CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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

78%

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

Fix and improve this skill with Tessl

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

Quality

Content

68%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 well-structured, mostly lean skill file with executable commands, complete configuration examples, and coherent example workflows. Its weakest area is workflow validation: verification of delegated Claude Code output is only mentioned abstractly rather than built into the workflows as concrete checkpoints.

Suggestions

Integrate explicit validation into the workflows, e.g., 'Parse the JSON response and check the result status/exit code before proceeding; if the task failed, use claude_continue with corrective instructions.'

Add a concrete verification step to the Error Handling section, such as a sample command showing how to inspect a failed or timed-out response.

Replace the pseudo-syntax MCP examples ('[claude_prompt] prompt: ...') with an actual example of invoking the tool, and add dependency/setup details for the Rust library example.

DimensionReasoningScore

Conciseness

The body is efficient: bullets, runnable code blocks, and no explanations of concepts Claude already knows. Minor instances of over-explanation remain — the opening tagline duplicates the frontmatter description, and the three parallel usage methods (MCP, CLI, Rust) add slight bulk that could be trimmed. Fits anchor 4 better than anchor 5, where every token would earn its place.

4 / 5

Actionability

Mostly executable guidance: concrete CLI commands ('claude -p "..." --output-format json', '--continue', '--resume'), a complete MCP server config JSON, and an install command for error handling. Gaps keep it below anchor 5: MCP examples use pseudo-syntax ('[claude_prompt] prompt: ...') rather than a real tool call, and the Rust example lacks dependency/setup information.

4 / 5

Workflow Clarity

Example workflows show a clear sequence (prompt, review results, then continue/resume), and Error Handling covers failure modes, but validation checkpoints are implicit: 'Check Results: Verify Claude Code's output before proceeding' is a best-practices bullet with no concrete verification step (e.g., checking the result status or exit code in the JSON output) integrated into the workflows. Fits anchor 3 (sequence present, checkpoints missing or implicit) better than anchor 4 (most checkpoints present).

3 / 5

Progressive Disclosure

Well-organized single-file structure (When to Use, Usage Patterns, Configuration, Best Practices, Example Workflows, Error Handling) with no nested references and no content that clearly belongs in a separate file. It does not qualify for the simple-skill exception (body exceeds 50 lines), so anchor 4 (good structure, appropriately placed content) applies rather than 5.

4 / 5

Total

15

/

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 strong description with an explicit 'Use when...' clause, concrete capabilities, and natural trigger terms for a well-defined niche. Its main flaw is second-person voice ('Use when you need to'), which the guidelines penalize, and slightly incomplete synonym coverage for triggers.

Suggestions

Rewrite in third-person voice to avoid the second-person penalty, e.g., 'Use when spawning a separate Claude Code instance to work on files, run tests, or perform multi-step coding operations in a specific directory.'

Broaden trigger term coverage with natural synonyms users would say, such as 'delegate to Claude Code', 'run a sub-Claude', or 'launch another Claude instance'.

DimensionReasoningScore

Specificity

The description names several concrete actions ('spawn a separate Claude Code instance to work on files, run tests, or perform multi-step coding operations'), which fits anchor 4, but the second-person 'Use when you need to...' violates the third-person voice rule, reducing specificity by 1 to 3. Pre-penalty it is not anchor 5 because coverage of capabilities is not comprehensive.

3 / 5

Completeness

It explicitly answers both 'what' ('Integrate with Claude Code CLI for delegating complex coding tasks') and 'when' with concrete trigger phrases ('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'), matching the anchor 5 example pattern.

5 / 5

Trigger Term Quality

Good natural keyword coverage including 'Claude Code', 'delegating complex coding tasks', 'spawn', 'run tests', and 'parallel work' that users would plausibly say. It falls short of anchor 5 because common synonyms and variations (e.g., 'delegate to Claude', 'subagent', 'sub-Claude', 'claude -p') are missing.

4 / 5

Distinctiveness Conflict Risk

A clear niche (spawning separate Claude Code instances, 'Claude calling Claude' patterns) with distinct triggers, but minor overlap risk with agent-orchestration or Claude-API-related skills whose users might phrase requests similarly. This fits anchor 4 (mostly distinct, minor overlap) better than anchor 5 (minimal conflict risk).

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

Raudbjorn/TTTRPS

Path

planning/done/claude-code-integration/claude-code-bridge/skill/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.