BD dsh-create-upgrade-guide
Use when a deepseek-harness change breaks an externally perceptible surface (CLI, profiles, cordis.yml or settings keys, persisted user data, SDK or wire APIs, published package entry points), or when changing a surface that an unreleased upgrade guide already covers, to write or update docs/upgrade-guide/v<version>/<item>/guide.md.
This skill writes migration guides when deepseek-harness changes break visible surfaces—CLI, configs, APIs, package entry points. It promises to generate docs in the right folder with proper structure.
Grade B, quality score 75, but process score dropped to 41. The catch: broken_references_missing_files is true, meaning the skill references files that don't exist. No lint errors or critical findings, yet the gap between quality and process suggests the docs may generate but the surrounding structure is incomplete.
Install if you have folder scaffolding in place and can fix broken links manually. If you expect a complete out-of-the-box solution, verify which files the skill actually needs first.
yml or settings keys, persisted user data, SDK or wire APIs, published package entry points), or when changing a surface that an unreleased upgrade guide…
As a process D 41/100 · Unfinished process — References files that are not bundled: ../../../docs/cookbook/reviewing-persistence-type-changes.md, ../dsh-doc/templates/upgrade-guide.md, ../../notes/README.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 · 0
✓ No critical or high findings
Files scanned: 1. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: ../../../docs/cookbook/reviewing-persistence-type-changes.md - warning
missing-refreference to a missing file: ../dsh-doc/templates/upgrade-guide.md - warning
missing-refreference to a missing file: ../../notes/README.md - warning
missing-refreference to a missing file: ../dsh-prose-standard/SKILL.md - warning
missing-refreference to a missing file: ../../../docs/AGENTS.md
Process rating: all ten parameters 41/100
- 0Tools and files. 5 referenced file(s) missing: ../../../docs/cookbook/reviewing-persistence-type-changes.md, ../dsh-doc/templates/upgrade-guide.md, ../../notes/README.md
- 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. 3 mutating operations with no state check
- 60Result and completion. Output format stated, no completion criterion
- 100Steps. 11 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 835 tokens
- high The skill tells the model to perform an irreversible action with no human approval
- low The response is described with custom markup (3 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)
- +1No license
- +2Single-language instructions
- +3Description length 334: enough signal without eating the budget
- +4Structure: 6 headings
- +3Step-by-step instructions: 11 items
- +3Output format is stated explicitly
- +4Has examples (1 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 75.