Dependency Review
Structured review workflow for dependency update PRs. Produces consistent research notes that incorporate existing PR discussion, multi-lens analysis, and an actionable verdict with explicit maintainer confirmation before any merge action.
When to use
Use when a dependency PR needs review and you want a consistent, auditable decision process.
Typical triggers:
- "Review this dependency PR"
- "Should we merge this dependency update?"
- "Check this Renovate/Dependabot PR"
- "Review one of our open dependency PRs"
- "What changed in this library bump?"
- "Is this dependency update safe to merge?"
- PR title contains dependency update patterns (e.g.
chore(deps):, fix(deps):, bump, update)
- User shares a PR URL for a dependency update
When not to use
- Feature PRs or application code reviews (use standard code review workflows)
- Dependency automation or bot configuration
- Approving/merging without explicit user confirmation
- Deciding organizational dependency policy
Required inputs
Collect before starting:
- Repository owner and name
- PR number or URL, or a copied PR summary including package name, version change, changed files, and CI status
- Optional: specific review concerns or areas of focus
If required details are missing, ask concise clarifying questions from references/questions.md.
If PR target is missing or ambiguous:
- Ask only the minimal follow-up question needed to identify the target PR.
- When repository context is known, use GitHub MCP to list likely open dependency PRs and let user choose.
- Keep shortlist concise: include PR number, title, dependency/package hint, author, and CI state when available.
Auto-extract from the PR when available:
- Package(s) being updated and version range (from → to)
- Changelog/release notes URL
- CI status
- Changed files and dependency ecosystem
- Existing top-level PR comments, review comments, and unresolved thread state
Instructions
Preferred advisor orchestration
When the runtime supports skill-local advisors, prefer this execution shape instead of a single long linear pass:
- Run
agents/target-pr-advisor.md first when the PR target is missing or ambiguous so the review starts from one explicit dependency PR.
- Run
agents/research-advisor.md to normalize the PR context, existing discussion, source list, and research notes.
- Fan out the lens advisors in parallel with the same normalized inputs:
agents/security-advisor.md
agents/code-quality-advisor.md
agents/impact-advisor.md
- Chain the combined research and lens outputs into
agents/verdict-advisor.md for recommendation, confidence, readiness, handoff, and confirmation wording.
- Chain into
agents/source-control-advisor.md only if the accepted next step requires PR patching, rebase, conflict resolution, or merge-readiness work.
Keep the lens advisors narrow and independent. The parent skill owns the unified review and should preserve disagreement between advisors instead of flattening it early.
Workflow summary
- Resolve target PR with
agents/target-pr-advisor.md and concise prompts in references/questions.md.
- Gather context and build shared evidence packet with
agents/research-advisor.md, assets/review-tracker.md, and assets/research-template.md.
- Run
agents/security-advisor.md, agents/code-quality-advisor.md, and agents/impact-advisor.md in parallel with the same normalized research packet.
- Use
agents/verdict-advisor.md to produce recommendation, confidence, readiness, follow-up, and explicit maintainer prompt.
- Use
agents/source-control-advisor.md only after verdict is accepted and only when branch work is required.
- Follow
references/instructions.md for detailed live-PR contract: target selection, checkpoint comments, decision gates, and handoff timing.
Assets
assets/research-template.md: research-comment structure for change summary, breaking changes, known issues, and sources
assets/verdict-template.md: verdict structure for lens assessments, recommendation, confidence, readiness, and follow-up items
assets/review-tracker.md: working checklist and tracker for context, validation, lens outcomes, and handoff decisions
References
references/instructions.md: detailed execution contract for target selection, live-PR checkpoints, and decision sequencing
references/questions.md: concise follow-up questions for choosing the target dependency PR and scoping the review
Advisors
agents/target-pr-advisor.md: resolves the exact dependency PR to review or returns a shortlist for user selection
agents/research-advisor.md: first pass; builds the shared evidence packet for all later advisors
agents/security-advisor.md: parallel lens pass; checks security posture and attack-surface changes
agents/code-quality-advisor.md: parallel lens pass; checks upstream stability, regressions, and API drift
agents/impact-advisor.md: parallel lens pass; checks repository blast radius, CI, and follow-up work
agents/verdict-advisor.md: chained synthesis pass; turns research and lens outputs into one decision
agents/source-control-advisor.md: conditional final pass; handles rebase, sync, validation reruns, and push safety when patching the PR
If helper advisors are unavailable, follow the same orchestration inline: research first, lenses next, verdict after that, and source-control last only when mutation is needed.
