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

81%

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

76%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 debugging guide with executable commands and well-structured issue workflows. The main weakness is missing validation/verification checkpoints around destructive operations (session folder removal, container restarts), which caps workflow clarity.

Suggestions

Add explicit validation before destructive operations: e.g., before `rm -rf data/v2-sessions/<group>/<session>/`, verify the session id with `ncl sessions get` and confirm it is the intended one; after removal, confirm re-provisioning on the next message.

Add a post-restart verification step after `ncl groups restart` (e.g., check `.heartbeat` mtime or `processing_ack` status) so the restart workflow has a feedback checkpoint.

Consider splitting the long Quick Diagnostic Script or the Common Issues deep-dives into a separate reference file to lift progressive_disclosure toward a one-level-deep ideal.

Dimension	Reasoning	Score
Conciseness	The body is dense and assumes Claude's competence (no padding about what containers or DBs are), with most lines earning their place via specific paths and commands; a few explanatory passages could be trimmed, keeping it just below the lean 5 anchor.	4 / 5
Actionability	It is packed with copy-paste-ready, fully executable commands (sqlite queries via scripts/q.ts, systemctl stop/disable, docker run probes, ncl CLI calls, and a complete quick-diagnostic script) covering the common debugging cases.	5 / 5
Workflow Clarity	Issues follow a Symptom -> Root cause -> Diagnosis -> Fix sequence and issue 1 has numbered steps, but destructive/batch operations like `rm -rf data/v2-sessions/...` and `ncl groups restart` lack explicit validation checkpoints before and after, which caps workflow_clarity at 3 per the destructive-ops guideline.	3 / 5
Progressive Disclosure	Content is well-organized into clearly headed sections with one-level-deep, clearly signaled references (docs/db.md, src/container-runner.ts); with no bundle files present the structure is good, though the ~294-line body could justify splitting some bulk into a separate file.	4 / 5
	Total	16 / 20 Passed

Description

87%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, third-person description that clearly states both the skill's purpose and its trigger conditions with concrete, domain-specific terms. Minor gains are possible by replacing the generic lead verb with a few more enumerated concrete actions.

Dimension	Reasoning	Score
Specificity	"Debug container agent issues" and "Covers logs, session DBs, mounts, and common issues" name the domain plus several concrete areas; short of 5 because "Debug" as the lead verb is generic rather than enumerating multiple distinct actions.	4 / 5
Completeness	It explicitly answers what ("Debug container agent issues... Covers logs, session DBs, mounts, and common issues") and when ("Use when things aren't working, container fails, authentication problems, or to understand how the container system works") with concrete trigger phrases.	5 / 5
Trigger Term Quality	"Use when things aren't working, container fails, authentication problems" supplies several natural trigger phrases a user would say, but phrasing like "things aren't working" is colloquial and a few precise synonyms are missing, fitting just below 5.	4 / 5
Distinctiveness Conflict Risk	"Debug container agent issues" / "how the container system works" carves a clear niche around container debugging with distinct triggers and minimal overlap risk with unrelated skills.	5 / 5
	Total	18 / 20 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: ad8837c

Reviewed: 4 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.