Backlog Manager

Classifies backlog issues into risk/type/agent-ready labels with evidence-backed reasoning, for GitHub, Linear, or a local file

Tested · Works

Test report

Verdict
Tested · Works
Score
9.6/10
Tested
Jul 15, 2026
Environment
Claude Code 2.x (agent harness)
Upstream re-checked
Aug 10, 2026 · 642c4de

Ran it for real against a 5-item local backlog (stale README command, dark-mode feature, flaky test, broken doc link, Stripe-to-Adyen migration): it correctly agent-ready'd only the two mechanical docs fixes and routed the flaky test, the unspec'd feature, and the billing migration to needs:human with a specific blocking question for each -- exactly the judgement call an ad hoc triage pass got fuzzy on.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

  • Installs cleanly 5/5
  • Triggers reliably 5/5
  • Output vs. baseline 9/10
  • Docs & honesty 5/5

What Backlog Manager does

Triages an engineering backlog (GitHub Issues, GitHub Projects, Linear, or a named local file) by assigning a managed risk:*/type:*/agent:ready|needs:human label set, writing a short Agent Assessment with reasoning and a suggested plan per issue, syncing state from linked PRs, and reporting drift and branch-cleanup candidates. It explicitly refuses to implement code, delete branches, or invent tracker policy, and stops to report blockers instead of guessing.

How to install Backlog Manager

git clone https://github.com/owainlewis/agent-skills.git
cd agent-skills
mkdir -p ~/.claude/skills
cp -r skills/backlog-manager ~/.claude/skills/backlog-manager

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger Backlog Manager

  • /backlog-manager Classifies backlog issues into risk/type/agent-ready labels with evidence-backed reasoning, for GitHub, Linear, or a local file

It also activates on plain-language prompts like these:

  • Triage this BACKLOG.md file and label each item's risk and agent-readiness
  • Classify our open GitHub issues into agent-ready versus needs-human
  • Sync backlog status from linked PRs and flag stale branch candidates

Frequently asked questions

Is the Backlog Manager skill free?
Yes. The skill itself is free from owainlewis/agent-skills. SkillProof publishes the install command and an independent test verdict at no cost.
Does Backlog Manager work with Claude Code?
We tested it with Claude Code 2.x (agent harness) on Jul 15, 2026. Verdict: Tested · Works. Ran it for real against a 5-item local backlog (stale README command, dark-mode feature, flaky test, broken doc link, Stripe-to-Adyen migration): it correctly agent-ready'd only the two mechanical docs fixes and routed the flaky test, the unspec'd feature, and the billing migration to needs:human with a specific blocking question for each -- exactly the judgement call an ad hoc triage pass got fuzzy on.
What is the Backlog Manager SkillProof Score?
9.6/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 9/10, docs & honesty 5/5.
How do I install Backlog Manager?
Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Backlog Manager with Cursor, Copilot, Gemini CLI, Codex or other AI tools?
The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.