CtrlK
BlogDocsLog inGet started
Tessl Logo

common-debugging

Troubleshoot systematically using the Scientific Method. Use when debugging crashes, tracing errors, diagnosing unexpected behavior, or investigating exceptions.

67

Quality

82%

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

77%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 core Root-Cause Protocol is well-sequenced with explicit verification and feedback loops, and the single bundle reference is valid and properly disclosed. Quality is dragged down by noise sections — an empty P1 priority heading and a 'canonical response anchors' list of bare words — that pad the body without adding actionable value.

Suggestions

Delete the 'Canonical response anchors' section — a bare word list ('hypothesis', 'one hypothesis', 'stop', 'minimal') gives the executing model nothing to act on; the protocol already uses these terms naturally.

Remove the stray '## **Priority: P1 (HIGH)**' heading, which occupies a top-level heading slot without conveying any instruction.

Add one short worked example under Root-Cause Protocol (a sample one-line hypothesis and the single-variable experiment that confirms or kills it) to lift actionability from mostly-executable to copy-paste concrete.

DimensionReasoningScore

Conciseness

The protocol sections are lean, but the body carries genuinely unnecessary content: a stray "## **Priority: P1 (HIGH)**" heading that conveys nothing to the executing model, and a "Canonical response anchors" section listing bare words ("hypothesis", "one hypothesis", "stop", "minimal") with no actionable guidance. That is more than the 'minor trimmable instances' of anchor 4, but the bulk of the content does earn its place, so it does not fall to anchor 2's pervasive padding.

3 / 5

Actionability

The guidance is directive and concrete for an instruction-only skill: "Gather error, logs, repro steps, recent diffs", "Change one variable to prove or kill the theory", "Remove all print/console.log before commit". It is short of anchor 5 because there is no worked example (e.g., a sample hypothesis and the experiment that confirms or kills it), but it clearly exceeds anchor 3's pseudocode-vagueness.

4 / 5

Workflow Clarity

The six numbered steps (OBSERVE through VERIFY) form a clear sequence with an explicit validation step ("Re-run the failing case and regression checks"), feedback loops for error recovery ("Stop if fix #2 starts before understanding fix #1: Re-open root cause"), and a checklist for incident pressure. This matches anchor 5; anchor 4 would require a missing or only-implicit checkpoint, and none is missing.

5 / 5

Progressive Disclosure

The body is ~45 lines with well-organized sections, and the single reference link ([Bug Report Template](references/bug-report-template.md)) is real, clearly signaled, and exactly one level deep. Under the rubric's simple-skill exception (under 50 lines, no need for further external references), well-organized sections alone merit the top anchor; the only blemish is the stray Priority heading, which is an organization wart rather than a navigation problem.

5 / 5

Total

17

/

20

Passed

Description

87%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: explicit what and when clauses, natural trigger terms, and a well-delineated debugging niche. Its only weakness is that the capability statement itself is a single generic verb, with the concrete activities carried entirely by the when-clause.

DimensionReasoningScore

Specificity

The description names the debugging domain and enumerates several concrete activity types ("debugging crashes, tracing errors, diagnosing unexpected behavior, or investigating exceptions"), though the core capability statement is a single generic verb ("Troubleshoot systematically"). It sits between anchor 3 (1-2 concrete actions) and anchor 4 (several specific actions with minor gaps) — several activities are listed but they appear as when-triggers rather than capability actions, so it does not clearly match anchor 5's comprehensive action coverage.

4 / 5

Completeness

It explicitly answers both: what ("Troubleshoot systematically using the Scientific Method") and when ("Use when debugging crashes, tracing errors, diagnosing unexpected behavior, or investigating exceptions") with concrete trigger phrases. This matches anchor 5's structure, mirroring the good example; anchor 4 would require the 'when' clause to be less explicit, which it is not.

5 / 5

Trigger Term Quality

"debugging crashes", "tracing errors", and "investigating exceptions" are phrases users naturally say when they need this skill. A few common natural terms are missing (e.g., "bug", "fix", "stack trace", "why is it failing"), so it does not reach anchor 5's comprehensive synonym coverage but clearly exceeds anchor 3's partial coverage.

4 / 5

Distinctiveness Conflict Risk

Debugging is a clear niche with distinct, well-scoped triggers (crashes, errors, exceptions, unexpected behavior); minimal overlap risk with unrelated skills. It matches anchor 5 — the four trigger phrases delineate the niche precisely enough to avoid mis-triggering.

5 / 5

Total

18

/

20

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

Total

14

/

16

Passed

Repository
HoangNguyen0403/agent-skills-standard
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.