agentleFS
nakane1chomenakane1chome/claude-skills/skills/sdlc-cross-review/SKILL.md

sdlc-cross-review

Skill0 starsChanged 8 months agoUnlicenseView on GitHub

Review a document against its SDLC lifecycle context — assess completeness and check consistency with parent documents in the document hierarchy.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 7 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈7

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read the target document and its surrounding project structure

    line 14
  2. Distinctive:

    If the project defines its own hierarchy, use that.

    line 17
  3. Distinctive:

    If the document isn't ready for cross-review, recommend the appropriate skill and stop

    line 24
  4. Distinctive:

    Ask: does the developer want to proceed with cross-review now, or address completeness first?

    line 25
  5. Distinctive:

    Do validation artifacts exist that cover what the document specifies?

    line 36
  6. Distinctive:

    Ask: are missing validation artifacts a known gap, or an oversight?

    line 39
  7. Distinctive:

    Not every project will use all levels.

    line 93

≈ “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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Review the target document(s) at $ARGUMENTS against its SDLC lifecycle context.

Stop after each stage and have changes reviewed with user.

Note: This skill checks a document's position and consistency within a project hierarchy — it does not polish the document itself. Stages 0-4 are analysis only — findings are presented for discussion, not applied as edits. The developer holds final authority on all judgment calls.

  1. Read and identify context (developer confirms)
    • Read the target document and its surrounding project structure
    • What is this document about and where does it sit in the project?
    • Can you identify a document hierarchy (V-model, or project-defined)?
    • If the project defines its own hierarchy, use that; otherwise ask the developer to clarify
    • Confirm understanding of the document's position before proceeding
  2. Assess completeness (agent proposes, developer decides)
    • Is this a skeleton that needs fleshing out, or a draft that needs polishing?
    • Skeletons need generative work (structure, diagrams, missing sections) — that's a flesh-out task, not a cross-review
    • Drafts with language issues need review-steps first
    • If the document isn't ready for cross-review, recommend the appropriate skill and stop
    • Ask: does the developer want to proceed with cross-review now, or address completeness first?
  3. Review vs parent document (agent critiques, developer discusses)
    • Identify the parent document(s) that constrain this document (left side, decomposition)
    • Is the target document consistent with decisions and constraints in its parent(s)?
    • Are there contradictions or gaps between the target and its parent documents?
    • Does the target document trace back to requirements or decisions in the parent?
    • Present findings and ask: are any inconsistencies intentional or reflect evolved thinking?
  4. Cross-validate against the right side (agent critiques, developer discusses)
    • Identify the validation pair for this document (see V-Model Context below)
    • Do validation artifacts exist that cover what the document specifies?
    • Is anything specified in the document that has no corresponding validation?
    • Is anything validated that isn't specified in the document?
    • Ask: are missing validation artifacts a known gap, or an oversight?
  5. Summary and recommendations (agent leads)
    • What is the document's overall consistency with its hierarchy?
    • What are the top issues to address?
    • Recommendation: consistent / minor gaps / needs rework

Pipeline Position

This skill sits outside the main pipeline (flesh-out -> review-steps -> strong-edit -> agent-optimize). It's a lateral check — validating a document against its project context, not polishing the document itself. Run it when a document is mature enough to check against its hierarchy.

When to Use This vs Other Skills

GoalUse
Raw notes need structure and expansionflesh-out
Draft needs polish and consistencyreview-steps
Complete draft needs critical evaluationstrong-edit
Check document against its SDLC hierarchysdlc-cross-review
Finalized document needs agent-friendly restructuringagent-optimize

V-Model Context

The V-model pairs each definition stage with a corresponding testing stage. The left side decomposes requirements; the right side validates them. Each level on the right validates the corresponding level on the left.

Requirements Analysis ◄──────────────────► Acceptance Testing
     │                                              ▲
     │ constrains                                   │ validates
     ▼                                              │
System Design ◄────────────────────────────► System Testing
     │                                              ▲
     │ constrains                                   │ validates
     ▼                                              │
Architecture Design ◄──────────────────────► Integration Testing
     │                                              ▲
     │ constrains                                   │ validates
     ▼                                              │
Module Design ◄────────────────────────────► Unit Testing
     │                                              ▲
     │ constrains                                   │ validates
     ▼                                              │
              Implementation

Standard Cross-Validation Pairs

Left Side (Definition)Right Side (Validation)
Requirements analysisAcceptance testing
System designSystem testing
Architecture designIntegration testing
Module designUnit testing

Not every project will use all levels. Identify which levels the project uses and apply the relevant checks.

References

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.