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, session DBs, mounts, and common issues.

Quality

79%

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

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/debug/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

88%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.

An exemplary debugging reference: concrete executable commands, an error-code taxonomy, decision-tree triage for the session DBs, and verified fix procedures with an end-of-guide diagnostic checklist. Its only weaknesses are mild — a few sections could be trimmed for token efficiency, and the long single-file layout could split detail into reference files.

DimensionReasoningScore

Conciseness

The guide is dense and command-first with no padding or explanation of concepts Claude already knows; every section carries system-specific facts (paths, error codes, mount layout). Minor trims are possible (e.g. the Provider SDK query config block and some multi-sentence fix narratives), keeping it at anchor 4 rather than the lean anchor 5.

4 / 5

Actionability

Fully executable throughout: copy-paste-ready SQL via "pnpm exec tsx scripts/q.ts ...", docker/systemctl/ncl commands with exact paths, a precise auth error-code taxonomy with remediation commands, and a complete 7-step diagnostic script. This matches anchor 5's comprehensive, copy-paste-ready coverage of common cases.

5 / 5

Workflow Clarity

Each common issue follows symptom → root cause → diagnosis → fix → verify (e.g. "Verify only one instance runs"), the session-DB section gives an explicit decision tree for reading the message flow, the destructive rm -rf session clear is preceded by "Inspect first", and the Quick Diagnostic Script is a checklist with remediation hints. Explicit validation steps, feedback loops, and a checklist match anchor 5.

5 / 5

Progressive Disclosure

Good structure with clear headers, a log-location table, and clearly signaled one-level-deep references ([docs/db.md](../../../docs/db.md), [docs/db-session.md](../../../docs/db-session.md)). It stays at anchor 4 rather than 5 because all ~300 lines live inline in a single file with no bundle split — some content (e.g. per-issue fix details or the SDK options section) could live in separate reference files.

4 / 5

Total

18

/

20

Passed

Description

62%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.

The description answers both what and when with an explicit trigger clause and a distinct niche, but its action vocabulary is thin (just "Debug") and its trigger terms mix concrete symptoms with generic filler like "things aren't working". It is solid but not comprehensive, sitting at the midpoint-to-good boundary.

Suggestions

Replace the generic "things aren't working" with concrete failure symptoms users would actually say, e.g. "agent not replying", "container exits immediately", or "messages silently lost".

Convert the topic list "Covers logs, session DBs, mounts, and common issues" into concrete actions, e.g. "Inspect session DBs and logs, diagnose delivery failures and auth errors, restart containers, and repair the gateway".

Add natural trigger synonyms such as "bot stopped responding", "container crash", or "agent auth error" to broaden keyword coverage for skill matching.

DimensionReasoningScore

Specificity

The only concrete action verb is "Debug"; "Covers logs, session DBs, mounts, and common issues" enumerates topic areas rather than specific debugging actions. This matches anchor 3 (domain plus limited concrete actions) rather than anchor 4, which requires several specific actions.

3 / 5

Completeness

Both parts are present: "Debug container agent issues... Covers logs, session DBs, mounts" (what) and an explicit "Use when... container fails, authentication problems" clause (when). It falls short of anchor 5 because the when-clause leans on the vague "things aren't working" rather than fully concrete trigger phrases.

4 / 5

Trigger Term Quality

"container fails" and "authentication problems" are natural trigger phrases, but "things aren't working" is generic and common user phrasings like "agent not replying", "bot stopped responding", or "container crash" are missing. Some relevant keywords exist but common variations are absent, matching anchor 3.

3 / 5

Distinctiveness Conflict Risk

"Container agent issues" plus the specific trigger terms carve out a clear niche unlikely to fire for unrelated skills. Minor overlap risk remains from the broad "things aren't working" catch-all, matching anchor 4 rather than the minimal-conflict anchor 5.

4 / 5

Total

14

/

20

Passed

Validation

87%

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

CriteriaDescriptionResult

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

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.