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

88%

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

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is actionable and the tracing workflow is clearly sequenced, but it carries redundant material and time-sensitive log detail that hurt conciseness, and its single external reference points to a file that is not present in the bundle. Tightening the repetition and either including or removing the missing script would lift the weaker dimensions.

Suggestions

Consolidate the repeated 'NEVER fix just the symptom' guidance and the 'Stack Trace Tips' section with the earlier 'Adding Stack Traces' section to remove redundancy.

Move or drop the time-sensitive 'Real-World Impact' log (the 2025-10-03 session date and test count); if retained for context, place it in a clearly labeled historical section so it doesn't penalize conciseness.

Either add the referenced `find-polluter.sh` to a scripts/ directory or remove the `@find-polluter.sh` reference so progressive disclosure points to a real, navigable file.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with concrete code, but padded with redundancy ('NEVER fix just the symptom' repeated, 'Stack Trace Tips' rehashes the instrumentation section) and a vanity 'Real-World Impact' log carrying time-sensitive detail (a 2025-10-03 date, '1847 tests passed') outside any deprecated section.	2 / 3
Actionability	Provides fully executable instrumentation code (`new Error().stack`, console.error logging), a concrete capture command (`npm test 2>&1 \| grep 'DEBUG git init'`), and a real bisection invocation (`./find-polluter.sh '.git' 'src/*/.test.ts'`) — copy-paste ready.	3 / 3
Workflow Clarity	Sequences a clear 5-step investigative process (Observe → Find Immediate Cause → Ask What Called This → Keep Tracing Up → Find Original Trigger) with worked trace chains; the task is investigative rather than destructive/batch, so the missing validation checkpoints are not a capping factor.	3 / 3
Progressive Disclosure	References one external resource via `@find-polluter.sh`, but no scripts/ directory exists so the referenced file is missing; the body is otherwise a fairly monolithic inline document (two DOT diagrams plus a full multi-layer real example) that could be split out.	2 / 3
	Total	10 / 12 Passed

Description

100%

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 specific, uses a natural 'Use when' trigger, covers both what and when, and defines a distinct niche. Voice is correctly third person ('traces bugs'). No corrections needed.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions: 'systematically traces bugs backward through call stack, adding instrumentation when needed, to identify source of invalid data or incorrect behavior' — matching the multiple-specific-actions anchor.	3 / 3
Completeness	Explicitly answers both what ('systematically traces bugs backward through call stack...') and when ('Use when errors occur deep in execution...'), satisfying the explicit-trigger requirement for a 3.	3 / 3
Trigger Term Quality	Opens with natural trigger phrasing a user would say — 'Use when errors occur deep in execution and you need to trace back to find the original trigger' — covering 'errors', 'trace back', and 'call stack' terms users actually use.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche — backward call-stack root-cause tracing with instrumentation — with distinct triggers unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 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: microsoft/FluidFramework
Path: .agency/plugins/nori/skills/root-cause-tracing/SKILL.md
Commit: f9f2007

Reviewed: about 7 hours 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.