.agents/skills/oat-pjm-review-backlog/SKILL.md
Use when prioritizing the file-backed repo backlog or evaluating roadmap alignment. Produces value-effort ratings, dependency mapping, and execution recommendations.
npx skillsauth add tkstang/open-agent-toolkit oat-pjm-review-backlogInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Analyze the file-backed backlog under .oat/repo/reference/backlog/ to produce a structured review with value-effort ratings, dependency graph, parallel work lanes, and a recommended execution sequence. Optionally cross-reference a roadmap to identify alignment gaps.
OAT MODE: Backlog Review
Purpose: Review active backlog item files, evaluate roadmap alignment, and recommend a practical execution order.
When executing this skill, provide lightweight progress feedback so the user can tell what’s happening after they confirm.
Print a phase banner once at start using horizontal separators, e.g.:
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ OAT ▸ REVIEW BACKLOG ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Before multi-step work, print short step indicators, e.g.:
[1/5] Resolving backlog inputs…[2/5] Cataloging backlog items…[3/5] Reading codebase context…[4/5] Writing review document…[5/5] Summarizing recommendations…Parse from $ARGUMENTS:
.oat/repo/reference/backlog/..oat/repo/reviews/backlog-and-roadmap-review.md.Backlog root:
backlog-root is provided, use it directly..oat/repo/reference/backlog/.backlog/index.mdbacklog/items/*.mdbacklog/completed.mdRoadmap document (optional):
--roadmap is provided, use it directly..oat/repo/reference/roadmap.md.Output path:
--output is provided, use it directly..oat/repo/reviews/backlog-and-roadmap-review.md.Read all active backlog item files from backlog/items/*.md.
For each item, capture:
id when present; if missing, assign a stable sequential review ID (B01, B02, ...)titlepriorityscopestatus## Description and ## Acceptance CriteriaAlso read:
backlog/index.md for curated overview notesbacklog/completed.md for recent completionsbacklog/archived/*.md only when historical context is needed for an active itemBefore rating items, build enough context to assess effort accurately:
Use the Explore agent for broad codebase exploration if needed. Use direct Read/Glob/Grep for targeted lookups.
For each active backlog item, assess:
Value (High / Medium / Low):
Effort (High / Medium / Low):
Quadrant (derived):
Provide a brief rationale for each rating.
For each item, identify:
Then group items into independent parallel lanes and organize them into recommended execution waves.
If a roadmap was provided:
Use the template at .agents/skills/oat-pjm-review-backlog/references/backlog-review-template.md.
Ensure:
After writing the review, provide:
documentation
Use when OAT implementation changes and repository reference docs must be synchronized. Updates .oat/repo/reference to match current behavior.
business
Merge multiple analysis artifacts into a single coherent report with provenance tracking. Reads existing artifacts from /deep-research, /analyze, and /compare.
testing
Use when the user questions or suspects an agent claim is wrong. Adversarially gathers evidence to verify or refute the claim using the best sources available in the current environment.
tools
Use when prioritizing backlog work or evaluating a roadmap. Produces value-effort ratings, dependency mapping, and execution recommendations.