agentleFS
CrystalPlatformsCrystalPlatforms/ADM-CLI/.claude/skills/dispatch/SKILL.md

dispatch

Skill1 starsChanged 6 months agoMITView on GitHub

Convert a PRD into independently-grabbable GitHub issues using vertical slices. Use when the user wants to create issues from a PRD, break down a PRD into tasks, or create GitHub issues from requirements.

40 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use edge-detection, odds-analysis and 8 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.
  • noahowshSkill

    edge-detection

    Comparing a tennis model's probability with the market: no-vig close, expected value at the best available price, closing line value, fractional Kelly sizing, and the checks that separate an estimated edge from noise. Use when the user has a probability and wants to know whether a price is better than fair, how large a stake is reasonable, or whether an edge is real. Requires a probability the user trusts. Do not use for fetching prices: see odds-explorer. Do not use for devig math alone: see odds-analysis. Do not use for historical testing: see backtesting.

    Also in 4 projects that use this

  • noahowshSkill

    odds-analysis

    Odds math for two-way tennis markets: American to implied probability, margin, devigging (multiplicative, power, Shin), no-vig fair odds, consensus across books, favorite-longshot bias, and expected value of a price. Use when the user asks what a price implies, how to remove the vig, what the true probability is, or how to compare books. Do not use for fetching or comparing live prices: see odds-explorer. Do not use for deciding a bet against a model: see edge-detection.

    Also in 4 projects that use this

  • agiprolabsSkill

    walk-forward-validation

    Walk-forward validation framework for trading strategies and ML models with time-series-aware splits, overfit detection, and regime-aware validation

    Also in 4 projects that use this

  • Yahmez3Skill

    backtesting

    Use when backtesting a trading strategy — evaluating a signal series against historical price data and computing performance metrics (Sharpe, Sortino, max drawdown, CAGR, win rate, expectancy). Triggers on "backtest this strategy", "what's the Sharpe on X", "run a walk-forward test", or "compare strategies A and B". Produces equity curves, trade logs, and tear sheets.

    Also in 4 projects that use this

  • ffsshhttiikkSkill

    feature-engineering

    Machine learning feature engineering

    Also in 4 projects that use this

  • varun29ankuSSkill

    orchestrate

    This skill should be used when the user asks to 'orchestrate a task', 'break down work into parallel agents', 'coordinate subtasks', 'run agents in parallel', or mentions 'multi-agent'. Decomposes complex tasks into tracked subtasks, dispatches parallel subagents, and coordinates until completion.

    Also in 4 projects that use this

  • +3 more from noahowsh

The file

We split this skill into the rules it gives an agent

8 rules. 0 are common, 6 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 38 edited versions we read keep these.

  • 6

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Ask the user for the PRD GitHub issue number (or URL).

    line 16
  2. Very specific:

    If the PRD is not already in your context window, fetch it with gh issue view <number> (with comments).

    line 18
  3. Very specific:

    If available, review ./plans/ for related plan files and any prior session decisions to ensure issues align with established architectural …

    line 22
  4. Distinctive:

    Should any slices be merged or split further?

    line 53
  5. Distinctive:

    Create issues in dependency order (blockers first) so you can reference real issue numbers in the "Blocked by" field.

    line 62
  6. Distinctive:

    Do NOT close or modify the parent PRD issue.

    line 64
  7. Distinctive:

    Before creating GitHub issues, verify:

    line 68
  8. Distinctive:

    If any check fails, inform the user and provide the fix command.

    line 73

“Common” is measured: kept by at least 6 in 10 of the 38 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Dispatch — PRD to Issues

Break a PRD into independently-grabbable GitHub issues using vertical slices (tracer bullets).

CLI tools — special case. If the PRD describes a command-line tool, suggest running /agent-cli in design mode before issue creation. Locking flags, output formats, and error model up front prevents rework across the dependency-ordered slices.

Process

1. Locate the PRD

Ask the user for the PRD GitHub issue number (or URL).

If the PRD is not already in your context window, fetch it with gh issue view <number> (with comments).

2. Review existing context (optional)

If available, review ./plans/ for related plan files and any prior session decisions to ensure issues align with established architectural choices.

3. Draft vertical slices

Break the PRD into tracer bullet issues. Each issue is a thin vertical slice that cuts through ALL integration layers end-to-end, NOT a horizontal slice of one layer. Follow the rules in vertical-slice-rules.md.

Slices may be 'HITL' or 'AFK'. HITL slices require human interaction, such as an architectural decision or a design review. AFK slices can be implemented and merged without human interaction. Prefer AFK over HITL where possible.

Agent-loopable AC test — applied to every issue before creation:

Could an AFK agent picking up this issue tomorrow tell, by itself, whether the work is done — without asking anyone?

If the answer is no, the acceptance criteria are too weak. Sharpen them until each AC reduces to a test, an observable artifact, or a runnable command. AFK issues with vague ACs become HITL issues by accident — the agent stalls on "is this what you wanted?" and the parallelism collapses.

HITL issues are allowed subjective ACs, but the issue must be explicitly marked HITL and the subjective gate named ("design review by @owner before merge"). Don't ship a subjective AC under an AFK label.

Cut what wasn't asked. Every slice traces to a user story in the PRD. If a draft issue includes work outside the PRD ("also refactor X while we're here"), drop it or file it as a separate issue. The downstream /tdd agent will implement exactly what the issue says — including the unscoped extra.

4. Quiz the user

Present the proposed breakdown as a numbered list. For each slice, show:

  • Title: short descriptive name
  • Type: HITL / AFK
  • Blocked by: which other slices (if any) must complete first
  • User stories covered: which user stories from the PRD this addresses

Ask the user:

  • Does the granularity feel right? (too coarse / too fine)
  • Are the dependency relationships correct?
  • Should any slices be merged or split further?
  • Are the correct slices marked as HITL and AFK?

Iterate until the user approves the breakdown.

5. Create the GitHub issues

For each approved slice, create a GitHub issue using gh issue create. Use the template in issue-template.md.

Create issues in dependency order (blockers first) so you can reference real issue numbers in the "Blocked by" field.

Do NOT close or modify the parent PRD issue.

Prerequisites

Before creating GitHub issues, verify:

  1. gh CLI is installed and authenticated (gh auth status)
  2. Current directory is a git repo with a GitHub remote
  3. User has write access to the repository

If any check fails, inform the user and provide the fix command.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.