CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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, environment variables, mounts, and common issues.

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

77%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 highly actionable, well-structured debugging reference with excellent validation checkpoints; its weaknesses are redundant repetition, some generic Docker over-explanation, and no progressive disclosure into reference files despite the skill's length.

Suggestions

Cut generic Docker knowledge ('-v vs --mount syntax', ':ro suffix explanation') - Claude already knows this; keep only project-specific mount behavior.

Consolidate the /home/node/.claude vs /root/.claude guidance into one authoritative section instead of repeating it in the architecture overview, issue 5, session persistence, and the diagnostic script.

Split the SDK options reference, IPC file-type listing, and quick diagnostic script into references/ files (e.g., sdk-options.md, ipc.md, diagnostics.sh) to shrink SKILL.md to an overview.

DimensionReasoningScore

Conciseness

The bulk is high-value project-specific detail, but generic Docker knowledge is over-explained ('Docker supports both -v and --mount syntax', ':ro suffix for readonly mounts'), the /home/node/.claude vs /root/.claude warning is repeated in 4+ places, and issue titles are duplicated (sections 1 and 5).

3 / 5

Actionability

Fully executable copy-paste bash/docker commands with exact paths, symptom-to-cause-to-fix pairs for each common issue, and a complete 8-step diagnostic script covering the common cases.

5 / 5

Workflow Clarity

Symptom-to-diagnose-to-fix-to-verify loops are explicit (verify env vars reach the container, verify sessions are accessible, verify session ID reuse in logs), and the quick diagnostic script is a literal checklist with OK/MISSING feedback.

5 / 5

Progressive Disclosure

Section structure is good, but there are no bundle files at all: the SDK options reference, IPC file-type reference, and ~30-line diagnostic script are inlined in a single ~345-line SKILL.md, content that clearly belongs in separate reference files.

3 / 5

Total

16

/

20

Passed

Description

78%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 solid description with an explicit 'Use when' clause and natural trigger phrases; the main weakness is that capabilities are stated as topics rather than a list of concrete debugging actions.

Suggestions

Replace topic enumeration with concrete actions, e.g., 'Check container logs, verify volume mounts, diagnose authentication failures, and fix session resumption issues.'

Add commonly-said synonyms such as 'docker' and 'error'/'exited with code 1' to the trigger list.

Drop the generic 'things aren't working' trigger in favor of more specific failure symptoms to reduce overlap with general debugging skills.

DimensionReasoningScore

Specificity

Names the domain ('Debug container agent issues') with 1-2 concrete actions ('debug', 'understand how the container system works'), but 'Covers logs, environment variables, mounts, and common issues' lists topics rather than actions, so coverage is not comprehensive.

3 / 5

Completeness

Explicitly answers both parts: 'what' via 'Debug container agent issues... Covers logs, environment variables, mounts' and 'when' via an explicit 'Use when' clause with multiple concrete triggers (container fails, authentication problems).

5 / 5

Trigger Term Quality

Natural phrases like 'things aren't working', 'container fails', and 'authentication problems' match what users would say, but common variations such as 'docker', 'error', or 'exit code' are missing.

4 / 5

Distinctiveness Conflict Risk

The 'container agent' niche is mostly distinct, but the generic trigger 'things aren't working' creates minor overlap risk with any general debugging skill.

4 / 5

Total

16

/

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

jbaruch/nanoclaw-telegram

Path

.claude/skills/debug/SKILL.md

Revision

bc4f114

Reviewed

Table of Contents

DiscoveryImplementationValidation

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.

Claim skill