BD skill-creator
Guides authoring, reviewing, and validating agent skills (SKILL.md + metadata.json + references/ + scripts/) in this Capgo skills repository and similar ones. Covers trigger and negative-trigger design, lean SKILL.md with a when-to-load reference index, traps over basics, verification and error-handling sections, version tagging of facts, subagent-oriented skills (main-agent vs subagent split), optional when_to_use frontmatter, inline snapshots with allowed-tools, skillgrade evals, and this repo's canonical skills/ to plugins/ mirroring and registration. Use when creating a new skill, tightening a skill's description or triggers, splitting a long skill into references, or fixing `bun run lint-skills` failures. Do not use for app documentation, README or marketing copy, or library code that is not a skill.
Guides authoring, reviewing, and validating agent skills (SKILL.md + metadata.json + references/ + scripts/) in this Capgo skills repository and similar ones.…
As a process D 47/100 · Unfinished process — References files that are not bundled: references/<topic>.md
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 · 1
✓ No critical or high findings
Medium and low: 1
-
low Broad scope
meta-dynamic-shellreferences/authoring-patterns.md:101Shell command executed automatically when the skill loads (Claude Code !`cmd` preamble)!`node -e "const fs=require('fs');if(!fs.existsSync('package.json'))process.exit(0);..."`
Files scanned: 6. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: references/<topic>.md
Process rating: all ten parameters 47/100
- 0Tools and files. 1 referenced file(s) missing: references/<topic>.md
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 6 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 100Steps. 36 steps
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1747 tokens
- low The response is described with custom markup (9 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
- +3Description length 816: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +4Structure: 15 headings
- +3Step-by-step instructions: 36 items
- +4Has examples (1 code blocks)
- +4Reference files are cited in the instructions (2 of 2)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 83.