coding-agent

Delegate coding tasks to Codex, Claude Code, or Pi agents via background process. Use when: (1) building/creating new features or apps, (2) reviewing PRs (spawn in temp dir), (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 (for example spawn/run Codex or Claude Code in a Discord thread; use sessions_spawn with runtime:"acp"), or any work in ~/clawd workspace (never spawn agents here). Claude Code: use --print --permission-mode bypassPermissions (no PTY). Codex/Pi/OpenCode: pty:true required.

Quality

82%

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

The canonical home for this skill is coding-agent in qsimeon/openclaw-engaging

Quality

Content

65%

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

The content is highly actionable with concrete executable commands and clear multi-step patterns, but it is padded with jokes/anecdotes and inline time-sensitive notes, and the batch/destructive workflows lack explicit validation checkpoints. Progressive disclosure is limited by the single-file monolith.

Suggestions

Remove the haiku anecdote and joke callouts (e.g., 'soul.md', 'org chart') to tighten the body and improve token efficiency.

Move the 'Learnings (Jan 2026)' and the 'PR #584, merged Jan 2026' note into a clearly labeled dated/deprecated section, or drop them, so time-sensitive content stops penalizing conciseness.

Add explicit validation checkpoints to the batch/parallel workflows (e.g., run build/tests and confirm they pass before 'git push' and 'gh pr create').

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient executable commands, but it includes padding (jokes like 'like your soul.md', a haiku anecdote, 'weird ideas about the org chart') and inline time-sensitive notes ('merged Jan 2026', a 'Learnings (Jan 2026)' section) that don't earn their tokens.	2 / 3
Actionability	Provides fully executable, copy-paste-ready bash commands across Codex, Claude Code, OpenCode, and Pi with concrete flags, workdir/background/pty parameters, and parameter tables, matching the 'copy-paste ready' anchor.	3 / 3
Workflow Clarity	Multi-step sequences (the workdir+background+pty pattern, parallel worktree fixes) are clearly listed with monitoring steps, but the destructive/batch operations (git push + gh pr create, parallel fixes) lack explicit validation checkpoints before proceeding, which caps the score at 2.	2 / 3
Progressive Disclosure	No bundle files exist; the ~287-line skill is a monolithic single file with well-organized headers but per-agent CLI detail that could be split out, and there are no one-level-deep external references, so it sits at 'some structure, content that should be separate is inline'.	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.

The description is third-person, comprehensive, and well-scoped: it states concrete actions, explicit positive and negative triggers, and clearly distinguishes the skill from adjacent tools. It fully satisfies every dimension with no over-claims or fluff.

Dimension	Reasoning	Score
Specificity	Names the specific agents (Codex, Claude Code, Pi) and four distinct concrete actions (building/creating features, reviewing PRs, refactoring large codebases, iterative coding with file exploration), matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	Explicitly answers both what ('Delegate coding tasks to Codex, Claude Code, or Pi agents via background process') and when (an explicit 'Use when:' clause with four numbered cases and a 'NOT for:' clause), satisfying the top anchor.	3 / 3
Trigger Term Quality	Uses natural phrases users would say ('building/creating new features or apps', 'reviewing PRs', 'refactoring large codebases', 'iterative coding') plus negative triggers ('simple one-liner fixes', 'reading code'), giving good coverage of common variations.	3 / 3
Distinctiveness Conflict Risk	The 'NOT for' clause actively disambiguates from adjacent tools (simple edits, reading code, thread-bound ACP harness requests) and scopes the niche to background-process delegation of coding agents, making conflicts unlikely.	3 / 3
	Total	12 / 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 — 13 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: nexu-io/nexu
Path: apps/desktop/static/bundled-skills/coding-agent/SKILL.md
Commit: dadfb1c

Reviewed: about 15 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.