Code review
Review code changes by collecting the review target, researching context, checking risks, and reporting findings before summary.From its SKILL.md
npx -y skills add modiqo/skillspec --skill code-reviewAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
SKILL.md
2.2 KB, as published. Nobody here has run it
Code Review
Review code changes by collecting the review target, researching context, checking risks, and reporting findings before summary.
This skill is a thin loader for the colocated skill.spec.yml. The spec is the source of truth for routes, rules, dependencies, imports, resources, recipes, tests, and trace requirements.
Runtime Contract
-
Load
./skill.spec.ymlfrom this skill folder before taking task actions. -
When the
skillspecCLI is available, run:skillspec decide ./skill.spec.yml --input='<user task>' --trace-dir "${PWD}/.skillspec/traces" -
Strip skill invocation prefixes such as
/my-skill,$my-skill, or/rote-shell-specbefore passing--input. -
Preserve the emitted trace
run_dir. -
When the CLI is available after a trace exists, run
skillspec trace align ./skill.spec.yml --decision-trace <run_dir>and report the alignment status with the trace path. -
Follow the selected route, matched rules, forbids, elicitations, dependencies, imports, recipes, and closures from
skill.spec.yml. -
If the CLI is unavailable, read
skill.spec.ymldirectly and apply its rules manually. Do not expand this loader into a second source of truth.
Quick Commands
skillspec validate ./skill.spec.yml
skillspec imports check ./skill.spec.yml
skillspec test ./skill.spec.yml
skillspec deps check ./skill.spec.yml
skillspec explain ./skill.spec.yml --input='<user task>' --trace-dir "${PWD}/.skillspec/traces"
skillspec trace align ./skill.spec.yml --decision-trace "${PWD}/.skillspec/traces/<run-id>"
Completion Report
When reporting completion, include the selected route, the SkillSpec trace run_dir, the skillspec trace align status (pass, fail, or unproven), key failed or unproven alignment checks, and the concrete execution evidence ids or files.
Route Hints
current_pr: Review current pull requestdiff_to_main: Review diff to mainspecific_paths: Review specific pathssecond_opinion: Provide review synthesis from supplied evidence