Home / flurdy / agent-skills · skills/backlog-groom/SKILL.md · GitHub

backlog-groom skillA

backlog-groom is agent-read markdown (skill) from flurdy/agent-skills: Per-bead backlog quality audit — flags thin descriptions, label drift, stale YAGNIs, mis-prioritised nice-to-haves, obvious splits, duplicates. Read-only; mutations need approval, dangerous ones one by one; judges quality, not template conformance..

Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.

What the file says

# Backlog Groom — Per-Bead Quality Audit

Walk the **open backlog** and ask, for each bead: *is this any good?* Flag hygiene, priority, lifecycle, structure, and duplicate problems, propose a concrete fix for each, and **only mutate on explicit approval**.

This is the hygiene counterpart to the intake/reconciliation skills — it is the only one that systematically reads every open bead and improves its quality.

## Relationship to other tools

- **`/triage`** is *forward intake*: prompt/Jira → new bead(s), with dup-check and splitting **at creation time**. The groomer does not create beads from prompts and does not re-implement splitting — when a bead obviously needs splitting, it hands the bead to `/triage`.
  - **`/triage <bead-id>`** (refine mode) is the *depth* counterpart to this sweep: it investigates one existing bead against the code, then deepens, corrects, or splits it. Hand a bead there whenever grooming it needs real investigation rather than a one-shot edit — see the "be fast" rule below.
…

Read the whole file at its exact version.

How to install

Latest version
mdr add flurdy/agent-skills/backlog-groom@v0.1.2
Exact content
mdr add flurdy/agent-skills/backlog-groom@sha256:e3d43f0b6b13dffc

Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_qokiafunwtganooi.svg)](https://markdownregistry.com/a/art_qokiafunwtganooi)

1 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
v0.1.2 latest2026-09-07 23d6b60 18,862 BA view · diff
v0.1.12026-09-03 7267adf 18,864 BA view · diff
v0.1.12026-09-03 cf76f5d 19,228 BA view · diff
v0.1.02026-08-09 eda93ef 19,230 BA view · diff
v0.1.02026-07-29 c2e967a 18,694 BA view

Audit of the latest version

A  17 of 17 checks passed. Deterministic, no model, same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (18862 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

flurdy/agent-skills · 9 stars · license MIT · pushed 2026-09-23 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_qokiafunwtganooi
GET https://markdownregistry.com/api/v1/resolve?ref=flurdy/agent-skills/backlog-groom
GET https://markdownregistry.com/api/v1/blob/e3d43f0b6b13dffce2b08a0e74322658bdc4acd262f8d0ba174c5daca6d3ddb4

Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

More from flurdy/agent-skills

AGENTS.md agents
flurdy/agent-skills · AGENTS.md
git:20260630.7b39634 · audit B · 9 stars
CLAUDE.md claude
flurdy/agent-skills · CLAUDE.md
git:20260907.23d6b60 · audit A · 9 stars
architect skill
flurdy/agent-skills · skills/architect/SKILL.md · Architecture and implementation planning gate for complex or high-blast-radius work. Produces evidence-backed…
v2.0.1 · audit A · 9 stars
artifact-hygiene skill
flurdy/agent-skills · skills/artifact-hygiene/SKILL.md · Run a local-only, read-only advisory audit of publishable working-tree files and unpublished branch history with…
v0.6.1 · audit A · 9 stars
beads-check-dolt-migration skill
flurdy/agent-skills · skills/beads-check-dolt-migration/SKILL.md · Detect whether a beads repository needs classic-to-Dolt migration or an in-place Dolt schema upgrade.
v1.1.0 · audit A · 9 stars
beads-migrate-to-dolt skill
flurdy/agent-skills · skills/beads-migrate-to-dolt/SKILL.md · Safely migrate classic Beads data or upgrade a Dolt schema, preserving backups and remote history. Repository aftercare…
v2.0.1 · audit A · 9 stars
beads-setup skill
flurdy/agent-skills · skills/beads-setup/SKILL.md · Preview and separately confirm a fresh repository Beads store with a dedicated private GitHub Dolt remote. Refuses…
v0.1.0 · audit A · 9 stars
beads skill
flurdy/agent-skills · skills/beads/SKILL.md · Shared Beads workflow baseline. Use whenever an agent uses `bd`, manages durable tasks, blockers, or handoffs, resolves…
v0.6.0 · audit A · 9 stars
browser-screenshot skill
flurdy/agent-skills · skills/browser-screenshot/SKILL.md · Take a screenshot of the running web application for visual verification of UI/CSS changes. Use when iterating on…
v1.1.0 · audit A · 9 stars
circleci-status skill
flurdy/agent-skills · skills/circleci-status/SKILL.md · Check CircleCI build status and failed job logs for the current GitHub repository. Use when asked whether CircleCI is…
v1.0.1 · audit A · 9 stars
clean-code skill
flurdy/agent-skills · skills/clean-code/SKILL.md · Format, lint, and fix all warnings across the entire codebase — including test files and pre-existing issues.
v1.1.0 · audit A · 9 stars
complete-task skill
flurdy/agent-skills · skills/complete-task/SKILL.md · Complete an in-progress task by running clean-code, staging, and committing. Close the bead on trunk, leave it open for…
v2.0.0 · audit A · 9 stars

Every file in flurdy/agent-skills

Browse by kind, by grade A, or by owner.