CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

64

Quality

75%

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/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.

The body is well-structured and action-packed with executable examples across MCP, CLI, and Rust interfaces, but it has minor redundancy in the example workflows and—critically—lacks explicit validation checkpoints in its destructive/batch delegation workflows, capping workflow clarity.

Suggestions

Add an explicit verification checkpoint to the destructive/batch example workflows (e.g., after the API-v2 migration, insert a step that runs the test suite or reviews the diff before proceeding) so workflow_clarity is not capped at 3.

Trim the redundant Example Workflows or fold them into the Usage Patterns section, and remove filler prose intros like 'Let me have Claude Code generate tests:' to tighten conciseness.

Replace the pseudo-syntax [claude_prompt] blocks with the real MCP tool-call format (or clearly label them as illustrative) so the examples are fully copy-paste ready.

DimensionReasoningScore

Conciseness

Mostly efficient with terse bullets and code blocks, but the Example Workflows re-demonstrate claude_prompt patterns already documented and include filler prose intros ('I'll use Claude Code to review...', 'Let me have Claude Code generate tests:'), which is minor over-explanation that could be trimmed.

4 / 5

Actionability

Provides mostly executable guidance—copy-paste bash commands, a Rust example, MCP tool list, and JSON config—but the [claude_prompt] blocks use pseudo-syntax with field labels rather than a verbatim real call format, leaving minor gaps versus fully copy-paste-ready examples.

4 / 5

Workflow Clarity

A loose sequence exists in Best Practices (including a 'Check Results' validation step), but the Example Workflows—especially the refactoring-with-followup that migrates files via claude_continue—have only implicit validation with no explicit verify/run-tests checkpoint, so the destructive/batch cap of 3 applies.

3 / 5

Progressive Disclosure

Well-organized into clear sections with no monolithic wall of text, but no bundle/reference files exist and inlined content (two MCP config variants, the Rust library example) could be split out, leaving minor organization gaps short of a fully separated overview-plus-references structure.

4 / 5

Total

15

/

20

Passed

Description

82%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' trigger clause, clear what/when coverage, and a distinctive niche. The only weakness is that the listed capabilities are phrased somewhat generically rather than as sharply distinct actions.

DimensionReasoningScore

Specificity

Names the domain and several concrete actions ('work on files, run tests, or perform multi-step coding operations') but the actions are framed generically rather than as distinct specific capabilities, matching the anchor that lists 1-2 concrete actions without comprehensive coverage.

3 / 5

Completeness

Explicitly answers both what ('Integrate with Claude Code CLI for delegating complex coding tasks') and when ('Use when you need to spawn a separate Claude Code instance to work on files, run tests...') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Covers the niche's natural terms well ('delegate coding tasks', 'spawn a separate Claude Code instance', 'Claude calling Claude', 'parallel work', 'multi-step coding operations') with only minor synonyms missing, fitting good-but-not-comprehensive keyword coverage.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear, specific niche ('Claude Code CLI', 'spawn a separate Claude Code instance', 'Claude calling Claude') with distinct triggers and minimal overlap risk with other skills.

5 / 5

Total

17

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
Raudbjorn/TTTRPS
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.