CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

dotnet-trace-collect

Guide developers through capturing diagnostic artifacts to diagnose production .NET performance issues. Use when the user needs help choosing diagnostic tools, collecting performance data, or understanding tool trade-offs across different environments (Windows/Linux, .NET Framework/modern .NET, container/non-container).

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Medium

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./plugins/dotnet-diag/skills/dotnet-trace-collect/SKILL.md
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.

The body is a highly actionable, environment-aware decision guide with verified one-level-deep references and a validation checklist. Its main weaknesses are duplicated guidance across sections and per-symptom command detail that belongs in the reference files.

Suggestions

Deduplicate the repeated guidance: the .NET Framework-without-admin fallback appears in both the quick decision matrix and the Windows (.NET Framework) section, and the circular-buffer stop-trigger warning appears in three places — state each once and cross-reference.

Move the per-symptom command blocks (Slow Requests, Networking, Assembly Loading) into the corresponding reference files, keeping only the tool/provider selection rules in SKILL.md.

Add a short error-recovery loop to Step 3 (e.g. what to check and retry when a collection command fails or produces an empty trace) to strengthen workflow validation.

DimensionReasoningScore

Conciseness

The body is dense with non-obvious domain knowledge (PerfView trigger flags, System.Net provider names), but the .NET Framework-without-admin guidance, the stop-trigger warning, and the symptom list each appear twice (e.g. lines 74/98 and 83/247) — anchor 3's 'some unnecessary explanation or could be tightened'.

3 / 5

Actionability

Copy-paste-ready commands cover the common cases throughout: 'PerfView /ThreadTime collect /BufferSizeMB:1024 /CircularMB:2048', 'dotnet-trace collect -p <PID> --profile gc-verbose', and the exact provider spec 'Microsoft-Windows-DotNETRuntime:0x4:4' — fully executable, matching anchor 5.

5 / 5

Workflow Clarity

A clear 4-step sequence (understand environment → recommend tools → guide collection → recommend analysis) with a Validation checklist, but there are no explicit error-recovery feedback loops (what to do when a collection command fails) — anchor 4 rather than 5.

4 / 5

Progressive Disclosure

The tool reference lookup table routes each environment to one of five real, one-level-deep reference files, but the per-symptom command detail in the Networking and Assembly Loading sections is inlined in SKILL.md where the reference-split pattern would place it — anchor 4's 'good structure; minor organization gaps'.

4 / 5

Total

16

/

20

Passed

Description

71%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.

The description has an explicit, well-formed what-and-when structure scoped to .NET performance diagnostics, with clear environment dimensions. It is weakened by generic capability wording ("diagnostic artifacts", "performance data") and the absence of symptom-level and tool-name trigger terms users naturally say.

Suggestions

Replace the generic phrase 'capturing diagnostic artifacts' with concrete artifact types, e.g. 'capturing performance traces (and pointing to dump collection)' so the what-clause lists specific actions.

Add natural symptom-level trigger terms users actually say — 'high CPU', 'memory leak', 'slow requests', 'excessive GC' — to the Use-when clause to improve trigger matching.

Name the key tools (PerfView, dotnet-trace, perfcollect, dotnet-monitor) in the description to sharpen trigger terms and reduce overlap with the dump-collect skill.

DimensionReasoningScore

Specificity

Names the domain ("production .NET performance issues") and a concrete action ("capturing diagnostic artifacts"), but "artifacts" is generic and no specific artifact types (traces, dumps) or tools are named — matching anchor 3 rather than 4's 'several specific actions'.

3 / 5

Completeness

Explicitly answers both: what ("Guide developers through capturing diagnostic artifacts to diagnose production .NET performance issues") and when ("Use when the user needs help choosing diagnostic tools, collecting performance data, or understanding tool trade-offs...") with concrete trigger phrases, matching the anchor 5 example pattern.

5 / 5

Trigger Term Quality

Phrases like "choosing diagnostic tools", "collecting performance data" are relevant keywords, but common user phrasings ("high CPU", "memory leak", "slow requests", PerfView/dotnet-trace) are absent — anchor 3's 'some relevant keywords but missing common variations'.

3 / 5

Distinctiveness Conflict Risk

A clear .NET performance-diagnostics niche with environment-scoped triggers, but "capturing diagnostic artifacts" overlaps the sibling dump-collect skill — mostly distinct with minor overlap risk, i.e. anchor 4 rather than 5.

4 / 5

Total

15

/

20

Passed

Validation

100%

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

dotnet/skills

Path

plugins/dotnet-diag/skills/dotnet-trace-collect/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.