Content
100%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
A high-quality conventions reference that delivers PostHog-specific judgment calls the linters cannot enforce, with executable YAML, named canonical files, an explicit lint validation gate, and a closing checklist. It is dense but not padded, and delegates cleanly to narrower sibling skills.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Dense, specialized PostHog knowledge Claude does not already have (dispatch cap, per-SHA concurrency, blobless-checkout foot-guns, App-token buckets) with no basic-concept padding; rationale sentences are the promised 'reasons behind them' rather than fluff, so every token earns its place. | 3 / 3 |
Actionability | Provides copy-paste YAML blocks (concurrency group, bounded blobless checkout, paths filter, App-token with fork fallback), concrete commands ('bin/hogli lint:workflows', 'actionlint'), and named canonical files, matching the executable copy-paste-ready anchor. | 3 / 3 |
Workflow Clarity | Sequenced 'Before you write' guidance, an explicit validation gate ('Run bin/hogli lint:workflows and actionlint before pushing'), a 'New-workflow checklist', and error-recovery guidance (empty-mode normalization on drafts, continue-on-error then promote-to-blocking rollout) satisfy the clear-sequence-with-validation-and-feedback anchor. | 3 / 3 |
Progressive Disclosure | No bundle files exist, so the skill is appropriately self-contained and well-sectioned; it delegates to sibling skills one level deep with clear signaling ('Related skills — reach for these instead of duplicating them here') rather than nesting references. | 3 / 3 |
Total | 12 / 12 Passed |