CtrlK
BlogDocsLog inGet started
Tessl Logo

analyze-crash

Stack Trace Crash Analysis for dd-trace-dotnet

55

Quality

69%

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

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 strongly actionable, well-sequenced analysis workflow with concrete commands, fallbacks, and a complete output template. Its weaknesses are redundancy in the GitHub-link and PR-link guidance (stated multiple times) and the absence of explicit validation checkpoints in the workflow.

Suggestions

Consolidate the GitHub-link rules into the single "GitHub Link Generation" section and remove the duplicated "Always include GitHub links" and path-construction repetitions.

Add explicit validation steps, e.g., after saving the report, verify the file exists and report the confirmed absolute path back to the user.

Move the "GitHub Link Generation" section adjacent to "Output Format" (or fold it in) so the Analysis Workflow proceeds directly from Phase 1 through Phase 5.

DimensionReasoningScore

Conciseness

The body is mostly domain-specific instruction with no teaching of concepts Claude already knows, but contains real redundancy: GitHub-link formatting rules appear in three places ("GitHub Link Generation", the path-construction example, and "Always include GitHub links"), and the prefer-PR-links guidance is repeated in Phase 5 and again in Important Guidelines. This is more than the "minor instances" of anchor 4, matching anchor 3 (could be tightened).

3 / 5

Actionability

Fully executable throughout: exact glob patterns ("**/Datadog.Tracer.Native/**/{filename}"), exact git log commands, a copy-paste PowerShell command with an explicit quoting caveat, a concrete output filename format (crash-analysis-{YYYYMMDD-HHMMSS}.md), and a complete markdown output template. Matches anchor 5 (copy-paste ready, covers common cases).

5 / 5

Workflow Clarity

Five clearly sequenced phases with fallback chains (direct path match, then glob, then filename) and explicit "continue with missing information" handling. However, there are no explicit validation checkpoints (e.g., verifying the output file was written or confirming a reconstructed path resolved correctly), so it fits anchor 4 rather than anchor 5's explicit validation steps and feedback loops.

4 / 5

Progressive Disclosure

A single-file skill (no bundle files exist) with well-organized sections and appropriate inlining for its length. Minor gaps: the "GitHub Link Generation" section is misplaced between "Analysis Workflow" and Phase 1 rather than near the output guidelines, and the ~60-line output-format template is a candidate for a reference file. Good structure with minor organization gaps matches anchor 4, not the clean split-and-navigation of anchor 5.

4 / 5

Total

16

/

20

Passed

Description

52%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 highly distinctive thanks to repo-specific naming, but it functions as a title rather than a capability description: it names no concrete actions, includes no trigger guidance, and omits common crash-reporting synonyms like "dump" or "SIGSEGV".

Suggestions

Add a 'Use when...' clause, e.g., "Use when analyzing a crash dump, stack trace, or SIGSEGV from the dd-trace-dotnet .NET tracer".

List concrete actions: "Parses and classifies stack frames, locates the crashing code in the repository, and reconstructs the crash flow".

Include natural trigger synonyms users actually say: crash, dump, minidump, stack trace, access violation, segfault.

DimensionReasoningScore

Specificity

"Stack Trace Crash Analysis for dd-trace-dotnet" names the domain clearly but lists no concrete actions (e.g., parse stack frames, classify frames, locate crash code, reconstruct crash flow). This matches anchor 2 (names domain, actions minimal/generic) rather than anchor 3, which requires at least 1-2 concrete actions to be stated.

2 / 5

Completeness

There is a clear "what" (crash analysis for the dd-trace-dotnet repository) but no "when" clause at all; the judging guidelines explicitly cap completeness at 3 for a missing 'Use when...' or equivalent trigger guidance.

3 / 5

Trigger Term Quality

"Stack Trace", "Crash", and "Analysis" are natural terms a user would say, but common variations and synonyms are missing ("dump", "minidump", "SIGSEGV", "access violation", "fatal error"). Some relevant keywords with missing synonyms matches anchor 3, not the comprehensive coverage of anchor 4.

3 / 5

Distinctiveness Conflict Risk

The explicit reference to the dd-trace-dotnet repository gives a clear niche with distinct triggers; generic crash-analysis or debugging skills would not match this description. Minimal conflict risk, matching anchor 5.

5 / 5

Total

13

/

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.

Validation — 14 / 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.