cursor-do

Delegate a single write task to Cursor Composer via cursor-companion.sh inside an isolated worktree, then Lead-review the diff and cherry-pick. Use when user invokes cursor:do, says delegate to cursor, have composer write it, refactor with cursor, hand a file edit to Composer. Do NOT load for: planning, code review only, read-only investigation, or multi-task team runs (use breezing --cursor or cursor:ask instead).

Quality

90%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

81%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A highly actionable, well-gated procedural skill with executable scripts and strong validation/feedback loops. Its main weakness is token efficiency from duplicating the plugin-root resolution script across steps.

Suggestions

Extract the repeated valid_root plugin-root resolution block into a sourced helper script (e.g. scripts/resolve-plugin-root.sh) and call it from Step 3 and Step 5 instead of inlining the ~40 lines twice.

Tighten the Step 0 narration-rules section by collapsing the violation/normal example blocks into a single compact do/don't pair to reduce token weight.

Consider moving the large per-step bash blocks into a scripts/ companion so SKILL.md reads as an overview with one-level-deep references, improving progressive_disclosure.

Dimension	Reasoning	Score
Conciseness	Operational prose is tight and assumes Claude's competence (no basic-concept padding), but the ~40-line valid_root plugin-root resolution script is duplicated verbatim in Step 3 and Step 5, which is avoidable token cost that 'could be tightened' into a sourced helper.	3 / 5
Actionability	Every step ships a complete, copy-paste-ready bash block with real commands (git worktree add, cherry-pick, contract-grep gates) and concrete error/exit-code handling, covering the common cases fully executably.	5 / 5
Workflow Clarity	Steps 0–8 are explicitly sequenced with validation checkpoints at every risky point (pre-check, commit-count guard, Plans.md precondition, contract-grep gates, conflict abort) and feedback loops (retry once, REQUEST_CHANGES, ABORT) for a destructive-to-main operation.	5 / 5
Progressive Disclosure	Clean section headers and one well-signaled one-level-deep reference (references/cursor-cli-only.md, a real file) with a Related Skills map, but the bulk of the workflow and bash logic lives inline in SKILL.md rather than being split out.	4 / 5
	Total	17 / 20 Passed

Description

100%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is a strong, dense trigger specification: concrete actions, natural user phrasing with synonyms, explicit what/when, and clear negative guidance separating it from adjacent skills. No vague fluff or over-claims.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Delegate a single write task to Cursor Composer via cursor-companion.sh inside an isolated worktree, then Lead-review the diff and cherry-pick' — naming the specific tool, the isolation mechanism, and the review/merge actions, which matches the comprehensive-coverage anchor.	5 / 5
Completeness	Explicitly answers both what (delegate→review→cherry-pick) and when ('Use when user invokes cursor:do, says delegate to cursor…') with concrete trigger phrases, plus a 'Do NOT load for' exclusion clause, matching the top anchor.	5 / 5
Trigger Term Quality	Covers natural phrases a user would say — 'delegate to cursor', 'have composer write it', 'refactor with cursor', 'hand a file edit to Composer' — plus the synonym pair cursor/composer and the explicit invocation 'cursor:do', matching the comprehensive synonym coverage anchor.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear single-task-write-delegate niche and explicitly disambiguates from siblings ('use breezing --cursor or cursor:ask instead'), giving minimal conflict risk.	5 / 5
	Total	20 / 20 Passed

Validation

87%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 2 missing, 2 deeper-than-1-level	Warning
referenced_paths_exist	Referenced path issues: 4 missing, 1 deeper-than-1-level	Warning

	Total	14 / 16 Passed

Repository: Chachamaru127/claude-code-harness
Path: opencode/skills/cursor-do/SKILL.md
Commit: 7d8deba

Reviewed: about 15 hours ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.