CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

landpr

This skill should be used when preparing a /landpr prompt/checklist to land a PR.

59

Quality

74%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/00-utilities/landpr/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

86%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 lean, highly actionable runbook: concrete commands, clear sequencing, and real validation checkpoints around destructive operations (force-push, branch deletion). The main gaps are the undefined `committer` tool and the absence of failure-path guidance if the gate, rebase, or final merge verification fails.

DimensionReasoningScore

Conciseness

The body is telegraphic — 16 numbered steps of pure commands and variable assignments with zero padding, no git-concept explanations, and no filler. Every line instructs an action, fully matching 'lean and efficient; assumes Claude's competence'.

5 / 5

Actionability

Nearly every step is a copy-paste-ready `gh`/`git` command with exact --jq filters and variable captures. It falls short of level 5 only because `committer` is an undefined external tool (no signature, no fallback shown) and placeholders like `<summary>` and `$contrib` require unstated context.

4 / 5

Workflow Clarity

The 16 steps are explicitly ordered with a stated goal (PR must end MERGED), a pre-commit gate (step 9), guarded force-push (--force-with-lease), and a final state verification (step 15) — so validation is present despite destructive operations. It misses level 5 because there is no error-recovery loop: what to do when the gate fails, conflicts are unresolvable, or the merge state check fails is left implicit.

4 / 5

Progressive Disclosure

This is a ~50-line single-purpose skill with no bundle files (references/, scripts/, assets/ are absent) and no content that warrants offloading. Per the simple-skill exception, the clean single numbered list with a goal header is appropriately organized for a skill of this size.

5 / 5

Total

18

/

20

Passed

Description

48%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 has a clear trigger ('when preparing a /landpr prompt/checklist') and a distinct command name, but says almost nothing about what the skill actually does — the multi-step rebase, gate, merge, and cleanup workflow is invisible from the frontmatter alone. It reads more like a routing hint than a capability description, capping its usefulness for skill selection.

Suggestions

State the concrete actions in the description, e.g. 'Rebases a PR onto a fresh base, runs the lint/build/test gate, updates the changelog, and merges via rebase or squash until the PR shows MERGED.'

Add natural trigger synonyms such as 'land', 'merge', or 'ship a pull request' so users phrasing the request differently still match the skill.

Replace the circular 'when preparing a /landpr prompt/checklist' trigger with what the user wants, e.g. 'Use when the user asks to land, merge, or ship a PR'.

DimensionReasoningScore

Specificity

The description names the domain ("land a PR") but lists no concrete actions — the rebase, test gate, merge-strategy, changelog, and cleanup steps the skill actually performs are entirely absent. It matches 'Names the domain but actions are minimal or generic' rather than level 3, which requires 1-2 explicitly stated concrete actions.

2 / 5

Completeness

An explicit 'when' is present ("when preparing a /landpr prompt/checklist"), but the 'what' is only the vague goal "land a PR" with none of the actual operations described. It sits between anchor 2 (vague what) and anchor 4 (both what and when clearly stated), closer to the midpoint since the when-clause is explicit but circular and the what is minimal.

3 / 5

Trigger Term Quality

"land a PR" and "/landpr" are natural terms a user might say, but common variations and synonyms are missing: "merge", "pull request", "squash", "rebase" never appear. This is 'some relevant keywords but missing common variations' — not level 4, which requires good coverage with only a few terms missing.

3 / 5

Distinctiveness Conflict Risk

"/landpr" is a niche, distinct command name unlikely to fire for unrelated skills, and landing a PR is a specific intent. It is not level 5 because 'land a PR' could mildly overlap with generic PR-review or merge-request skills without more distinguishing triggers.

4 / 5

Total

12

/

20

Passed

Validation

100%

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

marchatton/agent-skills

Path

.agents/skills/00-utilities/landpr/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.