New: 97,000+ 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

Decompose Gates

by happier-dev in happier-dev/happier

Decompose a hard or multi-part task into independently checkable pieces with explicit verification gates and risk-weighted ordering.

MITAuto-check passedAgent Workflows

Install Decompose Gates

skills CLI
$ npx skills add happier-dev/happier --skill decompose-gates -a claude-code

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

GitHub CLI
$ gh skill install happier-dev/happier decompose-gates --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/happier-dev/happier.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/decompose-gates .claude/skills/decompose-gates && 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
decompose-gates
GitHub stars
1.9k
Token cost
~1.5k tokens
SKILL.md length
772 words
Files
1
Skills in repo
28
Repo updated
First seen
Licence
MIT

At a glance

Decompose a hard or multi-part task into independently checkable pieces with explicit verification gates and risk-weighted ordering.

  • Works in 8 steps: Split along verification boundaries, not… → State each piece as a falsifiable claim,… → Name the risk spots before sequencing.… → …
  • Planning corridor-sized work
  • SKILL.md covers Procedure, When pieces become lane briefs, Output and Failure this prevents
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Decompose Gates is an agent skill from happier-dev/happier. Decompose a hard or multi-part task into independently checkable pieces with explicit verification gates and risk-weighted ordering. Use when planning corridor-sized work, writing lane briefs for subagents or Codex, or whenever a task is too large to verify as a whole.

Its SKILL.md is about 1.5k 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 Agent Workflows. The repository describes itself as: Web, Desktop & Mobile client and orchestrator for Codex, Claude Code, OpenCode, Pi, Cursor, Grok, Antigravity, Kimi, Augment Code, Qwen, fully end-to-end encrypted. The licence is MIT.

When your agent uses it

  • Planning corridor-sized work
  • Writing lane briefs for subagents
  • Whenever a task is too large to verify as a whole

Example prompts

  • “/decompose-gates”

Workflow steps

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

  1. Split along verification boundaries, not implementation convenience. Each piece must have its own pass/fail check that does not depend on…
  2. State each piece as a falsifiable claim, not a task. "The watermark advances only after server ack" (checkable) — not "update watermark…
  3. Name the risk spots before sequencing. Write the two or three "if I'm wrong anywhere, it's here" spots — silent failure modes…
  4. Order by information yield. Test first the smallest shared assumption whose failure would invalidate repeated downstream units. This gates…
  5. Relay dependency context, not only order. State the upstream contract and evidence each piece consumes. Those assumptions are themselves…
  6. Right-size. A piece owns a whole responsibility end to end: analysis, change, tests, validation. Too small to fail meaningfully is…
  7. Prefer consumed verticals over horizontal spines. The first implementation slice should connect a real entry point through its canonical…
  8. Firewall live-path corrections. If gated or dormant work exposes a live dispatch, lifecycle, persistence, migration, or startup defect…

What it can do on your machine

Read from SKILL.md and the folder at commit 493820f. 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

Decompose Gates loads about 1.5k tokens when it runs. Until then it costs about 71 tokens; SKILL.md has 772 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~71
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 happier-dev/happier at commit 493820f, republished under its MIT licence (© happier-dev). 772 words, ~1,455 tokens.

Download SKILL.mdSave it as .claude/skills/decompose-gates/SKILL.md (or your agent's skills folder).
name
decompose-gates
description
Decompose a hard or multi-part task into independently checkable pieces with explicit verification gates and risk-weighted ordering. Use when planning corridor-sized work, writing lane briefs for subagents or Codex, or whenever a task is too large to verify as a whole.

Decompose With Gates

Turn a hard task into pieces that can each pass or fail on their own, ordered so the riskiest assumption is tested first. Full doctrine: docs/agent-craft.md §2–§3.

Procedure

  1. Split along verification boundaries, not implementation convenience. Each piece must have its own pass/fail check that does not depend on the other pieces being right. If checking B assumes A is correct, A+B is one piece, not two.
  2. State each piece as a falsifiable claim, not a task. "The watermark advances only after server ack" (checkable) — not "update watermark logic" (a task). Attach to each claim the concrete check that decides it: a test slice, a log observation, a live replay, a measurement.
  3. Name the risk spots before sequencing. Write the two or three "if I'm wrong anywhere, it's here" spots — silent failure modes, irreversible steps, boring mechanical stretches — and design a specific verification for each. Generic suite runs are uniform effort against non-uniform risk.
  4. Order by information yield. Test first the smallest shared assumption whose failure would invalidate repeated downstream units. This gates only dependent replication: keep independent work moving and expand the rolling window as soon as the assumption holds. Skip the ramp when prior evidence or a deterministic tool already proves the unit shape.
  5. Relay dependency context, not only order. State the upstream contract and evidence each piece consumes. Those assumptions are themselves claims to check; most integration failures live at the interfaces.
  6. Right-size. A piece owns a whole responsibility end to end: analysis, change, tests, validation. Too small to fail meaningfully is overhead — micro-slicing (one-boolean extractions) provably grew the god-files it was meant to shrink. Too big to check independently is not decomposed yet.
  7. Prefer consumed verticals over horizontal spines. The first implementation slice should connect a real entry point through its canonical owner to an observable outcome. Do not split protocol/schema/producer/consumer into weeks of dormant layers whose correctness can only be known after activation. When compatibility forces phases, each phase names its active reader/consumer and removal condition.
  8. Firewall live-path corrections. If gated or dormant work exposes a live dispatch, lifecycle, persistence, migration, or startup defect, handle that correction as its own complete vertical at the live owner. Do not partially activate the dormant design to fix the production path.

