Agent skill

Review Backlog Killer

by aozyildirim in aozyildirim/Agena

Detect pull requests aging past warn / critical thresholds, score severity, and nudge reviewers via Slack DM, channel, email, or directly as a PR comment — with one-time auto-escalation when a PR…

MITAuto-check passedDevelopment

Install Review Backlog Killer

skills CLI
$ npx skills add aozyildirim/Agena --skill review-backlog-killer -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install aozyildirim/Agena review-backlog-killer --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/aozyildirim/Agena.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/agena/review-backlog-killer .claude/skills/review-backlog-killer && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
review-backlog-killer
GitHub stars
103
Token cost
~802 tokens
SKILL.md length
384 words
Files
1
Skills in repo
5
Repo updated
First seen
Licence
MIT

At a glance

Detect pull requests aging past warn / critical thresholds, score severity, and nudge reviewers via Slack DM, channel, email, or directly as a PR comment — with one-time auto-escalation when a PR…

  • Works in 6 steps: Define open: PR is open when `merged_at… → Configure thresholds per workspace… → Poller every 30 minutes updates… → …
  • Tasks that involve Pull requests
  • SKILL.md covers How to apply this pattern, Example PR comment template and Notes
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Review Backlog Killer is an agent skill from aozyildirim/Agena. Detect pull requests aging past warn / critical thresholds, score severity, and nudge reviewers via Slack DM, channel, email, or directly as a PR comment — with one-time auto-escalation when a PR hits critical so velocity stops leaking through review queues.

Its SKILL.md is about 800 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Development, covering Pull requests and Sprint planning and agile. It works with Slack. The repository describes itself as: Agentic AI platform with pixel agent technology — autonomous code generation, PR automation & multi-tenant SaaS. The licence is MIT.

When your agent uses it

  • Tasks that involve Pull requests
  • Tasks that involve Sprint planning and agile

Example prompts

  • “/review-backlog-killer”

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. Define open: PR is open when `merged_at IS NULL AND closed_at IS
  2. Configure thresholds per workspace (chip-pick is best UX —
  3. Poller every 30 minutes updates age_hours and severity
  4. Pick a notify channel per workspace
  5. Auto-escalate once when a PR crosses the critical threshold
  6. Manual nudge button on every row — fires the configured channel

What it can do on your machine

Read from SKILL.md and the folder at commit c4c92f8. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Review Backlog Killer loads about 802 tokens when it runs. Until then it costs about 70 tokens; SKILL.md has 384 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~70
When it runs · the whole SKILL.md, loaded when a task matches
~802

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from aozyildirim/Agena at commit c4c92f8, republished under its MIT licence (© aozyildirim). 384 words, ~802 tokens.

Download SKILL.mdSave it as .claude/skills/review-backlog-killer/SKILL.md (or your agent's skills folder).
name
review-backlog-killer
description
Detect pull requests aging past warn / critical thresholds, score severity, and nudge reviewers via Slack DM, channel, email, or directly as a PR comment — with one-time auto-escalation when a PR hits critical so velocity stops leaking through review queues.
tags
code-review, pull-request, slack, devex, ai-agent
publisher
agena

Review Backlog Killer

Pull requests get lost in review queues; team velocity drops silently. Sprint planning shows it as "I dunno, sometimes the reviewers are slow". This pattern surfaces stuck PRs deterministically and sends the reviewer a nudge through whichever channel they actually read.

How to apply this pattern

  1. Define open: PR is open when merged_at IS NULL AND closed_at IS NULL AND its provider status is in {open, opened, pending, review_required, in_review, active}. PRs with provider status in {abandoned, declined, closed, rejected} drop off the backlog.

  2. Configure thresholds per workspace (chip-pick is best UX — 6h / 12h / 1d / 2d / 3d / 1w / custom). Defaults: 24h warn, 48h critical, 6h between auto-nudges to the same reviewer.

  3. Poller every 30 minutes updates age_hours and severity (info < warn ≤ warning < critical ≤ critical) on every open PR. Merged or closed PRs auto-resolve out of the backlog.

