root-cause-tracing

Systematically trace bugs backward through call stack to find original trigger. Use when errors occur deep in execution and you need to trace back to find the original trigger.

Quality

78%

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/root-cause-tracing/skills/root-cause-tracing/SKILL.md

Quality

Content

71%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 content delivers a clear, actionable tracing workflow with executable instrumentation examples, staying reasonably concise. Its main weakness is progressive disclosure: everything is inlined into a single file with no reference structure to offload detail.

Suggestions

Move the long 'Real Example' trace and defense-in-depth layers into a reference file (e.g. references/example-trace.md) and link to it from the main body to improve progressive disclosure.

Consolidate the duplicate stack-trace guidance currently split between 'Stack Trace Tips' and the 'Adding Stack Traces' section to reduce padding.

Add an explicit validate/retry loop (confirm the suspected root cause with a targeted test before fixing) to tighten the workflow's error-recovery checkpoint.

Dimension	Reasoning	Score
Conciseness	Largely lean and action-oriented with executable snippets, but the closing 'Stack Trace Tips' and 'Real-World Impact' sections repeat guidance already covered above, adding modest padding.	4 / 5
Actionability	Provides concrete, executable TypeScript and bash snippets (instrumentation logging, grep command, bisection) that cover the common cases, though the trace-chain arrows are illustrative rather than runnable code.	4 / 5
Workflow Clarity	A clear numbered five-step trace sequence is present with the diagnostic loop (run -> capture -> analyze), and the bisection step offers a stop-at-first-polluter checkpoint; the destructive-ops cap does not apply, but error-recovery feedback after a failed trace is only implicit.	4 / 5
Progressive Disclosure	The body is well-sectioned but monolithic within SKILL.md with no bundle files and no one-level-deep references, so it does not demonstrate the split-and-navigate pattern the top anchor rewards.	3 / 5
	Total	15 / 20 Passed

Description

85%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 clearly and explicitly states both what the skill does and when to use it, with a distinct niche and natural trigger phrasing. Its main limitation is listing a single action rather than a fuller set of concrete capabilities.

Dimension	Reasoning	Score
Specificity	Names the domain (bug tracing through call stack) and concrete action ('trace backward ... to find original trigger'); it is a single focused action rather than multiple listed actions, so it sits between the 3 and 5 anchors.	4 / 5
Completeness	Explicitly answers both 'what' (trace bugs backward through call stack to find original trigger) and 'when' ('Use when errors occur deep in execution and you need to trace back to find the original trigger') with a concrete trigger phrase.	5 / 5
Trigger Term Quality	Includes natural user-facing phrases like 'errors occur deep in execution', 'trace back', and 'original trigger', though it lacks synonyms such as 'stack trace', 'call chain', or 'root cause'.	4 / 5
Distinctiveness Conflict Risk	Targets a clear niche (backward root-cause tracing of deep errors) with distinct triggers unlikely to fire for unrelated skills.	5 / 5
	Total	18 / 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: secondsky/claude-skills
Path: plugins/root-cause-tracing/skills/root-cause-tracing/SKILL.md
Commit: ad16332

Reviewed: 12 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.