claude-code-bridge

Integrate with Claude Code CLI for delegating complex coding tasks. Use when you need to spawn a separate Claude Code instance to work on files, run tests, or perform multi-step coding operations in a specific directory. Enables "Claude calling Claude" patterns for parallel work or specialized contexts.

Quality

79%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./planning/done/claude-code-integration/claude-code-bridge/skill/SKILL.md

Quality

Content

75%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.

The body is well-organized, mostly executable, and reasonably concise, with clear usage patterns and a validation-aware best-practices section. Its main weaknesses are non-executable MCP workflow pseudo-syntax and minor redundancy.

Suggestions

Replace the '[claude_prompt] prompt: ...' pseudo-syntax in Example Workflows with the actual MCP tool-call format or concrete CLI commands so the examples are copy-paste executable.

Consolidate the two MCP server config variants (claude_desktop_config.json vs ~/.claude/settings.json) into one canonical block with a brief note on the alternative to reduce redundancy.

Add an explicit validation/checklist step in the delegation workflow (e.g., verify output, capture session ID, re-run on failure) to strengthen the feedback loop for risky or multi-step tasks.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean and code-forward with minimal concept explanation, but the 'When to Use' section restates the description and the duplicate MCP config variants add mild padding that could be trimmed.	4 / 5
Actionability	Provides executable bash commands and concrete JSON/Rust snippets, but the MCP example workflows use a non-executable pseudo-syntax ('[claude_prompt]\nprompt: ...') rather than real tool calls, leaving a minor gap.	4 / 5
Workflow Clarity	The 'Refactoring with Followup' example sequences identify-then-migrate with an explicit 'After reviewing results' checkpoint, and Best Practice #5 ('Check Results: Verify Claude Code's output') adds validation, though formal feedback loops for risky ops are only implicit.	4 / 5
Progressive Disclosure	A single self-contained file with clear, well-signaled section headers and no nested references; minor organization gaps (redundant config block, illustrative pseudo-syntax blocks) keep it just below 5.	4 / 5
	Total	16 / 20 Passed

Description

83%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, well-structured description that clearly states both capability and trigger conditions with concrete use cases. It is specific and distinct, with only minor gaps in action specificity and synonym coverage.

Dimension	Reasoning	Score
Specificity	Names the domain (Claude Code CLI integration) and several concrete actions — 'work on files, run tests, or perform multi-step coding operations' plus 'spawn a separate Claude Code instance' — but the actions are general categories rather than sharply named operations, so it sits at 4 rather than 5.	4 / 5
Completeness	Explicitly answers both 'what' ('Integrate with Claude Code CLI for delegating complex coding tasks') and 'when' via a concrete 'Use when you need to spawn... to work on files, run tests, or perform multi-step coding operations' trigger clause.	5 / 5
Trigger Term Quality	Includes natural phrases a user might say ('delegating coding tasks', 'spawn a separate Claude Code instance', 'parallel work', 'run tests') with a clear 'Use when' trigger, but lacks synonyms and file/extension-style variations that would push it to 5.	4 / 5
Distinctiveness Conflict Risk	The 'Claude calling Claude' / spawn-a-separate-instance niche is distinct, but the secondary triggers ('work on files', 'run tests') overlap with general coding skills, leaving minor conflict risk.	4 / 5
	Total	17 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: Raudbjorn/TTTRPS
Path: planning/done/claude-code-integration/claude-code-bridge/skill/SKILL.md
Commit: abd89fa

Reviewed: 1 day 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.