CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

land-pr

Land lossless-claw pull requests safely; use when asked whether a PR is ready, whether CI passes, to merge or land a PR, or to perform maintainer closeout after review.

Quality

90%

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

SKILL.md
Quality
Evals
Security

Quality

Content

96%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.

Excellent operational content: fully executable gh/git commands, explicit validation checkpoints and recovery loops around a merge (irreversible) operation, and tight, padding-free prose. The only structural note is that at ~96 lines with moderately detailed sub-procedures (issue search, changeset handling) inlined in a single file, it is at the upper bound of what belongs directly in SKILL.md.

DimensionReasoningScore

Conciseness

The body is lean, imperative, and assumes competence: no concept explanations, no padding, just concrete commands, conditions, and decision rules. Every line is instruction; the only repetition (head-SHA pinning restated at merge time and in 'Do Not') reads as deliberate safety emphasis for a destructive operation rather than filler. Not the level below (4) because there is no over-explanation to trim.

5 / 5

Actionability

Every step carries a copy-paste-ready gh/git command with concrete flags (--match-head-commit, --squash, --json fields), and edge branches give exact fallback behavior (manual merge command, comment-vs-close decision rule). This matches 'Fully executable; copy-paste ready code or commands; specific examples cover the common cases'.

5 / 5

Workflow Clarity

The 8-step sequence is explicitly ordered with validation checkpoints throughout: readiness gating on pinned head SHA, check-state verification, HEAD comparison before branch review, re-reading the pin before merge, and post-merge state confirmation. Error-recovery feedback loops are present (pending/failing checks -> do not merge; ambiguous issue -> comment and ask instead of closing; missing changeset -> follow-up PR), matching the top anchor.

5 / 5

Progressive Disclosure

A single-file skill with clean section structure (Workflow / Do Not) and no nested references; the repo files it names (AGENTS.md, scripts/pr-merge) are environment targets, not bundle references. It is well above anchor 3 (structure is clear, nothing is buried), but the body runs ~96 lines — over the under-50-lines simple-skill exception — and detailed inline material like the step-5 issue-search heuristics could live in a one-level-deep reference, so it does not fully meet anchor 5's 'content appropriately split'.

4 / 5

Total

19

/

20

Passed

Description

82%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 well-formed description with an explicit use-when clause, good natural trigger phrases, and strong repo-scoped distinctiveness. Its main weakness is that the 'what' half understates the skill's coverage — the body performs readiness verification, check gating, issue closeout, and changeset follow-through that the description never mentions.

Suggestions

Expand the 'what' clause to enumerate the concrete actions the skill actually performs, e.g. 'Verify PR readiness and CI checks, merge with head-SHA pinning, search and close covered issues, and perform maintainer closeout (changesets, thank-you comments) for lossless-claw pull requests.'

Add a few more natural trigger variations users might say, such as 'is this PR good to merge', 'can we merge this', or 'finish landing this PR'.

Consider mentioning the post-merge maintainer follow-through (issue closeout, changesets) as a capability, not just a trigger, since it is roughly half the body's workflow.

DimensionReasoningScore

Specificity

The 'what' clause is a single concrete action — 'Land lossless-claw pull requests safely' — which names the domain and one action, matching the anchor 'Names domain and 1-2 concrete actions, but not comprehensive'. It does not list the several distinct capabilities the body actually covers (readiness verification, CI checks, issue closeout, changeset follow-up).

3 / 5

Completeness

It explicitly answers both: what ('Land lossless-claw pull requests safely') and when ('use when asked whether a PR is ready, whether CI passes, to merge or land a PR, or to perform maintainer closeout after review') with concrete trigger phrases, matching the top anchor.

5 / 5

Trigger Term Quality

Natural user phrases are well covered — 'whether a PR is ready', 'whether CI passes', 'to merge or land a PR' — including the merge/land synonym pair. A few natural variations ('is this good to merge', 'can we ship this', 'PR review closeout' wording) are missing, so it falls just short of the comprehensive-synonyms anchor.

4 / 5

Distinctiveness Conflict Risk

The 'lossless-claw' scoping gives it a clear niche, and the triggers (land/merge readiness, CI pass, maintainer closeout) are distinct from generic review skills, matching 'Clear niche with distinct triggers; minimal conflict risk'.

5 / 5

Total

17

/

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

referenced_paths_exist

Referenced path issues: 2 missing

Warning

Total

15

/

16

Passed

Repository

Martian-Engineering/lossless-claw

Path

.agents/skills/land-pr/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.