coding-agent

Run Codex CLI, Claude Code, OpenCode, or Pi Coding Agent via background process for programmatic control.

Quality

58%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/coding-agent/SKILL.md

Quality

Discovery

40%

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 identifies a clear niche around running specific coding agents as background processes, which makes it distinctive. However, it lacks a 'Use when...' clause entirely and doesn't enumerate specific concrete actions beyond 'run', making it incomplete and somewhat vague about what programmatic control actually involves.

Suggestions

Add an explicit 'Use when...' clause, e.g., 'Use when the user wants to launch, monitor, or interact with Codex CLI, Claude Code, OpenCode, or Pi Coding Agent as a background subprocess.'

List specific concrete actions such as 'spawn background processes, send prompts programmatically, capture output, monitor status, and terminate sessions'.

Include natural trigger terms users might say, such as 'run agent in background', 'headless coding agent', 'automate with Claude Code', or 'subprocess control'.

Dimension	Reasoning	Score
Specificity	Names specific tools (Codex CLI, Claude Code, OpenCode, Pi Coding Agent) and mentions 'background process' and 'programmatic control', but doesn't list concrete actions beyond 'run'. What does 'programmatic control' actually entail? No specific operations are enumerated.	2 / 3
Completeness	Describes what at a high level (run coding agents via background process) but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. Per rubric guidelines, missing 'Use when' caps completeness at 2, and the 'what' is also weak, so this scores 1.	1 / 3
Trigger Term Quality	Includes good tool-specific keywords like 'Codex CLI', 'Claude Code', 'OpenCode', 'Pi Coding Agent', and 'background process', but misses natural user phrases like 'run agent in background', 'headless mode', 'automate coding agent', or 'spawn subprocess'.	2 / 3
Distinctiveness Conflict Risk	The combination of specific tool names (Codex CLI, Claude Code, OpenCode, Pi Coding Agent) with 'background process' and 'programmatic control' creates a very distinct niche that is unlikely to conflict with other skills.	3 / 3
	Total	8 / 12 Passed

Implementation

77%

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

This is a highly actionable skill with excellent concrete examples and clear multi-step workflows for orchestrating coding agents via bash. Its main weaknesses are moderate verbosity from repeated PTY reminders, informal commentary, and a redundant Learnings section, plus the monolithic structure that could benefit from splitting advanced patterns into separate files. The time-sensitive 'Jan 2026' learnings and specific PR references (like Pi PR #584) add minor maintenance burden.

Suggestions

Remove the redundant 'Learnings (Jan 2026)' section — its points are already covered inline (PTY requirement, git repo requirement, exec usage, submit vs write). The haiku anecdote wastes tokens.

Reduce repeated 'remember PTY!' / 'with PTY!' inline comments — the prominent warning section at the top and the Rules section already cover this; repeating it in every code block is unnecessary.

Consider splitting advanced patterns (batch PR reviews, parallel worktree workflows, auto-notify) into a separate ADVANCED.md or PATTERNS.md file, keeping SKILL.md as a concise overview with references.

Dimension	Reasoning	Score
Conciseness	The skill contains useful information but includes unnecessary commentary (emoji jokes about 'soul.md', 'org chart', 'space lobster haiku'), redundant repetition of 'remember PTY!' across many sections, and the Learnings section largely restates what was already covered. Some tightening would improve token efficiency.	2 / 3
Actionability	Excellent actionability throughout — every section provides concrete, copy-paste-ready bash commands with specific flags, parameters, and real-world usage patterns. The parameter tables, process action tables, and worked examples for PR reviews, parallel issue fixing, and worktrees are all directly executable.	3 / 3
Workflow Clarity	Multi-step workflows are clearly sequenced with numbered steps (e.g., parallel issue fixing: create worktrees → launch agents → monitor → create PRs → cleanup). Background process monitoring is well-documented with poll/log/write/kill actions. The progress updates section provides explicit checkpoints for when to communicate status changes.	3 / 3
Progressive Disclosure	The content is well-structured with clear section headers and logical grouping, but it's a long monolithic file (~200+ lines) with no references to external files. The batch PR review patterns, parallel worktree workflows, and per-agent sections could be split into separate reference files for better organization.	2 / 3
	Total	10 / 12 Passed

Validation

81%

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 — 9 / 11 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning

	Total	9 / 11 Passed

Repository: deepgram/dglabs-deepclaw
Commit: ec8d4f8

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.