CtrlK
BlogDocsLog inGet started
Tessl Logo

analyze-crash

Stack Trace Crash Analysis for dd-trace-dotnet

54

Quality

62%

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

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/analyze-crash/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

67%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 well-structured, actionable crash-analysis workflow with concrete commands and clear sequencing. Its main weakness is redundancy: GitHub-link guidance and the report template recur across several sections and could be consolidated.

Suggestions

Consolidate the GitHub-link guidance (currently spread across 'GitHub Link Generation', 'Path construction', and two 'Important Guidelines' bullets) into one section and reference it once.

Trim the full Output Format template, which duplicates the structure already produced by Phases 1-5; keep only the section headings and required fields.

Move the large worked example block in 'Path construction' into a short reference or trim it to one example, since the format and single-line example already convey the rule.

DimensionReasoningScore

Conciseness

The ~200-line body is mostly efficient but repeats GitHub-link guidance across multiple sections and fully re-templates a report structure already implied by the phases, which could be tightened.

3 / 5

Actionability

Provides concrete, executable commands (git log patterns, Glob patterns, mkdir/powershell output-directory commands) and a worked GitHub-link format with examples, with only minor gaps.

4 / 5

Workflow Clarity

Five phases are clearly sequenced with numbered sub-steps and fallback checkpoints (Glob retry, continue-with-missing-info); the read-only analysis scope means destructive-feedback-loop requirements do not apply.

4 / 5

Progressive Disclosure

No bundle files exist and everything is inline, but the body is well-organized into phases, an output template, and guidelines; the full output template and repeated link guidance could be trimmed for a cleaner overview.

4 / 5

Total

15

/

20

Passed

Description

57%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 is distinctive and names its niche clearly, but it is terse: it states what the skill does without listing multiple concrete actions and omits any explicit 'Use when' trigger guidance.

Suggestions

Add a 'Use when...' clause specifying trigger conditions, e.g. 'Use when an engineer pastes a crash stack trace from dd-trace-dotnet that needs triage and explanation.'

Expand the action list beyond a single verb to name concrete outputs (e.g. 'classifies stack frames, locates crashing code, reconstructs crash flow, links related PRs').

Include natural trigger synonyms such as 'crash', 'stacktrace', and 'core dump' so users phrasing the request differently surface the skill.

DimensionReasoningScore

Specificity

Names the domain (crash analysis for dd-trace-dotnet) and one concrete action ('Stack Trace Crash Analysis'), but lists only a single action rather than comprehensive coverage of capabilities.

3 / 5

Completeness

States a clear 'what' (stack trace crash analysis for dd-trace-dotnet) but provides no 'Use when...' clause or explicit trigger guidance, capping completeness at 3 per the rubric.

3 / 5

Trigger Term Quality

Contains relevant keywords ('Stack Trace', 'Crash Analysis', 'dd-trace-dotnet') but misses common natural variations users might say such as 'crash', 'stacktrace', or 'dump'.

3 / 5

Distinctiveness Conflict Risk

Targets a highly specific niche (crash stack-trace analysis for one named repository) with distinct triggers and minimal overlap risk with other skills.

5 / 5

Total

14

/

20

Passed

Validation

87%

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

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

relative_links

Relative link issues: 4 missing

Warning

Total

14

/

16

Passed

Repository
DataDog/dd-trace-dotnet
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.