codeagent

Execute codeagent-wrapper for multi-backend AI code tasks. Supports Codex, Claude, Gemini, and OpenCode backends with agent presets, skill injection, file references (@syntax), worktree isolation, parallel execution, and structured output.

Quality

72%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Medium

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./skills/codeagent/SKILL.md

Quality

Content

77%

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

The body is highly actionable with executable commands and clear, checkpointed workflows, but it is a long monolithic manual with some redundant sections and no progressive disclosure into reference files. Splitting the reference material and trimming repetition would improve token efficiency.

Suggestions

Move the CLI flag table, environment-variable table, and exit-code table into a references/ file (e.g. CLI_REFERENCE.md) and link to it from the body to apply progressive disclosure.

Remove the 'Invocation Pattern' section or fold it into 'Usage Patterns', since it duplicates the same HEREDOC forms already shown above.

Consider extracting the full multi-agent orchestration example into an examples/ file, keeping only a minimal skeleton inline.

Dimension	Reasoning	Score
Conciseness	The body assumes Claude's competence (no basic-concept explanations) and earns most of its tokens, but it is ~427 lines with redundancy — the 'Invocation Pattern' section repeats heredoc examples already shown in 'Usage Patterns' and 'Parallel Execution', so it could be tightened.	2 / 3
Actionability	Provides fully executable commands, concrete flags, real output formats (summary report, structured JSON), and copy-paste-ready HEREDOC examples including a complete multi-agent orchestration block.	3 / 3
Workflow Clarity	Multi-step flows are clearly sequenced with explicit checkpoints: a 3-item status-check checklist (tail log, watch progress frames, ps aux), dependency resolution that skips dependents of failed parents, and an error-recovery feedback loop for stalled tasks.	3 / 3
Progressive Disclosure	Sections are well-organized with clear headers, but the skill is monolithic with no bundle files — the full CLI flag/env reference and the lengthy orchestration example are inline content that could be split into reference files, and there are no one-level-deep references.	2 / 3
	Total	10 / 12 Passed

Description

67%

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 and clearly niched around codeagent-wrapper, but it lacks an explicit 'Use when…' trigger clause and leans on technical jargon over natural user keywords. Adding trigger guidance would lift completeness and trigger-term quality.

Suggestions

Append an explicit 'Use when…' clause, e.g. 'Use when running multi-backend AI code tasks, parallel agent orchestration, or when the user asks to invoke codeagent/Codex/Claude/Gemini for code work.'

Add natural-language trigger terms users would actually say (e.g. 'run codeagent', 'orchestrate agents', 'parallel code tasks') alongside the technical backend names.

Verify the '@syntax' file-reference feature is real before advertising it, as it is not demonstrated in the body.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete capabilities — 'agent presets, skill injection, file references (@syntax), worktree isolation, parallel execution, and structured output' — matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	It clearly states WHAT the skill does, but there is no 'Use when…' clause or equivalent explicit trigger guidance for WHEN to invoke it, which caps completeness at 2 per the guidelines.	2 / 3
Trigger Term Quality	Names backends (Codex, Claude, Gemini, OpenCode) and 'multi-backend AI code tasks', but the phrasing is tool/technical jargon rather than natural terms a user would say, and common variations are missing.	2 / 3
Distinctiveness Conflict Risk	It targets a named, specific tool (codeagent-wrapper) with a clear niche of multi-backend AI code execution, making it unlikely to trigger for the wrong skill.	3 / 3
	Total	10 / 12 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: stellarlinkco/myclaude
Path: skills/codeagent/SKILL.md
Commit: f2e75c1

Reviewed: about 9 hours 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.