coding-agent

Delegate coding tasks to Codex, Claude Code, or Pi agents via background host sessions. Use when: (1) building or creating new features or apps, (2) reviewing PRs or parallel coding with managed worktree isolation when subagents are available, (3) refactoring large codebases, (4) iterative coding that needs file exploration. NOT for: simple one-liner fixes (just edit), reading code (use read tool), thread-bound ACP harness requests in chat, or any work in ~/clawd workspace (never spawn agents here). Requires OpenClaw host tools with exec_command plus write_stdin.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Content

65%

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

Highly actionable content with concrete commands for multiple coding agents and a clear monitoring workflow. It is weakened by inline verbosity/jokes, dated notes outside a deprecated section, and a monolithic structure with no progressive disclosure via references.

Suggestions

Move time-sensitive items ('Learnings (Jan 2026)', 'PR #584, merged Jan 2026') into a clearly labeled 'Deprecated / Old patterns' section, or remove the dated commentary, to improve conciseness.

Add explicit validation/verification checkpoints to the batch PR-review and parallel issue-fixing workflows (e.g. a step that confirms tests passed or that findings were verified before reporting) to lift workflow clarity.

Split per-agent detail (Pi install/provider flags, Codex flag reference) and the Learnings into separate reference files linked one level deep from SKILL.md to improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with copy-paste code, but padded with joking commentary ('read your soul docs and get weird ideas about the org chart', 'Skippy gets pinged in seconds') and time-sensitive info placed inline rather than in a deprecated section ('Learnings (Jan 2026)', 'PR #584, merged Jan 2026').	2 / 3
Actionability	Concrete, executable, copy-paste-ready commands throughout (e.g. `exec_command tty:true workdir:~/project command:"codex exec --full-auto '...'"`) with flag tables and follow-up tool usage, matching the fully-executable anchor.	3 / 3
Workflow Clarity	The start/poll/respond/kill monitoring pattern is a real feedback loop, but batch and parallel operations (batch PR reviews, parallel issue fixing) lack explicit validation checkpoints the orchestrator performs — verification is delegated into the subagent task text rather than a checked step.	2 / 3
Progressive Disclosure	Well-sectioned but monolithic ~280-line body with no external references and no bundle files; per-agent details and dated 'Learnings' are inline that could be split out, so it stops short of the one-level-deep reference structure of the top anchor.	2 / 3
	Total	9 / 12 Passed

Description

100%

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, third-person description that states concrete capabilities, provides explicit positive and negative triggers, and carves out a distinct niche. It fully answers both 'what' and 'when' with minimal fluff.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('building or creating new features', 'reviewing PRs', 'refactoring large codebases') tied to specific named agents (Codex, Claude Code, Pi), matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	Explicitly answers both what ('Delegate coding tasks to ... agents via background host sessions') and when (a numbered 'Use when: (1)-(4)' clause plus a 'NOT for:' exclusion list), satisfying the top anchor.	3 / 3
Trigger Term Quality	Natural trigger phrases users would say ('building or creating new features or apps', 'reviewing PRs', 'refactoring large codebases') plus clear negative triggers ('simple one-liner fixes', 'reading code') give good coverage despite some host-tool jargon.	3 / 3
Distinctiveness Conflict Risk	Clear niche (delegating coding work to coding-agent CLIs via host sessions) with explicit 'NOT for' exclusions (one-liners, reading code, ~/clawd work), making conflicts with other skills unlikely.	3 / 3
	Total	12 / 12 Passed

Validation

87%

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 — 14 / 16 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	14 / 16 Passed

Repository: trpc-group/trpc-agent-go
Commit: 737835b

Reviewed: 3 days 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.