CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

pr

Open a pull request for the current feature

Quality

79%

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/pr/SKILL.md
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.

The body is an exemplary procedural skill: dense with repo-specific, non-obvious directives, fully executable commands, explicit validation checkpoints, and fallback behavior for failure paths. The only structural improvement would be sectioning the main workflow the way the final section is sectioned.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence — e.g. "Never force push, unless users asks for it", "Pass their actual paths; do not assume that the repository root has a `src` directory" — with no explanations of concepts Claude already knows; every directive is project-specific and earns its place.

5 / 5

Actionability

Fully executable, copy-paste-ready commands cover the common cases: `bunx oxfmt <changed-file-or-package-directory>... --write`, `bun run build`, `git push -u origin HEAD`, `gh pr create --title "..." --body-file <path>`, and the maintainer-edits remediation via `gh api --method PATCH repos/<owner>/<repo>/pulls/<number> -F maintainer_can_modify=true`.

5 / 5

Workflow Clarity

A clear sequence (branch check → existing-PR check → format → build/stylecheck → commit → push → create PR → post-creation) with explicit validation ("Inspect any formatter changes before committing", build/stylecheck gates, `maintainerCanModify` check-and-fix) and error-recovery feedback loops (poll for the Vercel comment with sleep intervals; "If either the page path or the preview URL cannot be determined confidently, leave the created PR unchanged and report").

5 / 5

Progressive Disclosure

External references are well-signaled, conditional, and one level deep ("If the changes add a Remotion Element, read the [Element contribution guide]... before continuing"; the `pr-name` skill link), and nothing that belongs in a separate file is inlined. It falls short of a 5 because the ~60-line body has only one section header, leaving the main workflow as a flat, unsectioned sequence.

4 / 5

Total

19

/

20

Passed

Description

53%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 states a single clear, concrete action but is too terse to serve as a reliable trigger: it lacks any 'when to use' guidance, natural trigger variations such as "PR", and any mention of the other capabilities the skill actually covers (updating existing PRs, formatting, build checks, preview linking). It is functional but undersells and under-triggers the skill.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks to open, create, or update a pull request (PR) for the current branch or feature work."

Include the natural abbreviation and variations users actually say — "PR", "create a PR", "open a PR" — alongside "pull request".

Briefly enumerate the other concrete actions the skill performs (update an existing PR, run formatting/build checks before opening, link website preview pages) so the description's coverage matches the skill's scope.

DimensionReasoningScore

Specificity

"Open a pull request for the current feature" names the domain and one concrete action, matching the '1-2 concrete actions, but not comprehensive' anchor. It is not a 4 because only a single action is listed, and not a 2 because 'open a pull request' is concrete rather than generic.

3 / 5

Completeness

The "what" is clear (open a pull request for the current feature), but there is no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines.

3 / 5

Trigger Term Quality

"pull request" is a natural keyword users would say, but the very common abbreviation "PR" and variations like "create a PR" are absent, matching 'some relevant keywords but missing common variations or synonyms'.

3 / 5

Distinctiveness Conflict Risk

The description is clearly scoped to pull requests and is distinguishable from commit-message or general git skills, with only minor overlap risk against closely related git-workflow skills — matching 'mostly distinct; minor overlap risk'.

4 / 5

Total

13

/

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: 2 suspicious

Warning

Total

15

/

16

Passed

Repository

remotion-dev/remotion

Path

.agents/skills/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.