メニュー
Detects time and space complexity hotspots via AST scan. Use when code feels slow, before performance-sensitive merges, or to find O(n²) regressions.
デフォルトでは、最初にソースを確認する Prompt が選択されています。直接コマンドに切り替えるか、ローカルコピーをダウンロードすることもできます。
インストールを決める前に、SKILL.md と SkillsMP に表示されている付属ファイルをお読みください。
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
直接コマンドでは確認用 Prompt が省略されます。実行前にソースを確認してください。
npx skills add https://github.com/athola/claude-night-market --skill performance-reviewコマンドは1行のまま表示されます。コピー前に横へスクロールして全体を確認してください。
ローカルで確認しますか？SkillsMP が現在取得できるファイルをダウンロードできます。
SOC 職業分類に基づく
Turn hunches into accepted results: worthiness score, evidence bar, research-to-rules. Use when vetting ideas. Not for QA; use night-market-validation-and-qa.
Generates and self-executes a diff-derived test plan for a PR. Use when validating PR changes before merge. Do not use for code review; use sanctum:pr-review.
Curate the web-capture index. Use when the capture backlog grows, captures sit unprocessed at seedling/pending, or to surface stored research during work.
SKILL.md を表示中
| name | performance-review |
| description | Detects time and space complexity hotspots via AST scan. Use when code feels slow, before performance-sensitive merges, or to find O(n²) regressions. |
| alwaysApply | false |
| category | code-quality |
| tags | ["performance","complexity","algorithms","ast","static-analysis"] |
| tools | [] |
| usage_patterns | ["hotspot-detection","complexity-review","pre-merge-performance-check"] |
| complexity | advanced |
| model_hint |
| deep |
| estimated_tokens | 280 |
| progressive_loading | true |
| dependencies | ["imbue:proof-of-work","imbue:review-core","imbue:structured-output"] |
| modules | ["modules/time-complexity.md","modules/space-complexity.md","modules/gauntlet-integration.md","modules/kuva-visualization.md","modules/memory-allocation-lenses.md"] |
Static-analysis review of time and space complexity hotspots.
The skill runs in three escalating tiers. Tier 1 uses Python's
stdlib ast and always runs. Tier 2 uses gauntlet's tree-sitter
parser to extend detection across languages when gauntlet is
installed. Tier 3 uses the gauntlet code graph to upgrade
severity when hotspots reach other hotspots transitively. If
gauntlet is missing, Tiers 2 and 3 no-op and Tier 1 still
produces useful findings on Python source.
/performance-review # scan changed files
/performance-review path/to/file.py # scan one file
/performance-review --tier 1 # force Tier 1 only
Programmatic use:
from pensive.skills.performance_review import PerformanceReviewSkill
skill = PerformanceReviewSkill()
result = skill.analyze(context, "src/module.py")
for f in result.issues:
print(f"[{f.severity}] {f.file}:{f.line} {f.message}")
Skill(parseltongue:python-performance)
instead: that skill drives cProfile, py-spy, and benchmarks.Skill(pensive:code-refinement) whose algorithm-efficiency
module covers broader optimization patterns. This skill
detects; that skill teaches.Skill(leyline:loop-optimization) for the hand-vs-compiler rule.
This skill flags hotspot shapes, not transformation choices.Skill(pensive:architecture-review).perf-review:context-establishedperf-review:scan-completeperf-review:findings-categorizedperf-review:integration-checkedperf-review:report-generatedperf-review:findings-verifiedperf-review:context-established)git diff --name-only. If invoked with a path, scope to that.perf-review:scan-complete)Load modules/time-complexity.md for the time-side patterns and
modules/space-complexity.md for space-side. Each module
documents the AST shape of every detector.
Alongside the automated scan, load
modules/memory-allocation-lenses.md and apply its three
manual lenses (unbounded external-source collections, hot-path
recompute, serial blocking I/O) by reading the target files.
For each Python target file, call:
from pensive.skills.performance_review import PerformanceReviewSkill
result = PerformanceReviewSkill().analyze(context, path)
The visitor walks the AST once and emits ReviewFinding records.
perf-review:findings-categorized)Group findings by severity:
Within a severity, sort by file then line. Suppress findings the user has explicitly marked acceptable (TODO/comment markers) at module-load time of the target.
perf-review:integration-checked)Load modules/gauntlet-integration.md for the contract.
If gauntlet is installed, run Tier 2 on non-Python files that
were skipped at Step 2. If a .gauntlet/graph.db exists in the
working tree, run Tier 3 to upgrade severities based on
transitive hotspot reachability.
