CtrlK
BlogDocsLog inGet started
Tessl Logo

debugging-toolkit-smart-debug

Use when working with debugging toolkit smart debug

48

Quality

51%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/debugging-toolkit-smart-debug/SKILL.md

The canonical home for this skill is debugging-toolkit-smart-debug in administrakt0r/AI-Agents-Safe-Coding-Skills

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 content is a well-structured, actionable debugging playbook with a strong sequenced workflow and explicit validation, scoring well on workflow clarity and actionability. Its main weaknesses are minor boilerplate padding at the top and a broken reference to a non-existent resources/implementation-playbook.md file.

Suggestions

Remove the generic boilerplate instructions (lines 21-23) and the persona sentence (line 26) since they restate what Claude already knows and add tokens without value.

Fix or remove the dangling reference to resources/implementation-playbook.md (line 24) — either create the file or delete the reference, since pointing at a missing file degrades progressive disclosure.

Make the TypeScript example's helper calls (aiAnalyze, getSentryIssue, getDataDogTraces) concrete by noting they are illustrative placeholders or replacing them with real client calls so the example is fully copy-paste ready.

DimensionReasoningScore

Conciseness

The body is mostly efficient and list-driven without explaining what debugging or tools like Sentry/DataDog are, but the opening 'You are an expert AI-assisted debugging specialist...' persona line and the generic boilerplate instructions (lines 21-23) are trimmable padding Claude already knows, fitting the score-4 anchor of efficient content with minor over-explanation.

4 / 5

Actionability

It provides concrete named tools (Sentry, DataDog, Jaeger, Pyroscope, rr, Gremlin), a structured hypothesis format, strategy-by-scenario mappings, and a TypeScript example with real attribute calls; it falls just short of score 5 because the example uses illustrative functions (aiAnalyze, getSentryIssue) that are not real library calls, matching the score-4 anchor of mostly executable guidance with minor gaps.

4 / 5

Workflow Clarity

A clearly sequenced 10-step workflow (Triage through Prevention) with explicit validation in step 9 and a concrete success-criteria checklist (tests pass, no performance regression, error rate unchanged), plus production-safe techniques flagged for risky operations, matches the score-5 anchor of clear sequence with explicit validation steps and checklists.

5 / 5

Progressive Disclosure

Section structure is good with clear headers, but the single external reference on line 24 ('open resources/implementation-playbook.md') points to a file that does not exist in the bundle, a broken/dangling reference, and is only vaguely signaled, matching the score-3 anchor of structure present but references not cleanly signaled.

3 / 5

Total

16

/

20

Passed

Description

25%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 a single trigger clause with no statement of capability, scoring poorly across all dimensions because it never explains what the skill does and uses a non-natural repetitive label rather than real trigger keywords. It is essentially a placeholder-quality description that needs concrete actions and explicit natural-language triggers.

Suggestions

Add a 'what' clause naming 2-4 concrete capabilities, e.g. 'Triages production errors, generates ranked hypotheses, and recommends debugging strategies for live systems.'

Replace the repetitive label 'debugging toolkit smart debug' with natural trigger terms a user would actually say, such as 'production errors', 'stack traces', 'root cause analysis', or 'intermittent failures'.

Combine into a complete form: '<what>. Use when <when>' so both capability and trigger are explicit.

DimensionReasoningScore

Specificity

The phrase names a domain ("debugging toolkit smart debug") but states no concrete actions — it only provides a trigger, never describing what the skill does, matching the score-2 anchor where the domain is named but actions are minimal or absent.

2 / 5

Completeness

It contains a "Use when..." trigger (the when) but entirely lacks any "what does this do" statement, exactly matching the score-2 anchor "only 'when' is present without 'what'" exemplified by "Use when working with documents."

2 / 5

Trigger Term Quality

Only "debugging" is a term a user might naturally say; "debugging toolkit smart debug" is a repetitive product-style label rather than natural phrasing, with no synonyms or variations, fitting the score-2 anchor of one or two generic keywords missing the natural phrases.

2 / 5

Distinctiveness Conflict Risk

The trigger "debugging" is broad and would overlap with any general debugging skill; the tautological "toolkit smart debug" qualifier only narrowly scopes it, keeping it at the score-2 anchor of very broad, high-overlap-risk phrasing.

2 / 5

Total

8

/

20

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
administrakt0r/AI-Agents-Safe-Coding-Skills
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.