build an app or product from 0 to 1, taste-first, with phase gates: references, naming, style frames, UI loop, launch video, GTM and shipping. Use for 做产品, 起名, 找参考, UI 太丑, launch plans.
Promises to take a product from zero to launch through phases: references, naming, style guide, UI, video, GTM, and shipping. In practice — 20 files with instructions, but some links are broken. Checks show quality score of 68: the logic holds, but process score sits at 42. No critical errors found, but the skill was never run against models and hasn't been sandboxed. Works for those willing to patch gaps in instructions themselves and not expecting full automation. Install if you need a process skeleton, not a ready-made tool.
Build an app or product from 0 to 1, taste-first, with phase gates: references, naming, style frames, UI loop, launch video, GTM and shipping.
As a process D 42/100 · Unfinished process — References files that are not bundled: scripts/domain_check.py, scripts/cutout_vector.sh, scripts/cut.swift
The same skill appears in 1 more place: agentic-awesome-skills
How to improve
- For Hermes the description must be one sentence under 60 characters; move the conditions to a "When to Use" section.
- 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: 20. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-long-hermesdescription is 185 chars; the Hermes authoring standard requires ≤ 60 (one sentence, ending with a period) - warning
missing-refreference to a missing file: scripts/domain_check.py - warning
missing-refreference to a missing file: scripts/cutout_vector.sh - warning
missing-refreference to a missing file: scripts/cut.swift - warning
missing-refreference to a missing file: scripts/vectorize.js - note
frontmatter-keyunknown frontmatter key "risk" - note
frontmatter-keyunknown frontmatter key "source" - note
frontmatter-keyunknown frontmatter key "source_repo" - note
frontmatter-keyunknown frontmatter key "source_type" - note
frontmatter-keyunknown frontmatter key "date_added" - note
frontmatter-keyunknown frontmatter key "tools" - note
frontmatter-keyunknown frontmatter key "license_source"
Process rating: all ten parameters 42/100
- 0Tools and files. 4 referenced file(s) missing: scripts/domain_check.py, scripts/cutout_vector.sh, scripts/cut.swift
- 0Result and completion. Does not say what the result is
- 0Failures and branches. Linear process with no failure handling
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 2 mutating operations with no state check
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 36 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1663 tokens
- 100Progress reporting. Reports progress
- low 12 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
- +2Single-language instructions
- +3Description length 185: enough signal without eating the budget
- +4Structure: 13 headings
- +3Step-by-step instructions: 36 items
- +4Has examples (0 code blocks)
- +4Reference files are cited in the instructions (17 of 17)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 68.