CtrlK
BlogDocsLog inGet started
Tessl Logo

debug-issue

Systematically debug issues using graph-powered code navigation

58

Quality

66%

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 ./skills/debug-issue/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

78%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 is compact, highly actionable, and well-structured for a simple investigative skill, with named tools and a clear sequence. The main gaps are minor over-explanation of generic debugging wisdom and absent explicit feedback loops for confirming a root cause.

Suggestions

Add an explicit verification step such as 'Confirm the suspected root cause with the source and tests before proposing a fix' to close the workflow validation gap.

Trim generic debugging truisms (e.g. 'Recent changes are the most common source of new issues') to keep every line tool-specific and non-obvious.

Show one complete example invocation for query_graph_tool (with callers_of/callees_of arguments) so the most central tool is copy-paste ready.

DimensionReasoningScore

Conciseness

The body is lean and tool-focused with no concept padding, but lines like 'Recent changes are the most common source of new issues' state generic debugging knowledge Claude already has, matching 'efficient; minor instances of over-explanation that could be trimmed'.

4 / 5

Actionability

It names concrete tools with specific parameters (callers_of, callees_of, detail_level="minimal") and gives one full call example, but several tools lack complete call syntax, fitting 'mostly executable; concrete commands with minor gaps'.

4 / 5

Workflow Clarity

A clear numbered 5-step sequence is present and 'Read the implementation and its tests before changing code' serves as a validation checkpoint before edits, matching 'clear sequence with most checkpoints present; minor validation gaps' rather than the explicit feedback-loop anchor at 5.

4 / 5

Progressive Disclosure

The skill is under 50 lines with no bundle files and no need for external references, and it is organized into well-labeled sections (Steps, Tips, Token Efficiency Rules), meeting the simple-skill exception for a top score.

5 / 5

Total

17

/

20

Passed

Description

53%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 is concise and identifies a distinct niche, but it lacks an explicit 'Use when...' trigger clause and relies on jargon, capping both completeness and trigger-term quality. Adding natural trigger phrases would lift it toward the top anchors.

Suggestions

Add a 'Use when...' clause naming concrete triggers, e.g. 'Use when debugging an issue, tracing a bug, or finding the root cause of a failure in the codebase.'

Include natural synonyms users actually say (e.g. 'trace a bug', 'find root cause') alongside 'debug issues' to broaden trigger coverage.

Soften 'graph-powered code navigation' with a plain-language gloss so the description reads as a user-facing trigger rather than implementation jargon.

DimensionReasoningScore

Specificity

The phrase 'debug issues using graph-powered code navigation' names the domain and a concrete method, matching the anchor that lists 1-2 concrete actions without comprehensive coverage.

3 / 5

Completeness

It gives a clear 'what' (debug via graph navigation) but no 'Use when...' trigger clause, which per the judging guidelines caps completeness at 3.

3 / 5

Trigger Term Quality

'debug issues' is a natural term users say, but 'graph-powered code navigation' is jargon and no synonyms or trigger clause are present, fitting the 'some relevant keywords but missing variations' anchor.

3 / 5

Distinctiveness Conflict Risk

The graph-powered-navigation niche is mostly distinct with only minor overlap risk against general debugging skills, matching the 'mostly distinct; minor overlap' anchor rather than the fully-distinct 5 which requires explicit triggers.

4 / 5

Total

13

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
tirth8205/code-review-graph
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.