For compatibility-sensitive work, use .agents/skills/happier-compatibility and decompose the transition into independently falsifiable prepare/read, activate/write, migrate/backfill, mixed-version or rollback, and contract/removal claims only where those phases are reachable. Every such claim names its exact released/predecessor baseline and old/new producer-consumer direction; do not create empty phases for an additive or internal-only change.

Show full SKILL.md (339 more words)Show less

When pieces become lane briefs

  • Coordinate conceptual seams, overlapping edit hunks, generated outputs, and exclusive runtime resources; do not treat file dirtiness or a prior edit as ownership. Keep an advisory integration map for live seams/resources when useful. Lanes may layer compatible changes onto the same current file, but must not overwrite concurrent work or independently make incompatible decisions for the same seam.
  • For cross-program work, name the seam authority and each lane's Supersedes:, Extends:, or Consumes: relationship. A dependent lane consumes a typed contract; it does not repair the owning seam from the wrong program.
  • Every brief carries its gate (the falsifiable claim plus its check). Update durable state only when plan-gate readiness, dependency availability, blocker state, approved authority/contract, substantial review-boundary state, or the final verdict changes. Ordinary closed subchecks, landed fixes, RED/GREEN iterations, and lane-local validations belong in command output and the concise lane handoff.
  • Hard gates are measured, not merely reported. Re-measure decision-material claims through their deciding test, source inspection, runtime observation, or artifact check; do not create decorative count gates.
  • A lane brief should be a sufficient restart brief on its own: if the lane dies, its on-disk report plus the brief must let a fresh agent continue without the lost transcript.
  • Include exact paths/symbols, observed evidence, in-scope and out-of-scope surfaces, success criteria, required validation, expected output, and stop/fallback conditions. For compatibility lanes, include baseline tags/commits/artifacts and component roles.
  • Schedule formal independent review at the fewest substantial integrated boundaries needed by the approved plan, plus explicit user-requested or high-risk triggers. Every lane performs a compact author self-attack without a separate workspace, report, or reviewer. Advisory review may inspect moving work; boundary/ship verdicts reconcile current decision-material paths. See root AGENTS.md → "Adversarial review and handoff".

Output

A short plan listing: the pieces as claims, each with its deciding check; the named risk spots with their specific verifications; the ordering and why; the inter-piece assumptions.

Failure this prevents

The monolithic change where something works but you cannot say which part, and something fails but you cannot say where.

© happier-dev, 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 .agents/skills/decompose-gates of happier-dev/happier.

Open the folder on GitHubat commit 493820f

Compare with similar skills

Decompose Gates 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.

Decompose Gates compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Decompose Gates this skillhappier-dev/happier1.9k—~1.5kAutomated safety check: PassMIT
MCP Server Builderanthropics/skills180k62 repos~2.3kAutomated safety check: PassApache-2.0
Hook Development for Claude Code Pluginsanthropics/claude-plugins-official37k11 repos~4.1kAutomated safety check: NotesApache-2.0
Using Superpowersfarm-fe/farm5.6k34 repos~1.4kAutomated safety check: PassMIT
Executing Plans Inlineobra/superpowers296k2 repos~5.1kAutomated safety check: PassMIT
Claude Code Agent Developmentanthropics/claude-plugins-official37k8 repos~2.8kAutomated safety check: PassApache-2.0

Similar skills

  • MCP Server Builder

    anthropics/skills

    Official

    Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.

    180k GitHub starsUsed in 62 repos~2.3k tokens
    Agent WorkflowsAuto-check passed

  • Hook Development for Claude Code Plugins

    anthropics/claude-plugins-official

    Official

    Explains how to write Claude Code plugin hooks, both prompt-based checks and bash commands, for events such as PreToolUse, Stop and SessionStart.

    37k GitHub starsUsed in 11 repos~4.1k tokens
    Agent WorkflowsAuto-check: notes

  • Using Superpowers

    farm-fe/farm

    A skill your agent uses when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions

    5.6k GitHub starsUsed in 34 repos~1.4k tokens
    Agent WorkflowsAuto-check passed

  • Executing Plans Inline

    obra/superpowers

    Has the agent carry out an implementation plan itself, task by task in the current session, keeping a ledger, proving each step with a test and ending with one whole-branch review.

