New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Skill Work Slicing

by nyldn in nyldn/claude-octopus

Break a plan or spec into vertical slices that each declare what blocks them — use when work is agreed but not yet cut into fileable pieces

MITAuto-check passed

Install Skill Work Slicing

skills CLI
$ npx skills add nyldn/claude-octopus --skill skill-work-slicing -a claude-code

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

GitHub CLI
$ gh skill install nyldn/claude-octopus skill-work-slicing --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/nyldn/claude-octopus.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/skill-work-slicing .claude/skills/skill-work-slicing && 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
skill-work-slicing
GitHub stars
4.2k
Used in
1 other repo
Token cost
~1.5k tokens
SKILL.md length
915 words
Files
2
Skills in repo
62
Repo updated
First seen
Licence
MIT

At a glance

Break a plan or spec into vertical slices that each declare what blocks them — use when work is agreed but not yet cut into fileable pieces

  • Works in 4 steps: Slice vertically → Declare what blocks what → File them → …
  • Work is agreed but not yet cut into fileable pieces
  • SKILL.md covers When To Use, When Not To Use, Inputs and Workflow, plus 4 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Skill Work Slicing is an agent skill from nyldn/claude-octopus. Break a plan or spec into vertical slices that each declare what blocks them — use when work is agreed but not yet cut into fileable pieces

Its SKILL.md is about 1.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).

The repository describes itself as: Run multiple AI models against the same research, design, or coding task. Surface disagreements before you ship. The licence is MIT.

When your agent uses it

  • Work is agreed but not yet cut into fileable pieces

Example prompts

  • “/skill-work-slicing”

Workflow steps

4 steps, taken from the step headings in SKILL.md.

  1. Slice vertically
  2. Declare what blocks what
  3. File them
  4. When bd will not accept writes

What it can do on your machine

Read from SKILL.md and the folder at commit e14b84f. 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

    Links to these hosts (documentation or services it may open):

    • github.com

    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

Skill Work Slicing loads about 1.5k tokens when it runs. Until then it costs about 40 tokens; SKILL.md has 915 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~40
When it runs · the whole SKILL.md, loaded when a task matches
~1.5k

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 nyldn/claude-octopus at commit e14b84f, republished under its MIT licence (© nyldn). 915 words, ~1,485 tokens.

Download SKILL.mdSave it as .claude/skills/skill-work-slicing/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
skill-work-slicing
description
Break a plan or spec into vertical slices that each declare what blocks them — use when work is agreed but not yet cut into fileable pieces
disable-model-invocation
true

Host: Codex CLI — This skill was designed for Claude Code and adapted for Codex. Cross-reference commands use installed skill names in Codex rather than /octo:* slash commands. Use the active Codex shell and subagent tools. Do not claim a provider, model, or host subagent is available until the current session exposes it. For host tool equivalents, see skills/blocks/codex-host-adapter.md.

Work Slicing

Turn a plan, spec, or the conversation so far into a set of tickets. Each one is a vertical slice — a narrow but complete path through every layer — and each declares the tickets that block it.

This is the step between "we know what we are building" and "someone can pick up a piece of it". It does not decide anything: if decisions are still open, run skill-pressure-test first.

Before slicing, map unresolved decision records and their dependencies. Each record names its question, required evidence, owner, resolution, and unblocked implementation. A dependency cycle withholds ready status until it is recut. Invalidated decisions reopen affected work rather than leaving stale completion.

Adapted from to-tickets in mattpocock/skills (MIT), retargeted at this repo's trackers.

When To Use

  • A plan or spec exists and needs cutting into fileable work.
  • A tracking epic is too big to claim and needs children.
  • Several people or sessions will work in parallel and need boundaries.

When Not To Use

  • Decisions are still open. Slicing unresolved work produces tickets that get reopened. Use skill-pressure-test.
  • The work fits one session. File one ticket, or none.
  • You want parallel execution across agents right now, with worktrees and waves. That is /octo:parallel, which decomposes into work packages it then runs. This produces tracker state for humans and future sessions.

Inputs

The plan, spec, or conversation. Optionally a parent epic id to hang the slices under.

Workflow

1. Slice vertically

Each slice cuts a narrow but complete path through every layer it touches — schema, API, UI, tests. It is not a horizontal slice of one layer.

  • A completed slice is demoable or verifiable on its own.
  • Each is sized to fit one fresh context window.
  • "Add the database columns" is horizontal and untestable alone. "Store and display the user's timezone, end to end" is vertical.

The first slice through a new area is the tracer bullet: thin, complete, and proves the path exists before anything is built out along it.

