CtrlK
BlogDocsLog inGet started
Tessl Logo

gstack-openclaw-investigate

Use when asked to debug, fix a bug, investigate an error, or do root cause analysis, and when users report errors, stack traces, unexpected behavior, or say something stopped working.

68

Quality

82%

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

SKILL.md
Quality
Evals
Security

Quality

Content

81%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.

A disciplined, well-sequenced debugging workflow with strong validation checkpoints and actionable directives. It is token-efficient and easy to navigate, with only minor room to tighten repeated admonitions.

DimensionReasoningScore

Conciseness

Largely lean with tight, directive prose and minimal concept re-explanation, though a few repeated admonitions (the 3-strike / architectural-smell points restated across phases) could be trimmed.

4 / 5

Actionability

Provides concrete commands ('git log --oneline -20 -- <affected-files>'), explicit decision branches, and a structured report template; it stops short of copy-paste code examples for verification, keeping it just below 5.

4 / 5

Workflow Clarity

A clearly sequenced five-phase investigation pipeline with explicit validation checkpoints (hypothesis testing, 3-strike rule, fresh reproduction, regression test) and feedback loops for recovery, matching the top anchor.

5 / 5

Progressive Disclosure

Well-organized into clearly headed phases with no nested references and no external bundle files to manage; it stays inline throughout rather than splitting detail out, so it is good but not maximally structured.

4 / 5

Total

17

/

20

Passed

Description

83%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 with a clear 'Use when...' clause covering both capabilities and natural trigger terms. It is specific and actionable, with only minor overlap risk and a few missing synonyms.

Suggestions

Add a few more natural trigger synonyms users say (e.g., 'it's broken', 'why is this failing', 'production is down') to broaden keyword coverage.

Tighten the niche by signaling this is for code/software debugging specifically, reducing overlap with general investigation or incident-response skills.

DimensionReasoningScore

Specificity

Names the debugging domain and several concrete actions ('debug, fix a bug, investigate an error, or do root cause analysis'), with minor gaps in coverage such as performance or log analysis.

4 / 5

Completeness

Explicitly answers both what ('debug, fix a bug, investigate an error, or do root cause analysis') and when ('Use when... users report errors, stack traces, unexpected behavior, or say something stopped working') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Includes natural user phrases ('something stopped working', 'errors, stack traces, unexpected behavior') with good coverage, though it omits some synonyms users say like 'it's broken' or 'why is this failing'.

4 / 5

Distinctiveness Conflict Risk

The debugging/root-cause niche is fairly distinct, but the broad 'investigate an error' framing could overlap with general coding or incident-response skills.

4 / 5

Total

17

/

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
garrytan/gstack
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.