agentleFS
Sign inStart free
clonable-edenclonable-eden/cekernel/skills/dispatch/SKILL.md

dispatch

Skill17 starsChanged 8 months agoMITView on GitHub

Batch-process open issues with the `ready` label — discover, triage, and delegate to the Orchestrator

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 9 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

  • SentrySkill

    spec

    Produce a verified spec — problem, desired outcome, and acceptance criteria — before building. Use when given a GitHub/Linear issue link, when starting from a fuzzy in-conversation idea, or asked to "figure out what to do" / "scope this" / "what should I build" — whenever the *what* isn't yet pinned down. Grills the ambiguities, checks the premise against the code, and produces acceptance criteria you sign off on — then hands to design-first.

    Also in 3 projects that use this

  • +3 more from noahowsh

The file

We split this skill into the rules it gives an agent

5 rules. 0 are common, 2 are distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 38 edited versions we read keep these.

  • 2

    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
  1. Very specific:

    No arguments required — by default, picks up all open issues with the ready label.

    line 13
  2. Distinctive:

    No label manipulation — pure filter, zero side effects

    line 32
  3. Very specific:

    Read skills/references/orchestrator-launch.md from the repository root ($(git rev-parse …

    line 36
  4. Distinctive:

    If no issues are found, report to the user and exit.

    line 45
  5. Very specific:

    Triage: read skills/references/triage.md from the same directory and follow the triage protocol for each discovered issue.

    line 47

“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

Discovers open issues labeled ready, triages them, and delegates to the Orchestrator agent for parallel processing.

Usage

No arguments required — by default, picks up all open issues with the ready label.

Optional flags:

  • --yes, -y — Skip the user confirmation step. Required for non-interactive execution (cron, at).
  • --env <profile> — Env profile (default: default). Available: default, headless, tmux, wezterm, or any custom profile in .cekernel/envs/.
  • --label <label> — Override the target label (default: ready).
/dispatch
/dispatch -y --env headless --label sprint-3

Note: In plugin mode, /cekernel:dispatch also works.

Idempotency

  • A merged Worker PR closes its issue via closes #N
  • Discovery uses --state open, so closed issues are excluded on the next run
  • No label manipulation — pure filter, zero side effects

Workflow

Read skills/references/orchestrator-launch.md from the repository root ($(git rev-parse --show-toplevel)/skills/references/orchestrator-launch.md; if the Read fails, resolve it via ${CLAUDE_SKILL_DIR}/../references/orchestrator-launch.md) and follow the launch protocol with these skill-specific policies:

  1. Step A (agent names + script path): as written.

  2. Discover issues:

    gh issue list --label <label> --state open --json number,title --jq '.[] | "\(.number)\t\(.title)"'

    If no issues are found, report to the user and exit.

  3. Step B (lock filter): remove locked issues from the candidate list before triage; report skipped issues.
  4. Triage: read skills/references/triage.md from the same directory and follow the triage protocol for each discovered issue.
  5. Confirm with user: skip if --yes/-y. Otherwise present the triaged issue list and wait for confirmation; if the user declines, exit without action.

  6. Step C (concurrency guard) — over-limit policy: stop dispatching (do NOT launch; remaining issues are left for the next run), notify via desktop notification, report which issues were dispatched and which deferred, then exit:

    source "${CEKERNEL_SCRIPTS}/shared/desktop-notify.sh"
desktop_notify "cekernel: dispatch stopped" "Orchestrator limit reached (${CURRENT_ORCH}/${MAX_ORCH}). Remaining issues deferred."
  7. Step D (session init): as written.
  8. Step E (prompt + launch): as written.

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.

Check your setup, free