CtrlK
BlogDocsLog inGet started
Tessl Logo

debug

Reproduce, minimize, localize, identify root cause, and distinguish diagnosis from an authorized fix. Prefer root-cause over symptom patches.

60

Quality

70%

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 ./crates/tui/assets/skills/debug/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

72%

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

The body is admirably concise and well-organized for a simple process skill, but the workflow steps describe what to do without how, and lack explicit validation/feedback checkpoints. Adding concrete techniques and a retry-on-failure loop would lift actionability and workflow clarity.

Suggestions

Add concrete techniques to each step, e.g. 'Minimize: bisect commits or reduce inputs until the failure is smallest', 'Localize: add targeted logging or use git bisect to pin component/file/line'.

Insert an explicit validation/feedback checkpoint, e.g. 'If reproduction fails, gather more signal (logs, env, recent changes) and retry before proceeding.'

Show the expected Output shape with a tiny worked example so the deliverable format is unambiguous.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence — it never explains what debugging or reproduction is, and every section (When to use, Non-goals, Workflow, Output shape) earns its place, matching the level-3 'every token earns its place' anchor.

3 / 3

Actionability

The numbered workflow gives a clear sequence but several steps ('Minimize the case', 'Localize to component/file/line') state direction without method, fitting the level-2 anchor of concrete guidance missing key details.

2 / 3

Workflow Clarity

The 5-step sequence is clearly ordered, but there are no explicit validation checkpoints or feedback loops (e.g., 'if reproduction fails, gather more signal and retry'), matching the level-2 anchor of sequence present but checkpoints missing or implicit.

2 / 3

Progressive Disclosure

The skill is under 50 lines with no need for external references and is organized into well-labeled sections, so per the judging guideline progressive disclosure scores 3 on well-organized sections alone.

3 / 3

Total

10

/

12

Passed

Description

67%

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 and distinctive about the debugging/diagnosis workflow, but it omits an explicit 'Use when' trigger clause and relies on somewhat technical jargon over natural user terms. Adding trigger guidance and common user phrasings would raise completeness and trigger-term quality.

Suggestions

Append an explicit trigger clause, e.g. 'Use when a test fails, output is wrong, or a regression/crash/flake needs diagnosis.'

Swap jargon like 'minimize' and 'localize' for or alongside natural user terms such as 'bug', 'failing', 'crash', and 'narrow down the case'.

Keep the root-cause-vs-fix distinction, but lead with the user-facing trigger before the action list.

DimensionReasoningScore

Specificity

The description enumerates multiple concrete actions — 'Reproduce, minimize, localize, identify root cause, and distinguish diagnosis from an authorized fix' — matching the level-3 anchor of listing several specific concrete actions rather than a vague domain label.

3 / 3

Completeness

It clearly answers 'what' (the diagnosis workflow) but provides no 'Use when...' clause or equivalent explicit trigger guidance, so per the judging guideline completeness is capped at 2.

2 / 3

Trigger Term Quality

It includes relevant debugging terms ('reproduce', 'root cause') but leans on jargon ('minimize', 'localize') and omits natural user phrasings like 'bug', 'failing', 'crash', or 'wrong output', fitting the level-2 anchor of some relevant keywords missing common variations.

2 / 3

Distinctiveness Conflict Risk

The diagnosis-versus-authorized-fix framing carves out a clear, distinct niche that is unlikely to trigger for unrelated skills, matching the level-3 anchor of a clear niche with low conflict risk.

3 / 3

Total

10

/

12

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
Hmbown/CodeWhale
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.