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.
90
88%
Does it follow best practices?
Impact
95%
1.72xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Quality
Discovery
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.
This is an excellent skill description that clearly defines what it does (delegate coding tasks to specific agents), when to use it (four enumerated scenarios), and critically, when NOT to use it (five exclusion cases). The inclusion of specific agent names, technical flags, and boundary conditions makes it highly actionable for skill selection. The description uses appropriate third-person voice and avoids vague language.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: building/creating new features, reviewing PRs (with detail about temp dir), refactoring large codebases, iterative coding with file exploration. Also specifies concrete exclusions and technical flags like '--print --permission-mode bypassPermissions' and 'pty:true'. | 3 / 3 |
Completeness | Clearly answers both 'what' (delegate coding tasks to specific agents via background process) and 'when' with an explicit numbered 'Use when:' clause covering four scenarios, plus a 'NOT for:' section that clarifies boundaries. This is thorough and explicit. | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would say: 'coding tasks', 'Codex', 'Claude Code', 'Pi agents', 'building', 'creating new features', 'reviewing PRs', 'refactoring', 'spawn', 'background process'. Good coverage of agent names and coding workflow terms. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with clear niche around delegating to specific named agents (Codex, Claude Code, Pi) via background processes. The explicit 'NOT for' exclusions (simple edits, reading code, ACP harness requests, ~/clawd workspace) sharply delineate boundaries and reduce conflict risk with other coding or reading skills. | 3 / 3 |
Total | 12 / 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 and well-structured skill with excellent executable examples covering multiple coding agents and workflows. Its main weaknesses are verbosity (casual asides, the haiku, some redundant explanations) and the monolithic structure that could benefit from splitting agent-specific details into separate reference files. The workflow clarity is strong with good sequencing and monitoring patterns for background processes.
Suggestions
Remove casual/humorous asides (haiku, 'gets weird ideas about the org chart', emoji commentary) to improve token efficiency — these don't help Claude execute tasks.
Extract agent-specific sections (Codex CLI details, Pi options, OpenCode) into separate reference files and link from the main skill to improve progressive disclosure.
Remove the 'Learnings (Jan 2026)' section — most points are already covered inline (PTY requirements, git repo requirement, exec usage), making this redundant.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill contains some unnecessary content (emoji humor, the haiku anecdote, casual asides like 'gets weird ideas about the org chart') and could be tightened. However, most content is functional and relevant. The tables documenting parameters are useful but some could be trimmed since Claude knows bash tool parameters. | 2 / 3 |
Actionability | Excellent actionability throughout — every section provides copy-paste ready bash commands with correct flags, concrete examples for each agent (Codex, Claude Code, Pi, OpenCode), and specific patterns for PR reviews, parallel work, and worktrees. The commands are executable and complete. | 3 / 3 |
Workflow Clarity | Multi-step workflows are clearly sequenced (e.g., the parallel issue fixing section has numbered steps: create worktrees → launch agents → monitor → create PRs → cleanup). Background process monitoring is well-documented with poll/log/kill actions. The PR review workflow includes cleanup steps. Progress update guidelines serve as validation checkpoints for background operations. | 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 for detailed content. The agent-specific sections (Codex, Claude Code, Pi, OpenCode) and the parameter tables could be split into separate reference files to keep the main skill leaner. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
81%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
- qsimeon/openclaw-engaging
- Commit
4467e04
- 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.