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.

69

Quality

83%

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

77%

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 a clear workflow and concrete cross-platform commands. The main weaknesses are minor rule redundancy and a monolithic structure where the reference catalogs could be split into separate files.

Suggestions

Consolidate the repeated grep_search prohibition and read_file-size warning into a single statement to reduce token redundancy.

Move the detailed Event Type Reference catalog (and optionally the per-OS command lists) into a references/ file, keeping SKILL.md as a lean overview with one-level-deep links.

Consider enumerating the concrete investigation actions in the description (e.g., 'search errors, measure latency, trace tool calls, inspect system prompts') to lift specificity.

DimensionReasoningScore

Conciseness

The body is dense with non-obvious domain detail (JSONL event types, attrs, span hierarchy) and respects Claude's intelligence, but the grep_search prohibition and read_file-size warning are each repeated two-to-three times across Tooling Strategy, Investigation Workflow, and Important Rules, so it could be tightened.

2 / 3

Actionability

It provides copy-paste-ready grep/jq/Select-String/node commands for both macOS/Linux and Windows, exact file paths, and a specific attribute catalog, matching the fully-executable anchor.

3 / 3

Workflow Clarity

The Investigation Workflow is a clear five-step sequence with triage, slice-reading, root-cause, and remediation phases, plus explicit escalation fallbacks (collectDiagnostics, wiki); the task is read-only analysis so destructive-operation feedback loops are not required.

3 / 3

Progressive Disclosure

The ~270-line body is well sectioned but the large event-type reference catalog and the command catalog are entirely inline with no one-level-deep reference files, fitting the "content that should be separate is inline" anchor; the under-50-line exception does not apply.

2 / 3

Total

10

/

12

Passed

Description

90%

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, well-structured description with explicit what-and-when triggers and natural user-facing language. The only soft spot is specificity, which states one core action rather than enumerating several concrete operations.

DimensionReasoningScore

Specificity

The description names the domain ("unexpected chat agent behavior") and a concrete action ("analyzing direct debug logs in JSONL files"), but it offers a single primary action rather than a list of multiple specific operations, so it falls short of the top anchor.

2 / 3

Completeness

It explicitly answers both what it does ("Investigate... by analyzing direct debug logs") and when to use it via an explicit "Use when..." clause, satisfying the top anchor.

3 / 3

Trigger Term Quality

The "Use when users ask why something happened, why a request was slow, why tools or subagents were used or skipped" phrasing covers natural terms users would actually say, matching the good-coverage anchor.

3 / 3

Distinctiveness Conflict Risk

The Copilot debug-log troubleshooting niche has distinct triggers (slow requests, skipped tools, failed loads) and is unlikely to conflict with other skills, matching the clear-niche anchor.

3 / 3

Total

11

/

12

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.