  4. Pick a notify channel per workspace:

    • slack_dm — direct, most attention
    • slack_channel — visible to team
    • email — for async-first teams
    • pr_comment — most attention-grabbing because it lands where the reviewer already lives. The comment text is locale-aware so non-English teams don't get an English nudge.
    • manual — dashboard-only, no auto-notify
  5. Auto-escalate once when a PR crosses the critical threshold: set escalated_at, mark severity, surface above the fold to tech leads. Fire it once per PR, not on every poll cycle.

  6. Manual nudge button on every row — fires the configured channel immediately, overrides the interval. Useful for a tech lead doing a one-shot push before standup.

Show full SKILL.md (137 more words)Show less

Example PR comment template

⏱️ AGENA Review Backlog

This PR has been waiting for review for **47 hours** (severity: critical).
Nudge #2.

Configure thresholds at /dashboard/review-backlog.

When the Reviews module is also on, the message includes AGENA review score: 84 so reviewers see the time investment before clicking.

Notes

  • Idempotency on PR comment: before posting, check whether a prior AGENA comment already exists on that PR — re-post would be spammy. If the comment was deleted by a human, treat the row as un-nudged so the next cycle is allowed to comment again.
  • Provider-aware status refresh: PRs marked active in your local DB may have been abandoned upstream; refresh status before deciding to nudge so you don't ping reviewers on dead PRs.
  • Exempt repos are essential — legacy / maintenance repos shouldn't trigger nudges. Comma-separated repo-mapping ids in a workspace setting is the simplest UX.
  • The poller scales linearly with open PR count; 1000 open PRs ≈ 1 second of polling per cycle.

© aozyildirim, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/agena/review-backlog-killer of aozyildirim/Agena.

Open the folder on GitHubat commit c4c92f8

Compare with similar skills

Review Backlog Killer next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Review Backlog Killer compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Review Backlog Killer this skillaozyildirim/Agena103—~802Automated safety check: PassMIT
Human Writingkylesnowschwartz/SimpleClaude114—~3.6kAutomated safety check: PassNone
Process PR Reviewsnexu-io/nexu3.3k—~2.5kAutomated safety check: PassMIT
Ade Deeplinksarul28/ADE114—~3.2kAutomated safety check: PassAGPL-3.0
Reproduce And Fix Issuescursor/plugins11k1 repos~3.6kAutomated safety check: PassNone
Cold Readerkylesnowschwartz/SimpleClaude114—~5.7kAutomated safety check: PassNone

Similar skills

  • Human Writing

    kylesnowschwartz/SimpleClaude

    MUST be used for any request to draft, write, compose, or reword text another person will read, including 'draft a message', 'draft a reply', 'draft a Slack message', 'write an email', 'draft a PR…

    114 GitHub stars~3.6k tokensUpdated today
    DevelopmentAuto-check passed
  • Process PR Reviews

    nexu-io/nexu

    A skill your agent uses when the user asks to process, triage, fetch, view, count, list, or resolve review feedback in a GitHub PR.

    3.3k GitHub stars~2.5k tokensUpdated 5 mo ago
    DevelopmentAuto-check passed
  • Ade Deeplinks

    arul28/ADE

    A skill your agent uses when an agent needs to mint, share, or open ADE deeplinks (lane, work session, file, commit, artifact, branch, PR, Linear issue) so users — or the agent itself — can jump…

    114 GitHub stars~3.2k tokensUpdated today
    DevelopmentAuto-check passed
  • Official

    Reproduce triaged Slack bugs through a configured app-control adapter, verify existing fixes, and open a bounded draft pull request only after before-and-after proof.

    11k GitHub starsUsed in 1 repo~3.6k tokens
    DevelopmentAuto-check passed
  • Cold Reader

    kylesnowschwartz/SimpleClaude

    A document is done when a reader with no project context can understand it; this skill runs that check as a Vale lint plus a context-free reviewer pass and a scorecard.

    114 GitHub stars~5.7k tokensUpdated today
    DevelopmentAuto-check passed
  • Slack PR Message

    LedgerHQ/ledger-live

    Generate a formatted Slack message to share a pull request with the team.