Expected output
If the PR target is unresolved, return:
- A concise shortlist of candidate dependency PRs when live PR search is available
- The minimal follow-up question required to let the user choose the correct PR
- Explicit status:
Awaiting user PR selection
If the PR target is resolved, return a structured review containing:
- Package name, version change, and update type
- Existing PR discussion summary (top-level comments, review-thread themes, unresolved concerns)
- Research summary (changelog highlights, breaking changes, known issues)
- Security assessment with evidence
- Code quality assessment with evidence
- Impact assessment with evidence
- Verdict: recommendation, rationale, confidence, readiness, and follow-up items
- Handoff recommendation when follow-up work should become a tracked issue
- Explicit action prompt for the maintainer
Safety & constraints
- This skill is mutation-capable. Repository-local workflow instructions take precedence over inline guidance when they conflict.
Never:
- Merge or approve a dependency PR without explicit user confirmation
- Create a merge commit by merging the base branch into a Dependabot or Renovate PR branch
- Guess which PR to review when multiple plausible dependency PRs exist
- Skip the research checkpoint comment or final verdict comment on a live PR
- Ignore existing reviewer concerns because they are inconvenient or duplicative
- Claim CI passed or security is clear without checking actual status
- Expose secrets or tokens in comments or logs
- Dismiss security concerns for convenience
- Fabricate changelog entries or version details not found in sources
Always:
- Ask minimal follow-up questions when the target PR is missing or ambiguous
- Present evidence for each assessment (link to changelog, CVE, CI status)
- Assess technical recommendation, evidence confidence, and mechanical merge readiness independently
- Treat pending checks or required approval as readiness gates, not technical reasons to hold
- Require explicit compatibility evidence for major updates without treating semver category alone as low confidence
- List candidate dependency PRs for user selection when repository context exists but the PR target does not
- Fetch existing PR comments and review threads via GitHub MCP before analysis on a live PR
- Reuse one shared research packet across advisors instead of rediscovering the same facts in each pass — this includes PR metadata, changed files, CI status, and existing discussion
- Do not re-fetch PR comments or review threads independently in each advisor; pass the pre-fetched data from the research advisor to all lens advisors
- Prefer parallel lens analysis when the runtime supports it, then chain synthesis after all lens outputs are ready
- Post the research checkpoint comment to the PR before any branch mutation on a live PR
- Post the final verdict comment to the PR before any approval or merge on a live PR
- Make branch-sync or rebase needs explicit before patching the PR
- Rebase dependency PR branches onto the latest base branch when refresh is required; do not merge the base branch into the PR branch
- Make follow-up work explicit rather than burying it in review notes
- Respect the maintainer as the final decision-maker
- Keep review output in a consistent, repeatable structure
1---2name: fusion-dependency-review3description: 'Review dependency PRs with structured research, existing-PR-discussion capture, multi-lens analysis (security, code quality, impact), and a repeatable verdict template. USE FOR: dependency update PRs, Renovate/Dependabot PRs, library upgrade reviews, "review this dependency PR", "should we merge this update". DO NOT USE FOR: feature PRs, application code reviews, dependency automation/bot configuration, or unattended merge without confirmation.'4license: MIT5compatibility: Requires GitHub MCP server for PR context. Uses fusion-issue-authoring for follow-up handoff when post-merge work is identified.6metadata:7 source: https://skillmd.com/skills/equinor/fusion-dependency-review8 version: "0.1.5"9 status: experimental10 owner: "@equinor/fusion-core"11 tags:12 - github13 - pull-request14 - dependency-review15 - dependency-updates16 - security17 mcp:18 required:19 - github20---2122# Dependency Review2324Structured review workflow for dependency update PRs. Produces consistent research notes that incorporate existing PR discussion, multi-lens analysis, and an