backlog
Skill0 starsChanged 38 days agoMITView on GitHub
Capture, list, and prioritise ideas in BACKLOG.md — never executes items
36 other projects use a version of this.
Adopted by
Most recently taken up by
- newkayak12/claude-skillstheir own version, first seen Nov 1, 2026
- a-lottes/aSPARKtheir own version, first seen Nov 1, 2026
- ovargas/virtual-teamtheir own version, first seen Oct 25, 2026
- nschurmann/hola-aitheir own version, first seen Oct 25, 2026
- dpleshakov/tfsclitheir own version, first seen Oct 20, 2026
- RumbleJack56/skillstheir own version, first seen Oct 20, 2026
Used with
Projects with it also use issue, worktree and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
AWSSkillissue
Implement a GitHub issue end-to-end — branch, code, test, docs, and commit.
Also in 3 projects that use this
MicrosoftSkillworktree
Create, reuse or clean up a dedicated git worktree for working on a pull request or a private branch. Use from any PR-scoped workflow that needs an isolated checkout to keep current code and build output untouched.
Also in 3 projects that use this
AWSSkillretro
Conduct a retrospective on a coding session.
Also in 4 projects that use this
HashiCorpSkillchangelog
Add a `.changelog/<PR_NUMBER>.txt` entry for a GitHub Pull Request, commit, and push.
Also in 3 projects that use this
BlockSkillplan
Draft a TDD, PRD, or lightweight plan in the conversation without committing it.
Also in 4 projects that use this
VercelSkilldeploy
Deploy applications to Vercel. Use when the user says "deploy", "deploy to Vercel", "push to production", "deploy my app", or "go live".
Also in 3 projects that use this
Other versions36 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 36
- sammcj/agentic-coding★ 169same name
- nschurmann/hola-ai★ 101same name
- a-lottes/aSPARK★ 25same name
- camtrik/agent-trail★ 15same name
- ovargas/virtual-team★ 14same name
- greglas75/zuvo★ 7same name
- gonimar/claude-web-studio★ 4same name
- maxekman/skills★ 4same name
- cirne/agent-skills★ 3same name
- newkayak12/claude-skills★ 3same name
26 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
The file
We split this skill into the rules it gives an agent
6 rules. 0 are common, 3 are distinctive, and 3 are very specific to this project.
0
Common
Most of the 35 edited versions we read keep these.
3
Distinctive
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 17
Create it from the template below if it's missing.
- Very specific: line 29
If $ARGUMENTS is freeform text that isn't one of the above subcommands, treat the whole thing as add.
- Very specific: line 48
Wait for the answer. Write nothing to BACKLOG.md before it.
- Distinctive: line 50
If the conversation holds nothing to backlog, say so in one line and stop.
- Distinctive: line 85
Keep the confirmation terse and edits minimal — this skill exists partly to save Claude usage.
- Very specific: line 86
Use the ## Details section only when an item genuinely needs more than its title.
“Common” is measured: kept by at least 6 in 10 of the 35 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
/backlog
Manage a single repo-root BACKLOG.md of ideas/tasks: capture, list, prioritize, and update.
This skill strictly MANAGES the backlog — it NEVER executes the items. Its purpose is to capture ideas cheaply (defer instead of doing) and keep them prioritised. Capturing must be fast and low-token.
Backlog file: BACKLOG.md at the repository root (one backlog only — never create per-folder backlogs).
Create it from the template below if it's missing.
Subcommands (parse from $ARGUMENTS)
- (no args) or this → propose items from the conversation (see Propose). This is the default.
- add
<idea>→ quick-capture a new item (see Capture). - list
[open|done|dropped|<area>]→ show items, optionally filtered by status or area, sorted (see Sorting). - prioritize (alias groom) → re-rank; surface "quick wins" (High value + Small effort at the top); flag stale or duplicate items for the user.
- done
<id>→ set status = done (move to Closed). - drop
<id>→ set status = dropped (move to Closed). - edit
<id><field>=<value>→ change one field (title / value / effort / area / status).
If $ARGUMENTS is freeform text that isn't one of the above subcommands, treat the whole thing as add.
Item schema (minimal + area)
| Field | Values |
| ID | next integer |
| Title | one concise line |
| Value | H / M / L |
| Effort | S / M / L |
| Status | open / done / dropped |
| Area | project-defined tags (e.g. writing / research / claude-code / repo-meta / other) — set the list once in BACKLOG.md's header and reuse it |
Propose (/backlog or /backlog this)
- Pick the candidates from the conversation so far.
/backlogalone: every idea, to-do or deferred item the user mentioned./backlog this: the one subject of the user's last message before the command. That is a single candidate.
- Reply with a bullet list, one line per candidate, then one question:
Add all, or which? - Wait for the answer. Write nothing to
BACKLOG.mdbefore it. - Capture each confirmed item (see Capture) and confirm in one line per item.
- If the conversation holds nothing to backlog, say so in one line and stop.
Capture (quick, cheap, no execution)
- Append the item with defaults: Value=
M, Effort=M, Status=open, Area inferred from context (elseother). - Do NOT ask clarifying questions unless the idea is too vague to even title. Do NOT start working the item.
- Confirm in one terse line, e.g.
Added #7: <title> — M/M · research.
Sorting
Open items sorted by Value (H > M > L), then Effort (S < M < L) — so High-value / Small-effort quick wins rise to the top. Closed items (done/dropped) sit in a separate section below.
File template
# Backlog
Managed by `/backlog`. Open items sorted by value (H>M>L) then effort (S<M<L); quick wins (High value · Small effort) at the top.
**Areas:** `admin` · `money` · `home` · `work` · `other`
## Open
| ID | Title | Value | Effort | Area |
|---|---|---|---|---|
## Closed
| ID | Title | Status | Area |
|---|---|---|---|
## Details (optional — only for items needing more than a title)Rules
- One backlog only: repo-root
BACKLOG.md. Never split into per-folder backlogs. - Never execute or start a backlog item from this skill — capture / list / prioritise / update only.
- Keep the confirmation terse and edits minimal — this skill exists partly to save Claude usage.
- Use the
## Detailssection only when an item genuinely needs more than its title; quick-capture never writes details. - IDs are never reused; keep them stable across status changes.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

