AF create-pr
End-to-end pull-request flow with a review gate — reviews the branch BEFORE publishing (code-review skill's branch scope if installed; blockers must be fixed or explicitly waived), pushes with user approval, creates one PR per repo for multi-repo work items with house defaults from config (title pattern, target branch, required reviewers, auto-complete, work-item link), cross-references sibling PRs with deploy-order coupling, verifies every setting after creation, and reports the URLs. Detects the provider from the git remote (Azure DevOps via the azure-devops skill, GitHub via gh). Use this skill whenever the user says "create a PR", "open a pull request", "publish the branch and create a PR", "PR this", "ship this branch", "create the PRs for this task", or "raise a PR" — even if they don't explicitly say "create-pr skill". For reviewing someone else's PR (not creating one), use a review skill instead.
End-to-end pull-request flow with a review gate — reviews the branch BEFORE publishing (code-review skill's branch scope if installed; blockers must be fixed…
As a process F 51/100 · Will not run — References files that are not bundled: ../github/SKILL.md
How to improve
- The text references files that are not there: add them or drop the references.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: ../github/SKILL.md
Process rating: all ten parameters 51/100
- 0Tools and files. 1 referenced file(s) missing: ../github/SKILL.md
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 42 mutating operations with no state check
- 70When it triggers. States when to use, but not when not to
- 100Steps. 32 steps
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1918 tokens
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- high The skill tells the model to perform an irreversible action with no human approval
- low The response is described with custom markup (5 tags): a typed call is more reliable
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 917: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 8 example trigger phrases
- +4Structure: 14 headings
- +3Step-by-step instructions: 32 items
- +4Has examples (0 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 80.