root-cause-tracing

Use when errors occur deep in execution and you need to trace back to find the original trigger - systematically traces bugs backward through call stack, adding instrumentation when needed, to identify source of invalid data or incorrect behavior

Quality

73%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/kaizen/skills/root-cause-tracing/SKILL.md

Quality

Content

63%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 delivers an actionable, well-sequenced tracing workflow with concrete instrumentation code and a realistic worked example. Its weaknesses are conciseness bloat (verbose dot graphs, repetition, a dated anecdote) and a broken reference to a missing find-polluter.sh script with no bundle files provided.

Suggestions

Provide the referenced find-polluter.sh as a bundle script (or remove the '@find-polluter.sh' reference) so the actionability and progressive-disclosure gaps close.

Trim the two Graphviz 'dot' blocks to a short prose or bulleted decision rule, and remove the dated 'Real-World Impact' anecdote to tighten conciseness.

Add an explicit verification step to the tracing process (e.g., 'confirm the fix resolves the symptom and re-run the failing test') to lift workflow clarity.

Dimension	Reasoning	Score
Conciseness	The body is mostly focused and assumes Claude's competence, but two verbose Graphviz 'dot' blocks, a repeated console.error tip (in 'Adding Stack Traces' and again in 'Stack Trace Tips'), and a dated anecdote ('2025-10-03', '1847 tests passed') add padding that could be trimmed, fitting the score-3 anchor better than 4.	3 / 5
Actionability	Provides copy-paste-ready TypeScript instrumentation and a concrete 'npm test 2>&1 \| grep' command, but the referenced '@find-polluter.sh' script does not exist as a bundle file, leaving a minor gap that keeps it below 5.	4 / 5
Workflow Clarity	The 5-step tracing process (Observe → Find immediate cause → Ask what called this → Keep tracing up → Find original trigger) is clearly sequenced with a built-in 'is this the source? no - keeps going' loop, but lacks an explicit verification checkpoint confirming the fix resolves the symptom, so it stays at 4.	4 / 5
Progressive Disclosure	Section headers are well organized, but at ~190 lines everything is inlined with no working one-level-deep references — the lone '@find-polluter.sh' reference points to a non-existent file and the dot graphs / real example could live in separate files, matching the score-3 anchor.	3 / 5
	Total	14 / 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 strong description that pairs an explicit 'Use when' trigger with a clear, third-person statement of what the skill does and several concrete actions. The main gap is missing common synonyms ('root cause', 'debug', 'stack trace') that would broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — 'traces bugs backward through call stack, adding instrumentation when needed, to identify source of invalid data or incorrect behavior' — but stops short of comprehensive coverage, so it sits below the score-5 anchor.	4 / 5
Completeness	It explicitly answers both: what ('systematically traces bugs backward through call stack, adding instrumentation...to identify source of invalid data') and when ('Use when errors occur deep in execution and you need to trace back to find the original trigger'), matching the score-5 anchor with concrete trigger phrases.	5 / 5
Trigger Term Quality	Natural trigger phrases like 'errors occur deep in execution' and 'trace back to find the original trigger' plus 'call stack' give good coverage, but common synonyms such as 'root cause', 'debug', and 'stack trace' are absent, keeping it below 5.	4 / 5
Distinctiveness Conflict Risk	The deep-execution/call-stack tracing niche is mostly distinct with clear triggers, but it overlaps slightly with general debugging skills, so it does not reach the minimal-conflict score-5 anchor.	4 / 5
	Total	17 / 20 Passed

Validation

100%

Warnings & errors only

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: NeoLabHQ/context-engineering-kit
Path: plugins/kaizen/skills/root-cause-tracing/SKILL.md
Commit: 23e2428

Reviewed: 4 days ago

Table of Contents

Discovery Implementation Validation

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.