If gauntlet is missing, this step is a no-op and the report notes "Tier 2/3 not available: install gauntlet for multi-language and call-chain coverage."
perf-review:report-generated)Emit a markdown report:
## Performance Review: <target>
### HIGH (<count>)
- src/foo.py:42: Nested loop over the same iterable 'items'.
Suggestion: sort + two pointers, or hash-set membership.
### MEDIUM (<count>)
- ...
### LOW (<count>)
- ...
Tier coverage: 1 (always) | 2 (gauntlet ✓/✗) | 3 (graph ✓/✗)
The report is informational. Apply fixes via
Skill(pensive:code-refinement) or hand-merge.
| Tier | Source | When it runs | What it covers |
|---|---|---|---|
| 1 | stdlib ast | Always (Python source only) | T1-T6, S1-S3 |
| 2 | gauntlet.treesitter_parser | When gauntlet importable | Same patterns adapted to JS/TS, Go, Rust, Java, C/C++ |
| 3 | gauntlet.graph.GraphStore | When .gauntlet/graph.db exists | Severity upgrade via transitive call chains |
Findings use the shared ReviewFinding dataclass from
pensive.skills.base:
ReviewFinding(
file="src/module.py",
line=42,
severity="HIGH", # LOW | MEDIUM | HIGH | CRITICAL
category="time", # time | space
message="Nested loop over the same iterable 'items'.",
suggestion="Sort + two pointers, or hash-set membership.",
anchor="verbatim source text at file:line",
code_snippet="",
)
This shape matches every other pensive review skill, so the
findings can flow into Skill(pensive:unified-review) without
translation.
| Dependency | Required? | Effect when missing |
|---|---|---|
gauntlet.treesitter_parser | Optional | Tier 2 returns []; Python coverage unchanged |
gauntlet.graph.GraphStore | Optional | Tier 3 returns []; severities are not upgraded |
The optional-import contract follows the precedent in
plugins/leyline/src/leyline/tokens.py:25-32 and
plugins/gauntlet/hooks/pr_blast_radius.py:52-56: try-import
to module-level sentinels, then early-return on None inside
each tier helper. See modules/gauntlet-integration.md for the
exact code shape.
modules/time-complexity.md: T1-T6 detector patterns and AST
shapes.modules/space-complexity.md: S1-S3 detector patterns.modules/gauntlet-integration.md: Tier 2/3 contract,
fallback semantics, examples.modules/kuva-visualization.md: Rendering benchmark data as
charts with kuva (criterion, pytest-benchmark, ad-hoc tables).
Covers when chart evidence satisfies proof-of-work requirements.modules/memory-allocation-lenses.md: Manual review lenses
(not AST detectors) for unbounded collections fed from
external sources, hot-path recompute that should be memoized,
and serial blocking I/O over unbounded sets. Apply by reading
the code; the detector-test rule in Testing does not cover
these because nothing is automated.A perf-review finding is only useful if the caller can confirm it is real. Use this checklist before treating any finding as worth fixing:
cProfile, py-spy, or the
language-specific equivalent on the hotspot. The findings
pinpoint AST shapes; the profiler validates the runtime impact.benches/ exists, the
hotspot should show up in numbers, not just AST scans.[E1] (before) and [E2] (after).
When 3+ data points exist, render a kuva chart and attach it
to the PR (see modules/kuva-visualization.md).The Skill(imbue:proof-of-work) discipline applies: claims like
"the hotspot is fixed" require evidence, not assertion.
A test file already lives at
plugins/pensive/tests/skills/test_performance_review.py covering
the AST-shape detectors. Two rules for changes here:
The Iron Law applies: a new detector without a failing test first is a request to skip TDD on a code-analysis component, which is exactly the place where TDD pays off most.
perf-review:findings-verified)Every finding must cite a real location and a verbatim anchor. Write
findings to .review/findings.json and confirm each citation resolves:
python plugins/imbue/scripts/citation_verifier.py \
--findings .review/findings.json --repo-root .
Drop or label UNVERIFIED any finding the verifier fails (exit 1); only
verified findings enter the report. See Skill(imbue:review-core) Step 5
and Skill(imbue:structured-output) for the schema.
[] rather than raising.Skill(pensive:unified-review) without
translation when invoked from the unified entry point.Location + verbatim Anchor
confirmed by citation_verifier.py (exit 0), or unverified
findings were dropped or labeled UNVERIFIED