CtrlK
BlogDocsLog inGet started
Tessl Logo

error-detective

Search logs and codebases for error patterns, stack traces, and anomalies. Correlates errors across systems and identifies root causes. Use PROACTIVELY when debugging issues, analyzing logs, or investigating production errors.

56

Quality

64%

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/error-detective/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

53%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 body is well-structured and concise but lacks concrete, executable guidance — it describes what to do rather than providing the regex patterns, query templates, or tool commands it advertises. The workflow is sequenced but missing validation checkpoints.

Suggestions

Add at least one concrete, copy-paste-ready example per focus area (e.g. a sample error-extraction regex, an Elasticsearch/Splunk query template for error-rate spikes, a stack-trace correlation command).

Insert explicit validation checkpoints into the Approach (e.g. confirm a hypothesis with evidence before reporting it, verify error-rate baselines before flagging a spike).

Replace vague Output bullets like 'Root cause hypothesis with evidence' with a concrete output template the model should populate.

DimensionReasoningScore

Conciseness

The body is reasonably lean and assumes Claude's competence — short bulleted focus areas and a numbered approach with no padding — though a few generic lines like 'Focus on actionable findings' could be trimmed further.

4 / 5

Actionability

Guidance stays high-level and descriptive — 'Log parsing and error extraction (regex patterns)' and 'Look for patterns across time windows' — without any executable code, concrete regex examples, commands, or query templates the model could directly apply.

2 / 5

Workflow Clarity

A numbered 5-step approach is present and sequenced, but the steps lack concrete commands and there are no explicit validation checkpoints or feedback loops to confirm a hypothesis before reporting.

3 / 5

Progressive Disclosure

Content is well-organized into clear sections (Focus Areas, Approach, Output) for a short skill with no bundle files; structure is clean with only minor organization gaps and no nested references.

4 / 5

Total

13

/

20

Passed

Description

75%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 effectively covers both capability and usage triggers in third person, with strong concrete actions and natural trigger phrases. Its main gap is slightly more generic trigger phrasing rather than highly specific keywords.

Suggestions

Add a few more natural synonyms and tool-adjacent triggers (e.g. 'troubleshooting', 'incident', 'stack traces', 'log aggregation') to broaden keyword coverage.

Sharpen the 'when' clause with more concrete trigger phrases (e.g. 'Use when the user reports a production error, shares a stack trace, or asks why something failed').

DimensionReasoningScore

Specificity

Lists several concrete actions — 'Search logs and codebases for error patterns, stack traces, and anomalies', 'Correlates errors across systems and identifies root causes' — with only minor coverage gaps (no mention of specific tools or output artifacts).

4 / 5

Completeness

Both 'what' (search/correlate/identify root causes) and 'when' ('Use PROACTIVELY when debugging issues, analyzing logs, or investigating production errors') are answered; the 'when' could be slightly more explicit with concrete trigger phrases but is solid.

4 / 5

Trigger Term Quality

Natural user-facing triggers like 'debugging issues', 'analyzing logs', and 'investigating production errors' are present with good coverage, though a few common synonyms (e.g. 'troubleshooting', 'incident') are missing.

4 / 5

Distinctiveness Conflict Risk

The log/error/root-cause niche is fairly distinct with clear triggers, with only minor overlap risk against general debugging or code-review skills.

4 / 5

Total

16

/

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

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository
rmyndharis/antigravity-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.