Content
68%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.
A tight, well-organized policy/persona skill that respects the token budget almost perfectly — no padding, no over-explanation, clearly scoped activation triggers and guardrails. Its weakness is actionability and workflow: directives like "reinforce the frame" and "escalate to the CEO" lack concrete mechanics, and the growth-strategy file lifecycle is implied rather than sequenced. Fixing the dangling persona reference and adding one exemplar hook would resolve the remaining gaps.
Suggestions
Add a one-line exemplar of a good conversion-surface hook (e.g. a before/after README hero snippet) so the "one-line hook, runnable example, clear next step" rule is executable rather than evaluative.
Specify what "annotate them with growth implications and escalate to the CEO" concretely means — where the annotation goes and what the escalation action is.
Fix or inline the persona reference at ../../../.apm/agents/oss-growth-hacker.agent.md — the relative path does not resolve from the skill's directory.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The 37-line body is lean and rule-dense: no explanations of concepts Claude already knows, no padding, every line carries a directive ("Every conversion surface needs a one-line hook, a runnable example, and a clear next step"). Anchor 5 fits; there is nothing to trim, so 4 is excluded. | 5 / 5 |
Actionability | Some concrete, executable guidance exists ("Append-only for dated tactical notes; concise top-level summary kept to one screen", "Never stage or commit anything under WIP/", the hook/example/next-step criteria), but key execution details are missing: no example of what a good hook looks like, no mechanics for "escalate to the CEO", and abstract directives like "Reinforce the 'package manager for AI-native development' frame... Cut anything that dilutes it". Anchor 3 fits; not 4 because several directives lack the specifics to execute them, not 2 because there is real concrete guidance. | 3 / 5 |
Workflow Clarity | The activation checklist ("When to activate") is clear, but no sequenced process is laid out — the WIP/growth-strategy.md lifecycle ("create it locally on first use", "append-only for dated tactical notes", "concise top-level summary kept to one screen") is scattered across rules rather than presented as a sequence, and there are no validation checkpoints. Anchor 3 fits; not 4 because steps are not explicitly ordered, not 2 because the structure is coherent and no destructive/batch operation requires the validation cap. | 3 / 5 |
Progressive Disclosure | The body is under 50 lines with no bundle directories, and is cleanly organized into "When to activate" and "Key rules" sections with content appropriately inlined. Anchor 4 rather than 5 only because the sole external reference — the persona link at ../../../.apm/agents/oss-growth-hacker.agent.md — is a relative path that does not resolve from the skill's own directory and is not clearly signposted beyond the bare link; not 3 because nothing that belongs in a separate file is inlined. | 4 / 5 |
Total | 15 / 20 Passed |