Agent skill · Audited from source
Ship Pr
skill · pedronauck/skillsLicence not declaredAudited 16 Oct 2026 · source 118e61cf1c61
Is it safe? Yes — SAFE, grade B (89/100). We read this skill's source at commit 118e61cf1c61 and found no filesystem, network or shell access and no hard-coded secrets. What it does: Deliver implementation-complete work with impact/docs checks, release notes, commits, and a PR; optionally watch CodeRabbit. Excludes unfinished checkpoints, draft-only PRs, merged-PR amendments, and release publication.
Cite
Cite this page
ModelsAtlas. “Ship Pr (pedronauck/skills)”. Retrieved 16 Oct 2026. https://modelsatlas.com/skills/pedronauck/ship-pr
Trust audit
Audit 0.4.1 · source read 16 Oct 2026
SAFE means nothing in the source contradicts what the skill says it does. Grade B is shared by 16,667 of 17,602 audited skills.
What the source does
- FilesystemNone observedNo reads or writes in the source
- NetworkNone observedNo outbound calls in the source
- ShellNone observedNo commands run in the source
- DependenciesPinnedNothing floats
- SecretsNone foundNo keys in source
Five audit layers
| Layer | What we check | Result | Findings |
|---|---|---|---|
L0 Provenance | Repo owner, licence, archive status, activity | PASS | 0 |
L1 Static source | Secrets, path traversal, supply chain, hidden code | PASS | 0 |
L2 Instructions | Prompt injection, authority framing, hidden directives | PASS | 0 |
L3 Inventory | The files and declarations match the source | PASS | 0 |
L4 Sandbox | Run in isolation and watch behaviour | SKIPPED why | 0 |
Gates applied: no behavioural pass.
Findings (0)
No findings at any severity. We re-audit when the source changes.
Audit 0.4.1 · source sha 118e61cf1c61 · 16 Oct 2026Report an issue or request a re-scan
Provenance
Who published it, and what the verdict is pinned to
- Publisherpedronauck GitHub userOwner of the repository this skill is read from
- Source folderpedronauck/skills/skills/mine/ship-prThe exact folder we audited
- LicenceNot declaredAs the repository states it
- Commit pinned for this verdict118e61cf1c61A new audit runs when the source changes
- Repository statusNot archivedLast push 31 days ago
- Sandboxed runNot runSkills are read, not executed; layer L4 is skipped
What it tells the agent
Full source on GitHub ↗Its description: Deliver implementation-complete work with impact/docs checks, release notes, commits, and a PR; optionally watch CodeRabbit. Excludes unfinished checkpoints, draft-only PRs, merged-PR amendments, and release publication.
--- name: ship-pr description: "Deliver implementation-complete work with impact/docs checks, release notes, commits, and a PR; optionally watch CodeRabbit. Excludes unfinished checkpoints, draft-only PRs, merged-PR amendments, and release publication." disable-model-invocation: true metadata: author: Pedro Nauck github: https://github.com/pedronauck repository: https://github.com/pedronauck/skills --- # Ship a PR Finish the requested delivery scope using the repository's conventions. Reuse the implementation's impact analysis, current checks, and QA evidence. Do not turn preparing a PR into a release or automated review campaign unless requested or required by the project. 1. Inspect branch/base, staged and unstaged changes, relevant instructions, PR template, and current verification. Already-committed work is valid input. Keep unrelated changes out of staging. 2. Trace changed public behavior to its affected documentation, examples, config, and release notes. A focused diff can be inspected locally; bounded independent agents help only for distinct large areas. 3. Update the affected artifacts. Follow repository release-note policy; a binary on PATH does not establish repository adoption. Group related changes instead of creating a note for every bullet. 4. Write a PR description around the resulting behavior, material risks, and actual validation. Use the repository template; omit empty optional sections. Include existing QA artifacts only when they explain the change. 5. Before committing, run required scoped gates or reuse valid evidence as project policy allows. Stage owned paths explicitly and inspect the staged diff. Follow commitlint and hook requirements; no invented model attribution, history rewrite, or hook bypass. 6. When commit/push/PR creation is within the user's request, publish the feature branch and create or update its PR with `gh` using a body file. Respect requested draft status. Follow required CI to the current head; triage failures as they appear. 7. Start an external review watcher only when requested or already part of the authorized delivery workflow. Confirm the installed command and configured provider. Automatic remediation, commits, pushes, and unbounded polling are separate scope choices, not tool-detection defaults. ## References Load the phase that needs detail: `references/explore-impact.md`, `references/release-notes.md`, `references/pr-description.md`, `references/qa-artifacts.md`, `references/commit-conventions.md`, or `references/coderabbit-watch.md`. The read-only detector is `bash <ship-pr-dir>/scripts/detect-tooling.sh`, resolved relative to this skill. Its PATH results describe availability, not authorization or project configuration. Missing optional integrations do not block the normal PR flow. Sync Skeeper only for configured repositories with affected spec artifacts.
Excerpt, first 2,878 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.
Install
Pinned to the audited commit 118e61c
git clone https://github.com/pedronauck/skills git -C skills checkout 118e61cf1c61
The author documents no install command, so this uses the repository directly. Our verdict covers commit 118e61cf1c61 only.
Works in
The author has not said which agents this skill supports, and we have not tested it in any.
Audit history
Every audit, every source change
- ✓SAFE B 89 / 100
first audit · source
118e61cf1c61
Similar skills
obra/superpowers
Use when creating new skills, editing existing skills, or verifying skills work before deployment
mattpocock/skills
A relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go.
mattpocock/skills
Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.
Questions about Ship Pr
What does the Ship Pr skill do?
Is Ship Pr safe to install?
What can Ship Pr access on my machine?
How current is this page?
Sources
- github.com/pedronauck/skills/tree/main/skills/mine/ship-pr — the audited source at commit 118e61cf1c61 and every finding aboveObserved · 16 Oct 2026
Spotted something wrong? Report a correction · Methodology
Keep going in your AI
Opens with this page as the source. We add nothing else to the prompt.
- What does the Ship Pr skill do?
- Is Ship Pr safe to install?
- What can Ship Pr access on my machine?