CtrlK
BlogDocsLog inGet started
Tessl Logo

troubleshoot

Investigate unexpected chat agent behavior by analyzing direct debug logs in JSONL files. Use when users ask why something happened, why a request was slow, why tools or subagents were used or skipped, or why instructions/skills/agents did not load.

72

Quality

88%

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

82%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 thorough, highly actionable troubleshooting skill with concrete terminal commands, a clear investigation workflow, and useful external references. Its main weakness is length: the inlined event-type catalog with many JSONL examples could live in a separate reference file to improve token efficiency and structure.

Suggestions

Move the detailed Event Type Reference with its JSONL examples into a separate reference file (e.g. EVENT_TYPES.md) and summarize only the most common types inline, linking out for the rest — this would improve both conciseness and progressive disclosure.

Collapse the near-duplicate macOS/Linux and Windows command tables into a single table with a platform column, or present one platform as primary with a short Windows fallback note, to reduce repetition.

Trim the generic event example and special generic sub-section, which are rarely needed for troubleshooting, to tighten the reference further.

DimensionReasoningScore

Conciseness

Largely efficient and focused on log-specific facts Claude wouldn't know (event types, attrs, file layout), but the full Event Type Reference with multiple multi-line JSONL examples and the dual macOS/Windows command tables repeat similar patterns, adding length that could be trimmed.

3 / 5

Actionability

Provides concrete, executable grep/jq/Select-String/node one-liners, explicit file-reading order, and exact tool names to use — copy-paste ready guidance covering the common troubleshooting cases.

5 / 5

Workflow Clarity

The Investigation Workflow is clearly sequenced (identify logs → triage → read slices → determine cause → remediate), with a validation-flavored triage step and explicit feedback loops for network issues (collectDiagnostics before concluding) and the wiki as a last resort.

5 / 5

Progressive Disclosure

Well-organized with clear section headers and external URLs used appropriately for customization docs and the wiki, but the bulk of the Event Type Reference is inlined in SKILL.md rather than split into a separate reference file, which is the natural place for such detailed material.

4 / 5

Total

17

/

20

Passed

Description

95%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: third person, specific domain, and explicit 'Use when' triggers with multiple natural phrasings. It clearly answers both what the skill does and when to invoke it with minimal conflict risk.

DimensionReasoningScore

Specificity

Names the domain (debug logs in JSONL) and several concrete actions ('analyzing direct debug logs', investigating behavior), but does not enumerate a wide list of specific operations like extract/merge/convert, leaving minor coverage gaps.

4 / 5

Completeness

Explicitly answers both 'what' (investigate unexpected chat agent behavior by analyzing direct debug logs in JSONL files) and 'when' ('Use when users ask why...') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Comprehensive natural trigger phrases users would say: 'why something happened', 'why a request was slow', 'why tools or subagents were used or skipped', 'why instructions/skills/agents did not load' — covering the full range of troubleshooting questions including synonyms.

5 / 5

Distinctiveness Conflict Risk

Clear niche — Copilot Chat agent troubleshooting via JSONL debug logs — with distinct triggers (why requests are slow, why skills/agents didn't load) that are unlikely to match a different skill.

5 / 5

Total

19

/

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
posit-dev/positron
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.