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.

Quality

73%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Medium

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./.codex/skills/land/SKILL.md

Quality

Content

63%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.

The body delivers highly concrete, executable landing guidance with strong validation checkpoints and failure-handling loops, but it is overlong for a single SKILL.md. Redundant repetition of the preflight machinery and the absence of any bundle files to split out the extensive review-handling and failure-handling detail are the main drags on quality.

Suggestions

State the preflight command, handoff-note format, and exit-code semantics once (in the Fast Path Preflight section) and reference it from Steps and Commands instead of repeating all three verbatim.

Move the detailed Review Handling and Failure Handling material into reference files (e.g., references/review-handling.md, references/failure-handling.md) with clearly signaled one-level-deep links from SKILL.md.

Fix the internal contradiction between step 13 ("squash-merge and delete the branch") and the Goals section ("No need to delete remote branches after merge"), and reorder the interaction-policy steps (14-18) before the merge step so the sequence reads in execution order.

Dimension	Reasoning	Score
Conciseness	The body is dense and assumes Claude's competence (no beginner explanations), but the preflight command is repeated three times (Steps, Commands, and the Fast Path Preflight section), the handoff-note format appears twice, and review-reply rules are restated across Steps 14-18 and Review Handling — more than minor trimming would fix, fitting anchor 3 rather than anchor 4.	3 / 5
Actionability	Concrete gh commands, exit codes, REST endpoints, and exact [codex] comment prefixes make the guidance mostly executable, but the conflict branch inside the main Commands block contains only comments ("# Run the `pull` skill...") with no executable body, plus <sha>-style placeholders — minor gaps that keep it below anchor 5.	4 / 5
Workflow Clarity	The 18-step sequence has explicit validation gates (preflight exit codes, a final gh pr view re-check, gh pr checks --watch) and error-recovery loops (fix, commit, push, re-watch), but Steps 14-18 (interaction policies) are sequenced after step 13's squash-merge, and step 13 says to delete the branch while the Goals section says branches auto-delete — small inconsistencies that keep it below anchor 5.	4 / 5
Progressive Disclosure	No bundle files exist (no references/, scripts/, or assets/), and the one scripted dependency (.codex/skills/land/land_watch.py) lives outside the bundle at a hardcoded path; section headers are clear, but the bulk of Review Handling and Failure Handling is inlined content that belongs in separate reference files, matching anchor 3 rather than anchor 4 (which requires well-signaled one-level-deep references).	3 / 5
	Total	14 / 20 Passed

Description

83%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.

A strong description that clearly states what the skill does and when to use it, with concrete verbs and natural trigger phrases. Its only weaknesses are minor: slightly incomplete action coverage and the occasional overlap-prone word "merge".

Dimension	Reasoning	Score
Specificity	"monitoring conflicts, resolving them, waiting for checks, and squash-merging when green" lists several concrete actions, but coverage has minor gaps (no mention of review-feedback handling or CI failure fixes), matching anchor 4 rather than the comprehensive anchor 5.	4 / 5
Completeness	It explicitly answers both what ("Land a PR by monitoring conflicts... squash-merging when green") and when ("use when asked to land, merge, or shepherd a PR to completion") with concrete trigger phrases, matching anchor 5; it exceeds anchor 4 because the 'when' clause is fully explicit.	5 / 5
Trigger Term Quality	"use when asked to land, merge, or shepherd a PR" provides natural phrases users would say, but common variations like "pull request" or "CI" are absent, fitting anchor 4 (good coverage, a few natural terms missing) rather than the synonym-complete anchor 5.	4 / 5
Distinctiveness Conflict Risk	"Land a PR" and "shepherd a PR" carve a clear niche with distinct triggers, but the bare term "merge" carries minor overlap risk with generic git-merge tasks, fitting anchor 4 rather than the minimal-conflict anchor 5.	4 / 5
	Total	17 / 20 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: karanhudia/borg-ui
Path: .codex/skills/land/SKILL.md
Commit: 47dfb3e

Reviewed: 4 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.