CC thunder-deep-review
Reviews a pull request, diff, or branch against Thunderbolt's house rules (no any, type-over-interface, arrow fns, const/early-return, no error-swallowing or defensive code, useReducer at 3+ useState, useEffect discipline, route code-splitting, soft-deletes, integration-agnostic logic) and the 80 architecture invariants. Goes beyond bug-finding to catch architecture/abstraction-layer mistakes, undocumented intent, convention drift, bloat/supply-chain, and readability. Use when reviewing a PR/diff/branch, when the user says review, code-review, deep-review, or "review before merge". Read-only on the code: reports findings, never edits code or posts to the PR.
Reviews a pull request, diff, or branch against Thunderbolt's house rules (no any, type-over-interface, arrow fns, const/early-return, no error-swallowing or…
As a process C 64/100 · Has gaps — weak spots: failures and branches, running it twice, progress reporting
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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: 8. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
frontmatter-yamlSKILL.md: the frontmatter is not valid YAML (YAML parse error: Nested mappings are not allowed in compact mappings at line 2, column 14: description: Reviews a pull request, diff, or branch against Thunderbolt's hous… ^ ); fields were read line by line. The usual cause is a colon inside an unquoted value - warning
body-longSKILL.md body ≈ 7815 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 64/100
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 32 mutating operations with no state check
- 60Tools and files. Uses tools (read, web) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 7815 tokens
- 100Steps. 65 steps
- 100Consistency. Name and required fields are in place
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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 666: enough signal without eating the budget
- +4Structure: 21 headings
- +3Step-by-step instructions: 65 items
- +3Output format is stated explicitly
- +4Has examples (1 code blocks)
- +4Reference files are cited in the instructions (6 of 6)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 71.