actionable verdict with explicit maintainer confirmation before any merge action.2526## When to use2728Use when a dependency PR needs review and you want a consistent, auditable decision process.2930Typical triggers:3132- "Review this dependency PR"33- "Should we merge this dependency update?"34- "Check this Renovate/Dependabot PR"35- "Review one of our open dependency PRs"36- "What changed in this library bump?"37- "Is this dependency update safe to merge?"38- PR title contains dependency update patterns (e.g. `chore(deps):`, `fix(deps):`, `bump`, `update`)39- User shares a PR URL for a dependency update4041## When not to use4243- Feature PRs or application code reviews (use standard code review workflows)44- Dependency automation or bot configuration45- Approving/merging without explicit user confirmation46- Deciding organizational dependency policy4748## Required inputs4950Collect before starting:5152- **Repository** owner and name53- **PR number or URL**, or a copied PR summary including package name, version change, changed files, and CI status54- Optional: specific review concerns or areas of focus5556If required details are missing, ask concise clarifying questions from `references/questions.md`.5758If PR target is missing or ambiguous:5960- Ask only the minimal follow-up question needed to identify the target PR.61- When repository context is known, use GitHub MCP to list likely open dependency PRs and let user choose.62- Keep shortlist concise: include PR number, title, dependency/package hint, author, and CI state when available.6364Auto-extract from the PR when available:6566- Package(s) being updated and version range (from → to)67- Changelog/release notes URL68- CI status69- Changed files and dependency ecosystem70- Existing top-level PR comments, review comments, and unresolved thread state7172## Instructions7374### Preferred advisor orchestration7576When the runtime supports skill-local advisors, prefer this execution shape instead of a single long linear pass:77781. Run `agents/target-pr-advisor.md` first when the PR target is missing or ambiguous so the review starts from one explicit dependency PR.792. Run `agents/research-advisor.md` to normalize the PR context, existing discussion, source list, and research notes.803. Fan out the lens advisors in parallel with the same normalized inputs:81 - `agents/security-advisor.md`82 - `agents/code-quality-advisor.md`83 - `agents/impact-advisor.md`844. Chain the combined research and lens outputs into `agents/verdict-advisor.md` for recommendation, confidence, readiness, handoff, and confirmation wording.855. Chain into `agents/source-control-advisor.md` only if the accepted next step requires PR patching, rebase, conflict resolution, or merge-readiness work.8687Keep the lens advisors narrow and independent. The parent skill owns the unified review and should preserve disagreement between advisors instead of flattening it early.8889### Workflow summary90911. Resolve target PR with `agents/target-pr-advisor.md` and concise prompts in `references/questions.md`.922. Gather context and build shared evidence packet with `agents/research-advisor.md`, `assets/review-tracker.md`, and `assets/research-template.md`.933. Run `agents/security-advisor.md`, `agents/code-quality-advisor.md`, and `agents/impact-advisor.md` in parallel with the same normalized research packet.944. Use `agents/verdict-advisor.md` to produce recommendation, confidence, readiness, follow-up, and explicit maintainer prompt.955. Use `agents/source-control-advisor.md` only after verdict is accepted and only when branch work is required.966. Follow `references/instructions.md` for detailed live-PR contract: target selection, checkpoint comments, decision gates, and handoff timing.9798## Assets99100- `assets/research-template.md`: research-comment structure for change summary, breaking changes, known issues, and sources101- `assets/verdict-template.md`: verdict structure for lens assessments, recommendation, confidence, readiness, and follow-up items102- `assets/review-tracker.md`: working checklist and tracker for context, validation, lens outcomes, and handoff decisions103104## References105106- `references/instructions.md`: detailed execution contract for target selection, live-PR checkpoints, and decision sequencing107- `references/questions.md`: concise follow-up questions for choosing the target dependency PR and scoping the