agentsclimarketplace

Backlog review

Skill joris887/exosuit/.claude/skills/backlog-review

Execute comprehensive backlog review. Analyzes story quality, Definition of Ready compliance, dependencies, zombie stories, and generates a backlog health report.From its SKILL.md

Install
npx -y skills add joris887/exosuit --skill backlog-review

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 4 stars4 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

5.1 KB, as published. Nobody here has run it


backlog-review

Execute comprehensive backlog review:

1. Load Current State

Read these files:

  • @docs/reference/BACKLOG_INDEX.md (backlog overview)
  • docs/reference/backlog/E##-name.md (epic files as needed)
  • @docs/reference/PRD_SUMMARY.md (requirements overview, if exists)
  • @docs/progress.md (completed work)

2. Theme Coverage Analysis

Map each epic to requirements:

| Epic | Requirements Covered | Coverage % | Gap Analysis |

Priority Validation

  • Are high-priority items truly high-value?
  • Are dependencies properly ordered?
  • Any blocked items that should be deprioritized?

Scope Assessment

  • Stories that exceed original scope
  • Features creeping in without justification
  • Non-goals being violated

3. Story Quality Scan

For each non-done story, validate against the Definition of Ready checklist:

CriterionCheck
Title clear and specificDescribes the change, not the problem
Type assignedOne of: feature, bugfix, refactor, spike, infra, testing, docs, security, performance, skill
Size classifiedTRIVIAL, SMALL, STANDARD, LARGE, or XL. Flag for splitting only when the story spans unrelated topics — file count is not a threshold. See the cohesion test in ideate/references/story-template.md
Cohesion test passedSplitting the story would create artificial seams, not two meaningful pieces
3-7 acceptance criteriaEach testable and specific; LARGE/XL may exceed 3-7, grouped under sub-headings. No "should be fast" or "handle errors properly"
Verification commandsExact commands that prove completion
Out of scope definedAt least one explicit exclusion
Affected files listedProportionate to size, not capped at a fixed number
Pattern references"Follow patterns in [file]" where applicable
Dependencies resolvedNo unresolved blockers
No ambiguous languageNo vague terms, all criteria measurable
Self-containedAll referenced context included or linked

Classify each story:

  • Ready: Passes all 12 criteria → status: ready
  • Needs refinement: Missing 1-3 criteria → list what's missing
  • Needs rewrite: Missing 4+ criteria or too large → flag for /ideate refinement

4. Dependency Mapping

Create dependency graph for upcoming work:

[Story A] --depends on--> [Story B]
                              |
                              v
                         [Story C]

Validate dependency health:

  • Flag circular dependencies (A→B→C→A)
  • Flag stories blocked by draft/not-ready dependencies
  • Flag stories with >2 transitive dependencies (fragile chain)
  • Identify the critical path: longest dependency chain

5. Zombie Story Detection

Check each story's created: date (from inline metadata or YAML frontmatter):

  • Zombie (>2 sprint cycles old, still not done): Must be split or killed
  • Aging (>1 sprint cycle, same status): Flag for attention
  • Stalled (status: in-progress but no commits referencing it in >1 week): Flag as potentially abandoned

For each zombie, recommend: Split (too large), Kill (no longer needed), or Unblock (has a blocker that can be resolved).

6. Flow Metrics

If docs/sessions/.activity-log.jsonl exists and contains story events:

  • Throughput: Stories completed per sprint (from story events with to: done)
  • Cycle time by size: Average time from in-progress to done for TRIVIAL/SMALL/STANDARD/LARGE/XL
  • Completion rate: Stories started vs completed
  • Type distribution: Which story types are most common

7. Backlog Health Report

## Backlog Health Report - [Date]

### Overall Health: X/10

### Definition of Ready Compliance
- Stories meeting DoR: X/Y (Z%)
- Common DoR failures: [list most frequent missing criteria]
- Stories needing refinement: [list IDs]

### Coverage
- Requirements covered: X%
- Orphan stories (no requirement trace): X
- Requirement gaps (no stories): [list]

### Quality
- Stories ready for sprint: X
- Stories needing refinement: Y
- Stories too large (need split): Z

### Flow
- Throughput: X stories/sprint (last 3 sprints)
- Avg cycle time: TRIVIAL Xh, SMALL Xh, STANDARD Xh
- Completion rate: X%

### Zombie Stories
- Zombie (>2 cycles): [list IDs with age]
- Aging (>1 cycle): [list IDs]
- Stalled in-progress: [list IDs]

### Dependency Health
- Stories with unresolved blockers: [list]
- Circular dependencies: [list or "None"]
- Critical path length: X stories

### Priority Issues
- Blocked items: [list]
- Misordered dependencies: [list]

### Recommended Actions
1. [Action with specific story IDs]
2. [Action]
3. [Action]

Update docs/reference/BACKLOG_INDEX.md Backlog Health section with the calculated metrics.

Output the full backlog health report with specific recommendations.

Keep looking

Skills are one crate of 627,801. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.