debug

Debug container agent issues. Use when things aren't working, container fails, authentication problems, or to understand how the container system works. Covers logs, session DBs, mounts, and common issues.

Quality

91%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Medium

Suggest reviewing before use

Quality

Content

92%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

An excellent debugging reference: lean, highly actionable, and well-sequenced with validation checkpoints for destructive operations. The only weakness is progressive disclosure — a large single-file body with no split-out reference materials despite covering many distinct subsystems.

Suggestions

Move the per-issue troubleshooting ("Common Issues" sections 1–4) and the "Quick Diagnostic Script" into a reference file under references/ and link to them from a concise overview, keeping SKILL.md as a navigational hub.

Split the lengthy SQL-query and CLI-command catalogs ("Inspecting Session DBs", "Container CLI", "Restarting a session", "Manual Container Probes") into a commands reference doc, summarizing the most common one or two in SKILL.md.

Verify the two docs/*.md links resolve to real files, since there are no bundle files present in this skill package to confirm the references are valid.

Dimension	Reasoning	Score
Conciseness	Dense and technical with every line earning its place — a log-location table, specific sqlite queries, concrete commands, and a diagnostic script — with no padded explanation of concepts Claude already knows.	3 / 3
Actionability	Fully executable throughout: copy-paste `pnpm exec tsx scripts/q.ts` queries, `ncl groups restart --id <group-id>`, `docker run --rm` probes, and a complete numbered diagnostic script.	3 / 3
Workflow Clarity	Diagnostic flows are well sequenced with explicit checkpoints — a "Reading the flow" decision tree, issue 1's diagnosis→fix→verify steps, and the destructive "Clearing a Session" section that says "Inspect first" before rm -rf.	3 / 3
Progressive Disclosure	No bundle files exist and the ~290-line body is monolithic; the issue-by-issue troubleshooting and diagnostic script are inline rather than split into reference files, though the two docs/*.md links are one level deep and clearly signaled.	2 / 3
	Total	11 / 12 Passed

Description

90%Weight 40%Scale 1-3

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, third-person description that clearly states both what the skill does and when to invoke it, with natural trigger terms and a distinctive niche. The only minor gap is specificity, which names subsystems but does not enumerate a fuller list of distinct debug actions.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete subsystems ("Debug container agent issues", "Covers logs, session DBs, mounts, and common issues") but stops short of enumerating multiple distinct actions like the score-3 anchor.	2 / 3
Completeness	Explicitly answers both what (debug container agent issues; covers logs, session DBs, mounts, common issues) and when (explicit "Use when..." clause with multiple triggers), matching the score-3 anchor.	3 / 3
Trigger Term Quality	"Use when things aren't working, container fails, authentication problems, or to understand how the container system works" gives good coverage of natural phrases a user would actually say.	3 / 3
Distinctiveness Conflict Risk	"Container agent issues" / "container system" with triggers like "container fails" and "session DBs" carves a clear narrow niche unlikely to conflict with unrelated skills.	3 / 3
	Total	11 / 12 Passed

Validation

87%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 2 suspicious	Warning
referenced_paths_exist	Referenced path issues: 4 missing	Warning

	Total	14 / 16 Passed

Repository: nanocoai/nanoclaw
Path: .claude/skills/debug/SKILL.md
Commit: 641963c

Reviewed: 6 days ago

Table of Contents

Discovery Implementation Validation

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.