review108109## Advisors110111- `agents/target-pr-advisor.md`: resolves the exact dependency PR to review or returns a shortlist for user selection112- `agents/research-advisor.md`: first pass; builds the shared evidence packet for all later advisors113- `agents/security-advisor.md`: parallel lens pass; checks security posture and attack-surface changes114- `agents/code-quality-advisor.md`: parallel lens pass; checks upstream stability, regressions, and API drift115- `agents/impact-advisor.md`: parallel lens pass; checks repository blast radius, CI, and follow-up work116- `agents/verdict-advisor.md`: chained synthesis pass; turns research and lens outputs into one decision117- `agents/source-control-advisor.md`: conditional final pass; handles rebase, sync, validation reruns, and push safety when patching the PR118119If helper advisors are unavailable, follow the same orchestration inline: research first, lenses next, verdict after that, and source-control last only when mutation is needed.120121## Expected output122123If the PR target is unresolved, return:124125- A concise shortlist of candidate dependency PRs when live PR search is available126- The minimal follow-up question required to let the user choose the correct PR127- Explicit status: `Awaiting user PR selection`128129If the PR target is resolved, return a structured review containing:130131- Package name, version change, and update type132- Existing PR discussion summary (top-level comments, review-thread themes, unresolved concerns)133- Research summary (changelog highlights, breaking changes, known issues)134- Security assessment with evidence135- Code quality assessment with evidence136- Impact assessment with evidence137- Verdict: recommendation, rationale, confidence, readiness, and follow-up items138- Handoff recommendation when follow-up work should become a tracked issue139- Explicit action prompt for the maintainer140141## Safety & constraints142143- This skill is mutation-capable. Repository-local workflow instructions take precedence over inline guidance when they conflict.144145Never:146147- Merge or approve a dependency PR without explicit user confirmation148- Create a merge commit by merging the base branch into a Dependabot or Renovate PR branch149- Guess which PR to review when multiple plausible dependency PRs exist150- Skip the research checkpoint comment or final verdict comment on a live PR151- Ignore existing reviewer concerns because they are inconvenient or duplicative152- Claim CI passed or security is clear without checking actual status153- Expose secrets or tokens in comments or logs154- Dismiss security concerns for convenience155- Fabricate changelog entries or version details not found in sources156157Always:158159- Ask minimal follow-up questions when the target PR is missing or ambiguous160- Present evidence for each assessment (link to changelog, CVE, CI status)161- Assess technical recommendation, evidence confidence, and mechanical merge readiness independently162- Treat pending checks or required approval as readiness gates, not technical reasons to hold163- Require explicit compatibility evidence for major updates without treating semver category alone as low confidence164- List candidate dependency PRs for user selection when repository context exists but the PR target does not165- Fetch existing PR comments and review threads via GitHub MCP before analysis on a live PR166- Reuse one shared research packet across advisors instead of rediscovering the same facts in each pass — this includes PR metadata, changed files, CI status, and existing discussion167- Do not re-fetch PR comments or review threads independently in each advisor; pass the pre-fetched data from the research advisor to all lens advisors168- Prefer parallel lens analysis when the runtime supports it, then chain synthesis after all lens outputs are ready169- Post the research checkpoint comment to the PR before any branch mutation on a live PR170- Post the final verdict comment to the PR before any approval or merge on a live PR171- Make branch-sync or rebase needs explicit before patching the PR172- Rebase dependency PR branches onto the latest base branch when refresh is required; do not merge the base branch into the PR branch173- Make follow-up work explicit rather than burying it in review notes174- Respect the maintainer as the final decision-maker175- Keep review output in a consistent, repeatable structure