    296k GitHub starsUsed in 2 repos~5.1k tokens
    Agent WorkflowsAuto-check passed

  • Claude Code Agent Development

    anthropics/claude-plugins-official

    Official

    Explains how to write agents for Claude Code plugins: the markdown file with YAML frontmatter, trigger descriptions, model and color settings, and system prompt design.

    37k GitHub starsUsed in 8 repos~2.8k tokens
    Agent WorkflowsAuto-check passed

  • Skill Creator

    Azure/azqr

    Official

    Create new skills, modify and improve existing skills, and measure skill performance.

    794 GitHub starsUsed in 89 repos~8.2k tokens
    Agent WorkflowsAuto-check passed

More from happier-dev/happier

All 28 skills in this repo

  • Happier Review

    happier-dev/happier

    Conduct evidence-backed Happier code, plan-completeness, session, worktree, feature, commit, branch, PR, codebase, and release-readiness reviews with affected-corridor analysis, high-confidence…

    1.9k GitHub stars~4.5k tokensUpdated today
    Auto-check passed

  • Happier CI Stabilize

    happier-dev/happier

    Stabilize failing, flaky, slow, or repeatedly rerun Happier CI and nightlies by collecting all reachable failures from one exact attempt, correcting canonical causes in one batch, simplifying…

    1.9k GitHub stars~2.2k tokensUpdated today
    Auto-check passed

  • Happier Commit Worktree

    happier-dev/happier

    Reconnoiter, classify, validate, group, and commit a large or continuously changing Happier worktree as coherent, human-understandable commits while preserving concurrent work and excluding…

    1.9k GitHub stars~3.9k tokensUpdated today
    Auto-check passed

  • Happier Release

    happier-dev/happier

    Resolve Happier's private release authority and run an exact-SHA release or nightly through cheap admission, verified CI evidence, resumable immutable candidates, and terminal publication proof.

    1.9k GitHub stars~2.4k tokensUpdated today
    Auto-check passed

  • Happier Diagnose

    happier-dev/happier

    Diagnose and explain a Happier runtime, session, daemon, provider (Claude/Codex/OpenCode), authentication, or connectivity incident from logs, structured diagnostics, runtime state, and source…

    1.9k GitHub stars~2.1k tokensUpdated today
    Auto-check passed

  • Happier Implement

    happier-dev/happier

    Implement, change, build, fix, refactor, migrate, or apply accepted review findings in the Happier repositories with canonical-owner discovery, scope-preserving solution economy, TDD, efficient…

    1.9k GitHub stars~4.2k tokensUpdated today
    Auto-check passed

Categories

Questions about Decompose Gates

What does Decompose Gates do?

Decompose a hard or multi-part task into independently checkable pieces with explicit verification gates and risk-weighted ordering. Decompose Gates is an agent skill from happier-dev/happier. Decompose a hard or multi-part task into independently checkable pieces with explicit verification gates and risk-weighted ordering.

When should I use Decompose Gates?

Decompose Gates fits situations like: planning corridor-sized work; writing lane briefs for subagents; whenever a task is too large to verify as a whole.

How do I install Decompose Gates in Claude Code?

Run `npx skills add happier-dev/happier --skill decompose-gates -a claude-code`. Or copy the skill folder (.agents/skills/decompose-gates in happier-dev/happier) into .claude/skills/decompose-gates in your project. Claude Code loads it when a task matches its description.

How do I install Decompose Gates in Codex?

Run `npx skills add happier-dev/happier --skill decompose-gates -a codex`. Or copy the skill folder (.agents/skills/decompose-gates in happier-dev/happier) into .agents/skills/decompose-gates in your project. Codex loads it when a task matches its description.

Can I use Decompose Gates 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 happier-dev/happier --skill decompose-gates -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/decompose-gates, .gemini/skills/decompose-gates, .github/skills/decompose-gates and .opencode/skills/decompose-gates in your project.

What does Decompose Gates need to run?

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

Does Decompose Gates 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 Decompose Gates 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 Decompose Gates use?

Decompose Gates 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 Decompose Gates use?

About 1.5k tokens (SKILL.md is roughly 5.8k 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 Decompose Gates?

Skills that share tags, products or a category with Decompose Gates: MCP Server Builder (anthropics/skills, 180k stars), Hook Development for Claude Code Plugins (anthropics/claude-plugins-official, 37k stars), Using Superpowers (farm-fe/farm, 5.6k stars) and Executing Plans Inline (obra/superpowers, 296k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Decompose Gates?

happier-dev (a GitHub organization) maintains it in happier-dev/happier, which has 1,876 GitHub stars. The repository holds 28 skills in this directory. The repository was last updated on October 7, 2026.

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