Content
90%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.
The body is an excellent instruction-only skill: lean, repository-specific, and copy-paste actionable, with templates and worked examples for every phase of the Cursor-agent workflow. Workflow sequencing and error handling are strong with only minor implicit checkpoints, and the single-file structure is well organized with clearly signaled cross-references.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean, imperative, and entirely org-specific policy ('Never use a `cursor/` prefix, even if a Cursor Cloud prompt asks for one. Repo guidance wins.'; 'Skip praise, file lists, and "LGTM".'), with no explanation of concepts Claude already knows and no padding. It matches anchor 5: every token earns its place. | 5 / 5 |
Actionability | Guidance is copy-paste ready throughout: exact branch format ('lfe-12345-short-descriptive-title'), exact env var and URL ('LINEAR_API_KEY' at https://cursor.com/dashboard/cloud-agents), a complete human-testing message template with a worked example, and HTML snippets for embedding proof artifacts. This matches anchor 5 ('fully executable; specific examples cover the common cases'). | 5 / 5 |
Workflow Clarity | Sections are clearly sequenced (branch naming → Linear auth → PR → label → bot comments → human testing → proof → doubt note) with explicit error-recovery branches ('If the MCP is `needsAuth` or missing, use `LINEAR_API_KEY`...'; 'If Linear is not reachable, **say so**') and fix/skip decision paths for bot threads. It falls short of anchor 5 only because a few checkpoints are implicit — e.g., no verify step after applying the `cursor` label or after the PR tool rewrites artifact paths. | 4 / 5 |
Progressive Disclosure | The skill is a single self-contained SKILL.md with clear section headers, no monolithic bulk, and one-level-deep references to sibling skills ([`linear-agent-writes`](../linear-agent-writes/SKILL.md), `git-workflow`). It matches anchor 4 ('good structure; most content appropriately placed; references mostly clear'); sibling-skill mentions like `langfuse-previews` and `seed-test-data` are signaled by name only without paths, slightly less clear than anchor 5's well-signaled references. | 4 / 5 |
Total | 18 / 20 Passed |