CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

fix-root-cause

Apply when debugging. Trace each symptom back to the first place the system went wrong and fix it there. A guard is a fix only when the state it handles is legitimate.

Quality

93%

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

SKILL.md
Quality
Evals
Security

Quality

Content

100%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.

An exemplary lean principle skill: every line is a specific, followable debugging directive, the pattern reads as a clear ordered procedure with built-in recovery guidance, and the short single-file structure needs no progressive disclosure. No dimension shows a realistic gap to fix.

DimensionReasoningScore

Conciseness

The ~24-line body is pure directive prose — "Reproduce first.", "When stuck, instrument. Read the actual error and the actual state. Do not guess." — with zero explanation of concepts Claude already knows and every token earning its place, matching the level-5 anchor exactly. It does not fall to level 4 because no over-explanation instances exist to trim.

5 / 5

Actionability

Though code-free, the guidance is highly concrete per the instruction-skill scoring note: it names specific artifacts ("config files, caches, lock files, serialized state"), specific bug-hiding anti-patterns ("Guards, retries, swallowed errors, clamped values, and discarded state"), and a precise stopping criterion ("until the answer is a wrong decision in the code"), covering the common cases like the level-5 anchor.

5 / 5

Workflow Clarity

This is a simple single-purpose skill under 50 lines, so the simple-skill exception applies: the Pattern list is an unambiguous ordered procedure ("Reproduce first" → why-chain with an explicit termination condition → "When stuck, instrument" as error recovery), and it involves no destructive or batch operations that would impose a validation cap.

5 / 5

Progressive Disclosure

The skill is under 50 lines with no need for external references (no references/, scripts/, or assets/ bundle exists), and the body is cleanly organized into an intro definition, a **Why** section, and a **Pattern** checklist — exactly the well-organized-sections case the rubric scores at level 5.

5 / 5

Total

20

/

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 tight, third-person description that explicitly covers both what the skill does and when to apply it, with the standout "debugging" trigger term and a memorable distinguishing rule about guards. Its only weakness is missing common trigger synonyms such as "bug", "error", or "root cause".

DimensionReasoningScore

Specificity

The description names several concrete actions — "Trace each symptom back to the first place the system went wrong and fix it there" plus the specific guard rule "A guard is a fix only when the state it handles is legitimate" — which goes beyond the 1-2 actions of the level-3 anchor, though it stops short of the broad multi-action coverage of level 5.

4 / 5

Completeness

Both questions are explicitly answered: "Apply when debugging" gives a concrete when-trigger, and "Trace each symptom back to the first place the system went wrong and fix it there" states exactly what the skill does, matching the level-5 anchor's clear-and-explicit both-what-and-when pattern. It is not level 4 because the when clause is already concrete rather than needing more specificity.

5 / 5

Trigger Term Quality

"Apply when debugging" supplies the single most natural trigger term, reinforced by "symptom", "trace", and "fix" — comparable keyword density to the level-4 anchor — but common variations like "bug", "error", or "root cause" are absent, keeping it below level 5.

4 / 5

Distinctiveness Conflict Risk

The symptom-vs-root-cause framing carves a clear niche that most skills would not match, but the broad "debugging" trigger could overlap with closely related debugging-methodology or tooling skills, fitting the level-4 anchor (mostly distinct, minor overlap risk) rather than level 5.

4 / 5

Total

17

/

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

remotion-dev/remotion

Path

.agents/skills/fix-root-cause/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.