skills/mine.implementation-review/SKILL.md
Use when mine.orchestrate Phase 3 runs the post-execution quality gate. Reviews changed files against design doc and task files using a Sonnet subagent.
npx skillsauth add NodeJSmith/Claudefiles mine.implementation-reviewInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Post-execution quality gate. After /mine.orchestrate finishes, this reviews the full implementation against the original design doc and task files. Uses a Sonnet subagent for structured review across 7 categories.
$ARGUMENTS — path to a feature directory (design/specs/NNN-feature/) or a design.md file. If empty, find the most recently modified design/specs/*/design.md and confirm before proceeding.
If $ARGUMENTS points to a design/specs/NNN-*/ directory, use it directly.
If $ARGUMENTS points to a design.md file, the feature directory is one level up.
If $ARGUMENTS is empty:
Glob: design/specs/*/design.md
Sort by modification time, take the most recent. The feature directory is one level up. Confirm:
AskUserQuestion:
question: "Found feature at <feature_dir>. Review its implementation?"
header: "Confirm feature"
multiSelect: false
options:
- label: "Yes — review it"
- label: "No — let me specify the path"
description: "Tell me the correct feature directory and I'll use that"
Read <feature_dir>/design.md in full.
Read all <feature_dir>/tasks/T*.md files in order. If no task files exist, proceed with design-only review and note this in the summary.
Run git-branch-diff-files to find which files were changed since the branch diverged from its base. This handles base-branch detection automatically (closest remote branch, then default branch fallback):
git-branch-diff-files
If still empty (e.g., no commits yet), fall back to:
git diff --name-only HEAD~1
Read each changed file. If the list is large (more than 15 files), prioritize files referenced in the task Prompt sections first.
Run get-skill-tmpdir mine-impl-review and use <dir>/review.md for the review output.
Read ~/.claude/skills/mine.implementation-review/reviewer-prompt.md.
Launch a general-purpose subagent with model: sonnet. Pass this prompt (fill in bracketed values):
You are reviewing a completed caliper v2 feature implementation.
## Design doc
<full design.md content>
## Task files
<full content of each T*.md in order, separated by "--- T<NN> ---" headers>
## Changed files
<for each changed file: filename header + full content>
## Your instructions
<full reviewer-prompt.md content>
Write your complete structured review to: <temp file path>
The subagent will write the review to the temp file.
Read the temp file. Format the results clearly:
N. <name>: PASS|WARN|FAIL — notePhase 3 is the final output. The caller (mine.orchestrate) handles all gate logic, status updates, and next-step decisions. This skill does not prompt the user or update design.md.
development
Use when the user says: 'create an issue', 'file an issue', 'open an issue', 'write an issue', 'new issue for this'. Codebase-aware issue creation — investigates the code to produce well-structured issues with acceptance criteria, affected areas, and enough detail for automated triage.
development
Use when the user says: 'triage issues', 'classify issues by complexity', 'assess issue complexity', 'find quick wins', 'which issues are small', 'batch issue assessment'. Batch codebase-aware issue triage — parallel Haiku subagents assess actual complexity and effort by reading the code, not just titles.
development
Use when the user says: "review my changes", "run the reviewers", "code and integration review", "readability review", "maintainability review", "sniff test this", "WTF check", "code smells", "is this code any good", "fresh eyes on this branch", "review this directory", "check this module". Dispatches three parallel reviewers — code, integration, and a readability pass — and consolidates findings into one prioritized report.
development
Use when the user says: "clean code check", "style review", "LLM smell check", "code hygiene", "nitpick this", "style check", "find style sins", "nitpicker review", "anal retentive review", "exhaustive style review", "no-filter style report". Dispatches three parallel stylistic checkers — llm-checker (training-bias patterns), lazy-checker (deferred debt), and nitpicker (style hygiene) — and consolidates findings into a report organized by checker with a Summary section for orchestration consumption.