CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

system-profile

Profile a target (script, process, GPU, memory, interconnect) for performance analysis. Use when user says "profile", "benchmark", "bottleneck", or wants performance analysis.

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

The canonical home for this skill is aris-system-profile in OpenLAIR/dr-claw

SKILL.md
Quality
Evals
Security

Quality

Content

75%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, instruction-only skill body with concrete tooling, precise measurement dimensions, and a thoughtful instrumentation-safety mechanism (changelog + cleanup). The main gaps are mild redundancy in the flexibility reminders and the absence of a single example instrumentation pattern despite making code instrumentation a core strategy.

Suggestions

Cut one of the two repeated flexibility reminders ("Don't limit yourself to the examples below" vs. "don't use a fixed template") to tighten the intro and Step 2.

Add one minimal instrumentation snippet (e.g., a timing context manager or NCCL-collective wrapper) since writing instrumentation code is a headline capability of the skill.

Add an explicit validation step after instrumentation (e.g., re-run the target to confirm behavior is unchanged before collecting measurements).

DimensionReasoningScore

Conciseness

The body is efficient: tool lists are bare commands ("perf stat", "/usr/bin/time -v", "NCCL_DEBUG=INFO"), and it never explains concepts Claude already knows. Minor trimmable redundancy: "including writing instrumentation code when needed" duplicates Step 2, and "Don't limit yourself to the examples below" plus "don't use a fixed template" restate the same flexibility point twice. This places it above anchor 3 but short of anchor 5's every-token-earns-its-place.

4 / 5

Actionability

Concrete commands per category, precisely measurable dimensions ("allocated vs reserved vs peak", "NVLink vs PCIe topology impact"), a mandated changelog table, and a fixed output location (./profile_output/) make the guidance mostly executable. It misses anchor 5 because, despite code instrumentation being a core capability, no example instrumentation pattern (e.g., a decorator or context-manager snippet) is shown; it is clearly above anchor 3's pseudocode-level guidance.

4 / 5

Workflow Clarity

A clear 6-step sequence with real checkpoints: ask the user if $ARGUMENTS is unclear (Step 1), check tool availability before running (Step 5), and a mandatory changelog plus cleanup offer governing the code-modification risk. It falls short of anchor 5 because there is no explicit validate-instrumentation-then-retry feedback loop, but checkpoints are present rather than absent, keeping it above anchor 3.

4 / 5

Progressive Disclosure

Well-organized into six labeled sections, self-contained with no nested or buried references, and nothing that is clearly misplaced inline. It cannot take the under-50-lines exception (the body is ~95 lines), and per-category tool cookbooks or instrumentation examples could plausibly live in reference files, so anchor 4's 'minor organization gaps' fits better than anchor 5.

4 / 5

Total

16

/

20

Passed

Description

83%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A well-constructed description that clearly states what the skill does and when to use it, with natural quoted trigger terms. Its main weakness is trigger coverage that omits common synonyms and a capability list focused on targets rather than the full range of actions (instrumentation, reporting).

Suggestions

Add common user phrasings as triggers, e.g. "slow", "optimize", "latency", or "flamegraph", to broaden natural-keyword coverage.

Mention the concrete deliverable (bottleneck report with ranked recommendations) in the description so the 'what' covers outcomes, not just targets.

DimensionReasoningScore

Specificity

"Profile a target (script, process, GPU, memory, interconnect)" names the domain and enumerates concrete target types, giving several specific specifics with only minor gaps in action coverage (no mention of deliverables like reports or instrumentation). It sits above anchor 3 (which expects only 1-2 concrete actions) but below anchor 5's fully comprehensive action list.

4 / 5

Completeness

It explicitly answers both questions: the "what" ("Profile a target (script, process, GPU, memory, interconnect) for performance analysis") and the "when" with concrete quoted trigger phrases ("Use when user says 'profile', 'benchmark', 'bottleneck'..."). This matches the anchor-5 example structure exactly, and is clearly stronger than anchor 4's weaker 'when' clause.

5 / 5

Trigger Term Quality

The quoted triggers "profile", "benchmark", "bottleneck", plus "wants performance analysis", are phrases users naturally say, giving good keyword coverage. It falls short of anchor 5's comprehensive synonym coverage (missing terms like "slow", "optimize", "latency", "flamegraph", "speed up").

4 / 5

Distinctiveness Conflict Risk

Profiling/performance analysis with these triggers occupies a clear niche with minimal conflict risk, though "performance analysis" and "benchmark" could overlap with a dedicated benchmarking or debugging skill. Minor overlap risk with closely related skills matches anchor 4 rather than anchor 5's minimal conflict.

4 / 5

Total

17

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

wanshuiyin/Auto-claude-code-research-in-sleep

Path

skills/skills-codex/system-profile/SKILL.md

Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.