land

Land a PR by monitoring conflicts, resolving them, waiting for checks, and squash-merging when green; use when asked to land, merge, or shepherd a PR to completion.

1.90x

Quality

88%

Does it follow best practices?

Impact

95%

1.90x

Average score across 3 eval scenarios

Securityby

Low

Low-risk findings worth noting

Quality

Content

77%Weight 40%Scale 1-3

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-sequenced landing workflow with strong validation and failure-handling loops, undermined by verbosity and a missing referenced helper script. Tightening repetition and shipping or removing the land_watch.py reference would lift it further.

Suggestions

Ship the referenced `land_watch.py` in a scripts/ bundle or remove the reference and rely solely on the documented manual loop, since the file is currently a broken reference.

Deduplicate the Codex review guidance — the '## Codex Review — <persona>' format and the reply/acknowledgment rules are restated across Steps, Commands, Failure Handling, and Review Handling; consolidate into one section.

Move the detailed Review Handling and PR-metadata procedures into a separate reference file (e.g. REVIEW_HANDLING.md) and keep SKILL.md as a lean overview to reduce the inline monolith.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient but repeats guidance (Codex review comment format and the '## Codex Review — <persona>' signal are explained several times) and re-states concepts like mergeability and gh CLI behavior Claude already knows, so it could be tightened.	2 / 3
Actionability	Provides copy-paste-ready, executable commands — `gh pr view`, `gh pr checks --watch`, `gh pr merge --squash --subject ... --body ...`, and exact `gh api` endpoints with flags and `in_reply_to` id guidance.	3 / 3
Workflow Clarity	Steps 1–14 are clearly sequenced with explicit validation checkpoints ('confirm the full gauntlet is green locally before any push', 'watch checks until complete') and failure feedback loops (fix, commit, push, re-run) for risky merge operations.	3 / 3
Progressive Disclosure	Sections are organized, but the body is a single monolithic SKILL.md over 200 lines with the large Review Handling block inline, and it references `python3 .codex/skills/land/land_watch.py` — a script absent from the bundle (no scripts/ directory exists), a broken one-level reference.	2 / 3
	Total	10 / 12 Passed

Description

100%Weight 40%Scale 1-3

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

A concise, third-person description that clearly states concrete capabilities and an explicit trigger clause. It cleanly answers both what the skill does and when to invoke it.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions — 'monitoring conflicts, resolving them, waiting for checks, and squash-merging when green' — rather than vague language, matching the multiple-specific-actions anchor.	3 / 3
Completeness	Explicitly answers both what it does (monitor/resolve/wait/squash-merge) and when to use it via an explicit 'use when ...' trigger clause.	3 / 3
Trigger Term Quality	The 'use when asked to land, merge, or shepherd a PR to completion' clause covers natural terms a user would actually say (land, merge, shepherd a PR).	3 / 3
Distinctiveness Conflict Risk	The squash-merge-and-shepherd-to-completion niche with distinct triggers ('land', 'shepherd a PR') is unlikely to conflict with other skills.	3 / 3
	Total	12 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: openai/symphony
Path: .codex/skills/land/SKILL.md
Commit: 1f3219b

Reviewed: 12 days 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.