CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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

72%

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

The canonical home for this skill is root-cause-tracing in NeoLabHQ/context-engineering-kit

SKILL.md
Quality
Evals
Security

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.

A genuinely actionable debugging skill with concrete code, commands, and a clear sequenced process, held back by a duplicated worked example, dated self-congratulatory content, and a broken reference to a script that is not shipped in the bundle.

Suggestions

Fix the '@find-polluter.sh' reference: either ship the script in a scripts/ directory or inline its usage — currently 'See script for usage' points to a file that does not exist in the bundle.

Merge 'Real Example: Empty projectDir' into 'The Tracing Process' (they tell the same story) and cut the dated 'Real-World Impact' section to remove duplication and time-sensitive content.

Replace the two dot digraphs with short bullet decision lists — they restate the prose process at meaningful token cost.

DimensionReasoningScore

Conciseness

Mostly efficient, but the 'Real Example: Empty projectDir' section retells the exact git-init trace already walked through in 'The Tracing Process', and the two dot digraphs restate the same decision logic as the prose. The dated 'Real-World Impact' section ('2025-10-03', '1847 tests passed') is time-sensitive booster content that adds tokens without guidance.

3 / 5

Actionability

Concrete, executable guidance throughout: a copy-paste instrumentation function with console.error and stack capture, the command `npm test 2>&1 | grep 'DEBUG git init'`, and a script invocation `./find-polluter.sh '.git' 'src/**/*.test.ts'`. Minor gaps: the referenced find-polluter.sh script is not present in the bundle, and the trace example is tightly bound to one specific codebase.

4 / 5

Workflow Clarity

The 5-step tracing process (Observe → Immediate Cause → What Called This → Keep Tracing Up → Original Trigger) is clearly sequenced, with decision branches for dead ends and run-and-capture checkpoints (grep the debug output, analyze stacks, bisect tests). The minor gap is no explicit step to verify the source fix resolves the original symptom.

4 / 5

Progressive Disclosure

Section headers are clear, but there are no bundle files at all (no references/, scripts/, or assets/ directories), so the body's reference to '@find-polluter.sh' with 'See script for usage' is a dangling pointer to a nonexistent file. At ~180 lines with everything inline, content like the full real-world walkthrough and impact stats could live in a reference file.

3 / 5

Total

14

/

20

Passed

Description

66%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 solid description with an explicit use-when clause and multiple concrete capabilities, weakened by second-person voice, a missing 'root cause' trigger phrase, and a broad error-trigger opener that raises conflict risk with general debugging skills.

Suggestions

Rewrite in third person (e.g., 'Traces bugs backward through the call stack to the original trigger') to remove the 'you need' second-person construction and recover the specificity penalty.

Add the natural trigger phrases users would actually say — 'root cause', 'root cause analysis', 'stack trace' — to the use-when clause.

Narrow the trigger opener from 'Use when errors occur' to the skill's distinct scenario, e.g., 'Use when an error surfaces deep in the call stack and the origin of the invalid data is unclear'.

DimensionReasoningScore

Specificity

The description lists several concrete actions ('systematically traces bugs backward through call stack, adding instrumentation when needed, to identify source of invalid data'), which would merit a 4, but it uses second person ('you need to trace back'), incurring the mandated 1-point voice penalty. It also omits key capabilities like stack-trace capture and test bisection that the skill actually covers.

3 / 5

Completeness

Both halves are present: an explicit 'Use when errors occur deep in execution and you need to trace back to find the original trigger' clause and a clear what ('systematically traces bugs backward through call stack, adding instrumentation when needed'). The when-clause covers a single scenario and could be more specific with additional trigger phrases (e.g., stack traces, test pollution), so it doesn't reach the anchor-5 bar.

4 / 5

Trigger Term Quality

Good natural keyword coverage: 'errors occur deep in execution', 'trace back', 'call stack', 'bugs', 'invalid data', 'original trigger'. However, the most natural phrase a user would say — 'root cause' — is absent, along with 'stack trace' and 'debug', so it falls short of comprehensive synonym coverage.

4 / 5

Distinctiveness Conflict Risk

The deep-stack backward-tracing scenario is fairly niche, but the opener 'Use when errors occur' and phrases like 'incorrect behavior' and 'invalid data' are broad debugging triggers that would also fire for general debugging or error-fixing skills, creating real overlap risk.

3 / 5

Total

14

/

20

Passed

Validation

100%

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

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

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.