    622 GitHub stars~290 tokensUpdated yesterday
    DevelopmentAuto-check passed

More from aozyildirim/Agena

  • Cross Source Correlation

    aozyildirim/Agena

    Correlate near-in-time events across PR merges, deploys, monitoring (Sentry/NewRelic/Datadog/AppDynamics) and ticket trackers (Jira/Azure DevOps) into confidence-scored clusters that answer "which…

    103 GitHub stars~756 tokensUpdated 2 days ago
    Auto-check passed
  • Integration Rule Engine

    aozyildirim/Agena

    A declarative routing engine that turns ticket / error attributes (reporter, label, project, area path, error class, environment) into a tag + AI agent + priority assignment, so cross-source…

    103 GitHub stars~976 tokensUpdated 2 days ago
    Auto-check passed
  • Owasp Reviewer Prompt

    aozyildirim/Agena

    A paranoid OWASP-Top-10-aware system prompt for AI code review that traces data flow, treats every input as malicious, maps each finding to an OWASP category, and outputs a structured Summary /…

    103 GitHub stars~978 tokensUpdated 2 days ago
    Auto-check passed
  • Stale Ticket Triage

    aozyildirim/Agena

    Replace the weekly "look at every ticket older than X days" meeting with a scheduled AI scan that picks close / snooze / keep per ticket plus a one-sentence reason, so a PM can bulk-approve in 90…

    103 GitHub stars~714 tokensUpdated 2 days ago
    Auto-check passed

Works with

Questions about Review Backlog Killer

What does Review Backlog Killer do?

Detect pull requests aging past warn / critical thresholds, score severity, and nudge reviewers via Slack DM, channel, email, or directly as a PR comment — with one-time auto-escalation when a PR…. Review Backlog Killer is an agent skill from aozyildirim/Agena. Detect pull requests aging past warn / critical thresholds, score severity, and nudge reviewers via Slack DM, channel, email, or directly as a PR comment — with one-time auto-escalation when a PR hits critical so velocity stops leaking through review queues.

When should I use Review Backlog Killer?

Review Backlog Killer fits situations like: tasks that involve Pull requests; tasks that involve Sprint planning and agile.

How do I install Review Backlog Killer in Claude Code?

Run `npx skills add aozyildirim/Agena --skill review-backlog-killer -a claude-code`. Or copy the skill folder (skills/agena/review-backlog-killer in aozyildirim/Agena) into .claude/skills/review-backlog-killer in your project. Claude Code loads it when a task matches its description.

How do I install Review Backlog Killer in Codex?

Run `npx skills add aozyildirim/Agena --skill review-backlog-killer -a codex`. Or copy the skill folder (skills/agena/review-backlog-killer in aozyildirim/Agena) into .agents/skills/review-backlog-killer in your project. Codex loads it when a task matches its description.

Can I use Review Backlog Killer in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add aozyildirim/Agena --skill review-backlog-killer -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/review-backlog-killer, .gemini/skills/review-backlog-killer, .github/skills/review-backlog-killer and .opencode/skills/review-backlog-killer in your project.

What does Review Backlog Killer need to run?

SKILL.md names no scripts, command-line tools or credentials: Review Backlog Killer is instructions for the agent only.

Does Review Backlog Killer access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Review Backlog Killer safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Review Backlog Killer use?

Review Backlog Killer is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Review Backlog Killer use?

About 802 tokens (SKILL.md is roughly 3.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Review Backlog Killer?

Skills that share tags, products or a category with Review Backlog Killer: Human Writing (kylesnowschwartz/SimpleClaude, 114 stars), Process PR Reviews (nexu-io/nexu, 3.3k stars), Ade Deeplinks (arul28/ADE, 114 stars) and Reproduce And Fix Issues (cursor/plugins, 11k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Review Backlog Killer?

aozyildirim (a GitHub user) maintains it in aozyildirim/Agena, which has 103 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on October 9, 2026.

Source: aozyildirim/Agena on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.