CtrlK
BlogDocsLog inGet started
Tessl Logo

claude-code

Operate Claude Code CLI (v2.1+) via the terminal only when the user explicitly requests Claude Code or names this skill. Covers print mode (-p), interactive tmux sessions, and background (--bg) orchestration.

75

Quality

93%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Critical

Do not install without reviewing

SKILL.md
Quality
Evals
Security

Quality

Content

87%

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

The body is lean, highly actionable, and well-structured with verified progressive-disclosure references. Its one weakness is workflow_clarity: validation and error-recovery checkpoints for the long-running/background and tmux workflows are signaled but not laid out as explicit ordered feedback loops.

Suggestions

Add an explicit ordered validation/recovery chain for background and interactive workflows (e.g. '1. Start --bg -> 2. poll claude logs <id> until subtype != running -> 3. on error_max_turns/budget, --resume with adjusted --allowedTools -> 4. verify via git diff') so feedback loops are concrete, not implied.

For the destructive/cleanup steps, state an explicit checkpoint ('Verify claude agents --json --all shows no running sessions before killing tmux') rather than a flat cleanup bullet.

Make the print-mode verification checkpoint explicit ('Check JSON subtype == success; if error_max_turns, --resume with higher --max-turns') to turn the implicit guidance into an ordered loop.

DimensionReasoningScore

Conciseness

Dense tables and compact prose with no concept explanations or padding; every line carries executable guidance, matching the lean/efficient anchor. Version metadata is brief factual scope, not the deprecated-API anti-pattern.

3 / 3

Actionability

Provides fully executable, copy-paste-ready commands with real flags and concrete example prompts (e.g. 'claude -p ... --allowedTools ... --max-turns 10 --output-format json'), matching the executable-code anchor.

3 / 3

Workflow Clarity

The mode-selection table and numbered guardrails give a clear decision sequence and cleanup checklist, but validation checkpoints and validate->fix->retry feedback loops are mostly implicit rather than the explicit, ordered recovery chain the score-3 anchor rewards.

2 / 3

Progressive Disclosure

The body is a concise overview with five inline-signaled, one-level-deep references plus a 'Read when' navigation table; all referenced paths resolve to real bundle files, matching the clear-overview anchor.

3 / 3

Total

11

/

12

Passed

Description

100%

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 is specific, complete, and low-conflict: it states concrete capabilities with flags and gives an explicit use-trigger. It is concise with no vague fluff or over-claims.

DimensionReasoningScore

Specificity

Names multiple concrete capabilities with their flags ('print mode (-p), interactive tmux sessions, and background (--bg) orchestration'), matching the comprehensive-multi-action anchor rather than the partial score-2 anchor.

3 / 3

Completeness

Explicitly answers both what (the three CLI modes) and when ('only when the user explicitly requests Claude Code or names this skill'), satisfying the explicit-trigger requirement rather than capping at 2.

3 / 3

Trigger Term Quality

Includes the natural term users would say ('explicitly requests Claude Code or names this skill') plus mode keywords, with good coverage rather than missing common variations.

3 / 3

Distinctiveness Conflict Risk

A distinct niche (operating a specific CLI) gated by an explicit-request trigger makes accidental or conflicting invocation unlikely, matching the clear-niche anchor.

3 / 3

Total

12

/

12

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
XiaomiMiMo/MiMo-Code
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.