CtrlK
BlogDocsLog inGet started
Tessl Logo

create-pr

Create a GitHub pull request with the project's PR template fully populated. Analyzes the branch diff, fills in "What changed", "Issue", "How to test", "A11y impact", "Definition of Done", and other sections. Use this skill whenever the user wants to create a PR, open a pull request, submit their branch for review, or says things like "make a PR", "open a PR", "submit this for review", or "I'm ready to create a pull request" — even if they don't use the exact phrase "pull request".

86

1.35x
Quality

85%

Does it follow best practices?

Impact

84%

1.35x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

75%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 well-structured, actionable single-file skill: the workflow is clearly sequenced with concrete git/gh commands, a HEREDOC pattern for the PR body, and a user-confirmation checkpoint before the irreversible create step. It falls short of top marks only on small margins — trimmable explanatory asides, a missing command for the push check, and no error-recovery guidance for push/create failures.

Suggestions

Add a concrete command for the push check (e.g., `git rev-parse --abbrev-ref --symbolic-full-name @{u}` or `git ls-remote --heads origin HEAD`) so the 'check if pushed' step is executable rather than a directive.

Add a brief error-recovery step for `gh pr create` and `git push` failures (e.g., retry with `--head`, or surface the gh error and ask the user), which would add the feedback loop needed for a top workflow-clarity score.

Trim advisory asides like 'Read the full diff carefully. You need to understand every change...' and 'the kind of thing a reviewer reads to orient themselves' — the guidance is clear without them.

DimensionReasoningScore

Conciseness

The body is efficient — concrete commands, per-section guidance with no concept explanations Claude already knows — but has trimmable padding such as "Read the full diff carefully. You need to understand every change to write an accurate PR description" and "the kind of thing a reviewer reads to orient themselves before looking at code". This matches anchor 4 (efficient, minor instances of over-explanation) rather than 5, where every token earns its place.

4 / 5

Actionability

Gives concrete, runnable commands (git log/diff, gh pr list, gh pr create with HEREDOC) and specific per-section rules, but "Check if the branch has been pushed to the remote" has no accompanying command, and the HEREDOC body is a skeleton with "..." placeholders. Mostly executable with minor gaps — anchor 4, not 5's copy-paste-ready coverage.

4 / 5

Workflow Clarity

The sequence (gather context → fill template → push check → confirm with user → create → show URL) is clear and includes an explicit user-confirmation checkpoint before the irreversible gh pr create, plus a fallback (ask the user) when no ticket number is found. However there are no error-recovery loops (e.g., if the push or gh pr create fails), which keeps it at anchor 4 rather than 5's feedback loops.

4 / 5

Progressive Disclosure

No bundle files exist, and the single SKILL.md is well-organized under clear section headers (Gathering Context, Filling In the Template per section, Creating the PR) with no nested references. At ~110 lines the per-section template guidance is arguably bulk that could live in a reference file, but as a single-task skill with all content one level deep it fits anchor 4 (good structure, appropriately placed, minor organization gaps).

4 / 5

Total

16

/

20

Passed

Description

96%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.

An excellent description: concrete capabilities enumerated by template section, explicit and thorough trigger guidance with natural user phrasings, and third-person voice throughout. The only weakness is mild trigger overlap with review-oriented skills from the "submit this for review" phrasing.

DimensionReasoningScore

Specificity

"Create a GitHub pull request with the project's PR template fully populated. Analyzes the branch diff, fills in 'What changed', 'Issue', 'How to test', 'A11y impact', 'Definition of Done', and other sections" names multiple concrete actions with the exact sections produced — comprehensive coverage for this task's scope. Anchor 4 ('minor gaps in coverage') doesn't fit since nothing within the skill's stated scope is omitted.

5 / 5

Completeness

Explicitly answers what (create a PR with the template's sections fully populated from the branch diff) and when ("Use this skill whenever the user wants to create a PR... even if they don't use the exact phrase 'pull request'"), with concrete trigger phrases. This is the anchor-5 example pattern verbatim in structure.

5 / 5

Trigger Term Quality

Includes natural user phrasings and their variations: "wants to create a PR", "open a pull request", "make a PR", "submit this for review", "I'm ready to create a pull request", plus the abbreviation PR and full term pull request. This matches the anchor-5 pattern of comprehensive natural-term coverage including synonyms.

5 / 5

Distinctiveness Conflict Risk

The PR-creation niche is clear and triggers are distinct ("make a PR", "open a PR"), but "submit their branch for review" and "submit this for review" overlap with review/code-review skill triggers — a minor overlap risk with closely related skills, matching anchor 4. Not a 5 because that conflict risk is more than minimal in a skill library that also contains review skills.

4 / 5

Total

19

/

20

Passed

Validation

87%

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

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

14

/

16

Passed

Repository
HHS/OPRE-OPS
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.