Content
96%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 concise, actionable config reference: exact values, executable snippets, and a clearly sequenced edit-then-restart workflow. The only structural weakness is the progressive-disclosure tail — the referenced REFERENCE.md is absent from the bundle, so navigation beyond SKILL.md cannot be confirmed.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The ~30-line body is lean and assumes Claude's competence: no generic explanations of env files, ports, or auth concepts; every line delivers a fact specific to agentmemory ('Restart the server after changing it', the port arithmetic, 'one KEY=value per line, no export prefix'). | 5 / 5 |
Actionability | Guidance is copy-paste ready: an exact env-file path with a concrete three-line env block, exact port numbers and relocation flags ('--port <N>', '--instance <N>'), exact settings values ('AGENTMEMORY_TOOLS=all ... or core'), and a concrete auth pattern ('Authorization: Bearer'). | 5 / 5 |
Workflow Clarity | This is a simple single-purpose skill under 50 lines, and the single workflow is unambiguous: edit ~/.agentmemory/.env (format constraints stated), then 'Restart the server after changing it'. No destructive or batch operations are involved, so no validation checkpoints are required. | 5 / 5 |
Progressive Disclosure | Sections are well organized (Quick start, Defaults, Ports, See also, Reference) and the one external pointer ('The full recognized-variable list lives in REFERENCE.md') is clearly signaled and one level deep. However, REFERENCE.md is not present in the skill bundle, so the pointer is unverifiable, and the 'See also' items are bare skill names without paths. | 4 / 5 |
Total | 19 / 20 Passed |