CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

prlanded

Verify a merged PR actually landed correctly in this repo and clean up after it. Use right after a PR merges (especially with auto-merge) to confirm the merge commit, or for older PRs the squashed commit, matches your branch by content, catch late commits that were orphaned by the auto-merge race, and post its review record and update memory.

Quality

91%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Medium

Suggest reviewing before use

SKILL.md
Quality
Evals
Security

Quality

Content

92%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 is an exemplary instruction-only skill: lean, sequenced, and grounded in exact git and gh commands, with validation explicitly gating every destructive action. Its only shortcoming is that the late-commit fix-forward and worktree-cleanup steps give direction rather than executable commands.

DimensionReasoningScore

Conciseness

The body is lean and command-dense with no explanations of concepts Claude already knows; every step carries operational content. The repeated emphasis on destructive-operation gating is safety-critical instruction, not padding, matching the 'every token earns its place' anchor.

5 / 5

Actionability

Most steps give fully executable commands (gh pr view with JSON fields, git rev-list --parents, git merge-base --is-ancestor, git show --remerge-diff, and complete git patch-id --stable pipelines covering both merge shapes). Steps 3-4 rely on direction rather than commands ("fix-forward with a new PR", "Resolve and validate the exact worktree path"), which are minor gaps keeping it below copy-paste-complete.

4 / 5

Workflow Clarity

The five steps are clearly sequenced with explicit validation checkpoints gating the destructive operations: "Prepare cleanup only after the content diff is empty" and "If the content diff is non-empty and you are unsure why, stop and report rather than deleting anything". This provides exactly the validate-before-destructive feedback loop the rubric requires, including the patch-id re-check for the behind-main case.

5 / 5

Progressive Disclosure

The skill is under 50 lines with well-organized Steps and Notes sections, and its single external reference (docs/agents/pull-request-workflow.md#landed) is one level deep and clearly signaled with section anchors. No bundle files exist to inline or bury, so the structure fully satisfies the simple-skill organization anchor.

5 / 5

Total

19

/

20

Passed

Description

88%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 and concretely states both what the skill does and when to use it, with domain-specific trigger language. Its only weaknesses are incomplete synonym coverage for trigger terms and slight genericness in the cleanup portion, which create minor gaps rather than real conflict risk.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions covering the skill's full scope: "Verify a merged PR actually landed correctly", "confirm the merge commit... matches your branch by content", "catch late commits that were orphaned by the auto-merge race", and "post its review record and update memory". This matches the comprehensive-coverage anchor; there are no minor gaps that would place it at 4.

5 / 5

Completeness

The 'what' is explicit (verify a merged PR landed correctly by content and clean up after it) and the 'when' is explicit and specific: "Use right after a PR merges (especially with auto-merge)... or for older PRs". Both are answered with concrete trigger guidance, matching the top anchor rather than the 4 anchor where the 'when' could be more explicit.

5 / 5

Trigger Term Quality

Natural terms like "merged PR", "PR merges", "auto-merge", "squashed commit", and "landed" are phrases a user would plausibly say when needing this skill. Coverage is good but misses common variations such as "pull request" spelled out, "delete the branch", or "did my PR land", so it falls short of the comprehensive synonym coverage of the 5 anchor.

4 / 5

Distinctiveness Conflict Risk

The post-merge verification niche is distinct with specific triggers (merge commit, squashed commit, auto-merge race), but the "clean up after it" portion creates minor overlap risk with closely related branch-cleanup or PR-hygiene skills. This fits the 'mostly distinct; minor overlap risk' anchor rather than the minimal-conflict 5 anchor.

4 / 5

Total

18

/

20

Passed

Validation

93%

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

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 3 suspicious

Warning

Total

15

/

16

Passed

Repository

BigSimmo/PsychSift

Path

.claude/skills/prlanded/SKILL.md

Reviewed

Table of Contents

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.