2. Declare what blocks what

For every slice, name the slices that must close first. Only real ordering constraints — not preference, not tidiness. Two slices that merely touch the same file are not blocked on each other; two where one cannot be verified until the other exists are.

Cycles mean the slicing is wrong, not that the tracker needs a workaround. Recut.

3. File them

This repo has two trackers and they are not interchangeable:

  • bd (beads) is the system of record for work. bd create --parent=<id> makes a child; bd dep add <issue> <depends-on> makes a blocking edge; bd ready lists what is takeable — open, unblocked, and not in progress.
  • GitHub issues are the public surface, via gh. Use them when the work is externally visible or a contributor needs to see it.

Put the detail in the ticket body, not in the parent. The parent indexes; the ticket holds.

Use the tracker's atomic claim operation and read ownership back before editing a slice. If the tracker cannot claim atomically, use one integrator and do not treat an assignee read followed by a write as a lock. Never overwrite another owner's claim.

Show full SKILL.md (335 more words)Show less
4. When bd will not accept writes

bd is periodically write-blocked by pending Dolt schema migrations, and the repository rule is explicit: do not run the migration unless you are the single designated migrator, because migrating a second clone forks the schema irrecoverably.

When writes are blocked, do not pretend the work was filed and do not silently drop it. Instead:

  1. Emit the ready-to-run bd create and bd dep add commands, complete and in dependency order, so they can be run unmodified once writes return.
  2. Write them into the plan or a roadmap note under docs/roadmaps/, which is the practice this repo already follows.
  3. Say plainly, in the output, that nothing was filed and why.

Provider Or Data Priority

  1. The plan or spec as written.
  2. The repository, to check whether a slice is already partly built.
  3. The user, for sizing and priority. Do not invent priorities.

Stop Or Checkpoint Rules

  • Stop and recut if any slice cannot be verified on its own.
  • Stop if the blocking graph has a cycle.
  • Stop before filing if more than about ten slices come out of one plan — that usually means the plan is really several, and filing them all buries the first.
  • Confirm the slice list with the user before filing anything. Filing is visible to others and awkward to undo.

Output Contract

  1. Slice list — title, one-line scope, and what it blocks on.
  2. Order — which slices are takeable now, and which wait.
  3. Filed or not filed — ids and links if filed; if not, the exact commands and the reason they were not run.
  4. Left unsliced — anything in the plan too vague to cut, stated as such rather than forced into a ticket.

Verification

  • Every slice is demoable or verifiable alone.
  • No slice is a single layer's worth of work.
  • The blocking graph is acyclic and every edge is a real constraint.
  • If bd was unavailable, the emitted commands run unmodified — check the parent ids and the dependency order.

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

Files

SKILL.md and 1 other file in skills/skill-work-slicing of nyldn/claude-octopus.

  • SKILL.md
  • agents/openai.yaml

Open the folder on GitHubat commit e14b84f

Used in 1 other repository

We found 2 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in nyldn/claude-octopus, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Skill Work Slicing 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.

Skill Work Slicing compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Skill Work Slicing this skillnyldn/claude-octopus4.2k1 repos~1.5kAutomated safety check: PassMIT
Vertical SliceDonchitos/Claude-Code-Game-Studios26k—~5.2kAutomated safety check: NotesMIT
Vertical Slicesdatabuddy-analytics/Databuddy1.2k—~1.4kAutomated safety check: PassAGPL-3.0
Vertical Slicecodewithmukesh/dotnet-claude-kit7551 repos~2.6kAutomated safety check: PassMIT
V5 Breaking Changesremotion-dev/remotion63k—~879Automated safety check: PassCustom licence
Breaking Changeshashicorp/terraform-provider-aws11k—~291Automated safety check: PassMPL-2.0

Similar skills

  • Vertical Slice

    Donchitos/Claude-Code-Game-Studios

    Pre-production validation — end-to-end build to confirm the full loop is achievable before committing to Production.

    26k GitHub stars~5.2k tokensUpdated yesterday
    Game DevelopmentAuto-check: notes

  • Vertical Slices

    databuddy-analytics/Databuddy

    Design, implement, and review software using vertical slices (feature-first architecture) instead of horizontal layers.

    1.2k GitHub stars~1.4k tokensUpdated yesterday
    DevelopmentAuto-check passed

  • Vertical Slice

    codewithmukesh/dotnet-claude-kit

    Vertical Slice Architecture (VSA) for .NET applications — one of several supported architectures in dotnet-claude-kit.

    755 GitHub starsUsed in 1 repo~2.6k tokens
    Auto-check passed

  • V5 Breaking Changes

    remotion-dev/remotion

    Official

    Implement or review a Remotion 5 breaking change while the v4 and v5 release lines still share code.

