CtrlK
BlogDocsLog inGet started
Tessl Logo

cherry-pick-create-pr

Cherry-pick a single merged commit onto one release-X.Y branch, correctly resolving conflicts, running lint in a separate commit, pushing, and opening a cherry-pick PR via the create_pr_tool MCP following the PR template. Self-contained (carries its own conflict-resolution logic). Use inside a per-branch subagent when backporting a merged PR to a release branch. Has side effects (push + open PR).

73

Quality

90%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

88%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 highly actionable, well-sequenced skill body with strong validation checkpoints and feedback loops appropriate to a destructive, side-effecting operation. The main weakness is repetition of the attribution trailer and safety constraints across multiple sections.

Suggestions

Consolidate the Co-authored-by trailer requirement: state it once authoritatively and reference it from steps 3 and 4 instead of restating the full wording each time.

Consider moving the per-repository lint matrix (mattermost/mattermost vs other repos) into a short reference table or references file so the main flow stays lean.

The Constraints section largely repeats inline guidance from steps 2–5; trim it to only the cross-cutting rules not already stated at their point of action.

DimensionReasoningScore

Conciseness

Mostly efficient with command-and-template-driven guidance, but the Co-authored-by trailer requirement and several safety constraints are restated nearly verbatim in three places (attribution section, steps 3–4, and the Constraints section) and could be consolidated.

4 / 5

Actionability

Provides exact bash commands for every step, field-by-field create_pr_tool parameters, and a copy-paste PR body template — fully executable guidance covering the common cases.

5 / 5

Workflow Clarity

A clearly numbered 0–5 sequence with explicit validation checkpoints — the four preflight checks judged by OUTPUT not exit status, the empty-cherry-pick abort path, and the lint/fix/commit retry loop until clean — plus escalation paths for risky conflicts.

5 / 5

Progressive Disclosure

A single self-contained file with well-organized, clearly headed sections and no nested references; the per-area lint matrix and PR template are inline rather than split out, but the structure is navigable and the self-containment appears intentional.

4 / 5

Total

18

/

20

Passed

Description

92%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, specific description that clearly states a comprehensive set of concrete actions and gives an explicit use-when trigger tied to backporting. It is third-person, distinct, and free of fluff, with only minor room to broaden trigger synonyms.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Cherry-pick a single merged commit', 'correctly resolving conflicts', 'running lint in a separate commit', 'pushing, and opening a cherry-pick PR via the create_pr_tool MCP following the PR template' — giving comprehensive coverage of what the skill does.

5 / 5

Completeness

Explicitly answers both what (cherry-pick, resolve conflicts, lint, push, open PR) and when ('Use inside a per-branch subagent when backporting a merged PR to a release branch') with concrete trigger phrasing.

5 / 5

Trigger Term Quality

Includes natural terms a user would say — 'cherry-pick', 'backporting a merged PR to a release branch', 'release-X.Y branch' — but misses a few common synonyms or variations such as 'backport' as a noun or 'patch'.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear niche — backporting a merged PR to a release branch via a specific MCP tool — with distinct triggers and minimal overlap risk with other skills.

5 / 5

Total

19

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
mattermost/mattermost-ai-marketplace
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.