Coding Lead
v3.0.6Coding execution skill for any implementation-focused agent. Current production path is claude-only with simple tasks direct, medium tasks preferring ACP run...
⭐ 0· 1.5k·13 current·13 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description (coding execution) match the instructions: the SKILL.md describes how to classify tasks, detect ACP/acpx/qmd/smart-agent-memory, spawn ACP sessions or fall back to direct file edits/exec. The required capabilities (file I/O, spawning ACP or local acpx, running linters/tests) are appropriate for a coding-execution skill.
Instruction Scope
Instructions explicitly allow reading/writing project files (.openclaw/context-*.md, active-tasks.json), launching ACP sessions or acpx, and running local commands (linters, tests, php artisan, node memory CLI) — all expected for code-execution. This grants the agent broad local file and command execution scope (intended), so users should expect the skill to modify project files and run commands if invoked.
Install Mechanism
Instruction-only skill with no install spec and no code files. No downloads or archive extraction are requested, so there is minimal install-surface risk.
Credentials
The skill declares no required env vars or credentials. It references optional local tools and paths (e.g., ~/.openclaw/skills/smart-agent-memory/scripts/memory-cli.js, acpx CLI, qmd). Those references are proportional to its role and marked as optional/fallback.
Persistence & Privilege
always:false (not forced into every agent run) and normal autonomous invocation settings. The skill writes and reads project-scoped context files under .openclaw and may record to an optional smart-agent-memory CLI; it does not request elevated or cross-skill config modifications.
Assessment
This skill is coherent for a coding-execution role: it will read and write project files (creates .openclaw/context-*.md, updates active-tasks.json), may spawn ACP sessions (prefers Claude) or run local commands and tests as a fallback, and will call optional local CLIs if present (qmd, acpx, smart-agent-memory). Before installing, confirm you trust agents that will be given this skill (they can modify your repo and run commands), ensure sensitive files are excluded or protected (e.g., don’t store secrets in project files), and verify the presence and integrity of any optional local CLIs the skill might invoke. If you want stricter controls, restrict the agent's repository/command permissions or avoid granting this skill to agents allowed to operate autonomously.Like a lobster shell, security has layers — review code before you run it.
latestvk974dq7b5f1k42jfrcrkj7jnxn83x28r
License
MIT-0
Free to use, modify, and redistribute. No attribution required.