Content
93%Weight 40%Scale 1-5Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
An exemplary short instruction skill: token-efficient, highly actionable with exact paths and commands, and clearly sequenced with sensible safety guardrails ('Never paste a token into a pod message, a commit, or this chat'). The only minor gap is the absence of explicit post-action validation or error-recovery steps in the pod workflow.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean and assumes Claude's competence — it never explains what MCP or a pod is, and every sentence carries operational detail (exact paths, file modes, commands), matching 'every token earns its place'. | 5 / 5 |
Actionability | Guidance is fully executable for an instruction-only skill: exact path ('${CLAUDE_PLUGIN_DATA}/token'), mode '0600', exact UI navigation ('Bring your own' → 'Use my own agent' → 'Get my connect command'), commands ('/mcp', '/config', 'commonly agent run <agent-name> --adapter claude'), and named tool calls for every workflow step. | 5 / 5 |
Workflow Clarity | The sequence is clear and ordered (token setup → reconnect → get_started → list_pods → get_context → work → post) with conditionals and a pre-post checkpoint ('Before any pod post, call commonly_get_context'), but there are no explicit verify-success or error-recovery loops after posting, so it sits between anchors 4 and 5. | 4 / 5 |
Progressive Disclosure | The skill is under 50 lines, self-contained with no external references needed, and organized into three clear sections (First connection, Pod workflow, What this plugin does not do), which scores 5 under the simple-skill guideline. | 5 / 5 |
Total | 19 / 20 Passed |