    63k GitHub stars~879 tokensUpdated today
    Media & CreativeAuto-check passed

  • Breaking Changes

    hashicorp/terraform-provider-aws

    Official

    Review a PR for possible breaking changes. An agent skill from hashicorp/terraform-provider-aws.

    11k GitHub stars~291 tokensUpdated today
    DevOps & CloudAuto-check passed

  • Add Full Slice

    fullstackhero/dotnet-starter-kit

    Build a capability end-to-end — backend vertical slice (Contracts→handler→validator→endpoint) AND the React page wired to it.

    6.8k GitHub stars~783 tokensUpdated today
    Testing & QAAuto-check passed

More from nyldn/claude-octopus

All 62 skills in this repo

  • Octopus Quick

    nyldn/claude-octopus

    Quick execution for ad-hoc tasks without full workflow overhead — use for small, self-contained requests

    4.2k GitHub starsUsed in 1 repo~2.2k tokens
    Auto-check passed

  • Octopus Research

    nyldn/claude-octopus

    Thorough research across multiple sources — use for complex topics needing broad synthesis

    4.2k GitHub starsUsed in 1 repo~1.9k tokens
    Auto-check passed

  • Octopus Security Audit

    nyldn/claude-octopus

    OWASP compliance, vulnerability scanning, and adversarial red team testing — use for security reviews

    4.2k GitHub starsUsed in 1 repo~2.3k tokens
    Auto-check passed

  • Skill Audit

    nyldn/claude-octopus

    Audit codebases for quality, consistency, and broken patterns — use for pre-release or tech debt review

    4.2k GitHub starsUsed in 1 repo~3.2k tokens
    Auto-check passed

  • Skill Content Pipeline

    nyldn/claude-octopus

    Extract patterns and anatomy from URLs — use to reverse-engineer content strategies from live pages

    4.2k GitHub starsUsed in 1 repo~3.9k tokens
    Auto-check passed

  • Skill Context Detection

    nyldn/claude-octopus

    Auto-detect work context (Dev vs Knowledge) — use to tailor workflows based on current task type

    4.2k GitHub starsUsed in 1 repo~2.6k tokens
    Auto-check passed

Questions about Skill Work Slicing

What does Skill Work Slicing do?

Break a plan or spec into vertical slices that each declare what blocks them — use when work is agreed but not yet cut into fileable pieces. Skill Work Slicing is an agent skill from nyldn/claude-octopus.

When should I use Skill Work Slicing?

Skill Work Slicing fits situations like: work is agreed but not yet cut into fileable pieces.

How do I install Skill Work Slicing in Claude Code?

Run `npx skills add nyldn/claude-octopus --skill skill-work-slicing -a claude-code`. Or copy the skill folder (skills/skill-work-slicing in nyldn/claude-octopus) into .claude/skills/skill-work-slicing in your project. Claude Code loads it when a task matches its description.

How do I install Skill Work Slicing in Codex?

Run `npx skills add nyldn/claude-octopus --skill skill-work-slicing -a codex`. Or copy the skill folder (skills/skill-work-slicing in nyldn/claude-octopus) into .agents/skills/skill-work-slicing in your project. Codex loads it when a task matches its description.

Can I use Skill Work Slicing 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 nyldn/claude-octopus --skill skill-work-slicing -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/skill-work-slicing, .gemini/skills/skill-work-slicing, .github/skills/skill-work-slicing and .opencode/skills/skill-work-slicing in your project.

What does Skill Work Slicing need to run?

SKILL.md names no scripts, command-line tools or credentials: Skill Work Slicing is instructions for the agent only.

Does Skill Work Slicing access the network?

SKILL.md names 1 domain. As links in the text: github.com. This is read from the text; nothing was executed.

Is Skill Work Slicing 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 Skill Work Slicing use?

Skill Work Slicing 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 Skill Work Slicing use?

About 1.5k tokens (SKILL.md is roughly 5.9k 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 Skill Work Slicing?

Skills that share tags, products or a category with Skill Work Slicing: Vertical Slice (Donchitos/Claude-Code-Game-Studios, 26k stars), Vertical Slices (databuddy-analytics/Databuddy, 1.2k stars), Vertical Slice (codewithmukesh/dotnet-claude-kit, 755 stars) and V5 Breaking Changes (remotion-dev/remotion, 63k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Skill Work Slicing?

nyldn (a GitHub user) maintains it in nyldn/claude-octopus, which has 4,192 GitHub stars. The repository holds 62 skills in this directory. The repository was last updated on October 9, 2026.

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