fusion-dependency-review
Skill2 starsChanged 2 months agoMITView on GitHub
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.
In this repository31 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .github/copilot-instructions.mdCopilot instructions
- caveman-compressSkill
- fusion-core-servicesSkill
- fusion-designSkill
- fusion-framework-mockingSkill
- fusion-framework-testingSkill
- fusion-github-review-resolutionSkill
- fusion-issue-solvingSkill
- fusion-issue-task-planningSkill
- fusion-mcpSkill
- fusion-package-scribeSkill
- fusion-pm-mcpSkill
- fusion-backend-devSkill
- fusion-developer-appSkill
- fusion-developer-portalSkill
- fusion-devtoolsSkill
- fusion-help-apiSkill
- fusion-help-docsSkill
- fusion-help-integrationSkill
- fusion-infra-cliSkill
- fusion-issue-authoringSkill
- fusion-roles-cliSkill
- fusion-rulesSkill
- fusion-skill-authoringSkill
- fusionSkill
- fusion-skillsSkill
- equinor-design-systemSkill
- fusion-code-conventionsSkill
- fusion-researchSkill
- fusion-rule-authorSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
23 rules. About 0 are common, 16 are distinctive, and 7 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈16
Distinctive · estimate
This author's own choices. Worth a look.
7
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 27
Use when a dependency PR needs review and you want a consistent, auditable decision process.
- Very specific: line 55
If required details are missing, ask concise clarifying questions from references/questions.md.
- Distinctive: line 57
If PR target is missing or ambiguous:
- Distinctive: line 59
Ask only the minimal follow-up question needed to identify the target PR.
- Distinctive: line 60
When repository context is known, use GitHub MCP to list likely open dependency PRs and let user choose.
- Distinctive: line 61
Keep shortlist concise: include PR number, title, dependency/package hint, author, and CI state when available.
- Distinctive: line 75
When the runtime supports skill-local advisors, prefer this execution shape instead of a single long linear pass:
- Very specific: line 77
Run agents/target-pr-advisor.md first when the PR target is missing or ambiguous so the review starts from one explicit dependency PR.
- Very specific: line 78
Run agents/research-advisor.md to normalize the PR context, existing discussion, source list, and research notes.
- Distinctive: line 86
Keep the lens advisors narrow and independent.
- Very specific: line 92
Run agents/security-advisor.md, agents/code-quality-advisor.md, and agents/impact-advisor.md in parallel with the same normalized research …
- Very specific: line 93
Use agents/verdict-advisor.md to produce recommendation, confidence, readiness, follow-up, and explicit maintainer prompt.
- Very specific: line 94
Use agents/source-control-advisor.md only after verdict is accepted and only when branch work is required.
- Very specific: line 95
Follow references/instructions.md for detailed live-PR contract: target selection, checkpoint comments, decision gates, and handoff timing.
- Distinctive: line 118
If helper advisors are unavailable, follow the same orchestration inline: research first, lenses next, verdict after that, and …
- Distinctive: line 122
If the PR target is unresolved, return:
- Distinctive: line 128
If the PR target is resolved, return a structured review containing:
- Distinctive: line 147
Create a merge commit by merging the base branch into a Dependabot or Renovate PR branch
- Distinctive: line 158
Ask minimal follow-up questions when the target PR is missing or ambiguous
- Distinctive: line 161
Treat pending checks or required approval as readiness gates, not technical reasons to hold
- Distinctive: line 166
Do not re-fetch PR comments or review threads independently in each advisor.
- Distinctive: line 167
Prefer parallel lens analysis when the runtime supports it, then chain synthesis after all lens outputs are ready
- Distinctive: line 174
Keep review output in a consistent, repeatable structure
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
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.mdfirst when the PR target is missing or ambiguous so the review starts from one explicit dependency PR. - Run
agents/research-advisor.mdto 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.mdagents/code-quality-advisor.mdagents/impact-advisor.md
- Chain the combined research and lens outputs into
agents/verdict-advisor.mdfor recommendation, confidence, readiness, handoff, and confirmation wording. - Chain into
agents/source-control-advisor.mdonly 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.mdand concise prompts inreferences/questions.md. - Gather context and build shared evidence packet with
agents/research-advisor.md,assets/review-tracker.md, andassets/research-template.md. - Run
agents/security-advisor.md,agents/code-quality-advisor.md, andagents/impact-advisor.mdin parallel with the same normalized research packet. - Use
agents/verdict-advisor.mdto produce recommendation, confidence, readiness, follow-up, and explicit maintainer prompt. - Use
agents/source-control-advisor.mdonly after verdict is accepted and only when branch work is required. - Follow
references/instructions.mdfor 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 sourcesassets/verdict-template.md: verdict structure for lens assessments, recommendation, confidence, readiness, and follow-up itemsassets/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 sequencingreferences/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 selectionagents/research-advisor.md: first pass; builds the shared evidence packet for all later advisorsagents/security-advisor.md: parallel lens pass; checks security posture and attack-surface changesagents/code-quality-advisor.md: parallel lens pass; checks upstream stability, regressions, and API driftagents/impact-advisor.md: parallel lens pass; checks repository blast radius, CI, and follow-up workagents/verdict-advisor.md: chained synthesis pass; turns research and lens outputs into one decisionagents/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
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

