Skip to content

notque/vexjoy-agent / skills/process/workflow

workflow

Verified

Structured work: multi-phase tasks, feature builds, planning, objective loops, hill climbing.

FileKindSize
SKILL.mdskill md13.2 KB
references/adr-template.mdmarkdown9.4 KB
references/agent-upgrade.mdmarkdown12.5 KB
references/article-evaluation-pipeline.mdmarkdown8.9 KB
references/article-evaluation-pipeline/references/report-template.mdmarkdown2.5 KB
references/article-evaluation-pipeline/references/wabi-sabi-classification.mdmarkdown2.4 KB
references/auto-pipeline.mdmarkdown12.5 KB
references/auto-pipeline/references/pipeline-catalog.jsonconfig15.0 KB
references/auto-pipeline/references/pipeline-catalog.mdmarkdown4.3 KB
references/build_dag.pyscript12.5 KB
references/chain-composer.mdmarkdown20.4 KB
references/chain-composer/references/canonical-chains.mdmarkdown13.9 KB
references/comprehensive-review-workflow.jsscript19.3 KB
references/comprehensive-review.mdmarkdown27.8 KB
references/comprehensive-review/references/output-templates.mdmarkdown10.6 KB
references/comprehensive-review/references/wave-0-per-package.mdmarkdown5.6 KB
references/comprehensive-review/references/wave-1-foundation.mdmarkdown10.4 KB
references/comprehensive-review/references/wave-2-deep-dive.mdmarkdown7.3 KB
references/comprehensive-review/references/wave-3-adversarial.mdmarkdown7.4 KB
references/dag-compatibility-matrix.mdmarkdown13.0 KB
references/dag-composition-patterns.mdmarkdown5.0 KB
references/dag-orchestration-advanced.mdmarkdown6.3 KB
references/dag-orchestration-examples.mdmarkdown11.4 KB
references/dag-skill-patterns.mdmarkdown12.5 KB
references/de-ai-pipeline.jsscript14.6 KB
references/de-ai-pipeline.mdmarkdown6.3 KB
references/discover_skills.pyscript12.1 KB
references/do-perspectives.mdmarkdown11.5 KB
references/doc-pipeline.mdmarkdown9.2 KB
references/domain-research.mdmarkdown32.8 KB
references/domain-research/references/task-type-guide.mdmarkdown11.4 KB
references/explore-pipeline.jsscript18.6 KB
references/explore-pipeline.mdmarkdown15.0 KB
references/fan-out-workflow.jsscript9.7 KB
references/fan-out-workflow.pyscript10.4 KB
references/feedback-loop-construction.mdmarkdown14.3 KB
references/fl-design.mdmarkdown9.6 KB
references/fl-error-handling.mdmarkdown8.5 KB
references/fl-implement.mdmarkdown7.6 KB
references/fl-pipeline.mdmarkdown6.0 KB
references/fl-plan.mdmarkdown11.0 KB
references/fl-release.mdmarkdown3.8 KB
references/fl-shared.mdmarkdown3.6 KB
references/fl-validate.mdmarkdown4.5 KB
references/github-profile-rules.mdmarkdown10.5 KB
references/github-profile-rules/references/rule-categories.mdmarkdown6.5 KB
references/hc-SPEC.mdmarkdown3.3 KB
references/hc-domain-playbooks.mdmarkdown15.4 KB
references/hc-ledger.mdmarkdown3.3 KB
references/hc-profiling-tools.mdmarkdown3.7 KB
references/hill-climb.mdmarkdown9.3 KB
references/hook-development-pipeline.mdmarkdown12.9 KB
references/mcp-pipeline-builder.mdmarkdown16.3 KB
references/mcp-pipeline-builder/references/analysis-checklist.mdmarkdown6.2 KB
references/mcp-pipeline-builder/references/design-rules.mdmarkdown7.1 KB
references/mcp-pipeline-builder/references/evaluation-guide.mdmarkdown7.6 KB
references/mcp-pipeline-builder/references/python-scaffold-template.mdmarkdown9.5 KB
references/mcp-pipeline-builder/references/ts-scaffold-template.mdmarkdown1.6 KB
references/mcp-pipeline-builder/scripts/assemble-scaffold.pyscript6.3 KB
references/mcp-pipeline-builder/scripts/register_mcp.pyscript6.9 KB
references/mcp-pipeline-builder/templates/client-cli.ts.tmplother682 B
references/mcp-pipeline-builder/templates/client-http.ts.tmplother1.4 KB
references/mcp-pipeline-builder/templates/index.ts.tmplother1.1 KB
references/mcp-pipeline-builder/templates/package.json.tmplother477 B
references/mcp-pipeline-builder/templates/readme.md.tmplother1.1 KB
references/mcp-pipeline-builder/templates/tools.ts.tmplother3.0 KB
references/mcp-pipeline-builder/templates/ts-scaffold.tmplother556 B
references/mcp-pipeline-builder/templates/tsconfig.json.tmplother408 B
references/ol-SPEC.mdmarkdown2.4 KB
references/ol-state-file.mdmarkdown2.9 KB
references/pipeline-index.jsonconfig23.9 KB
references/pipeline-orchestrator.mdmarkdown15.3 KB
references/pipeline-orchestrator/orchestration-patterns.mdmarkdown8.1 KB
references/pipeline-orchestrator/preferred-patterns.mdmarkdown4.6 KB
references/pipeline-retro.mdmarkdown19.0 KB
references/pipeline-scaffolder.mdmarkdown22.4 KB
references/pipeline-scaffolder/references/architecture-rules.mdmarkdown18.9 KB
references/pipeline-scaffolder/references/generated-skill-template.mdmarkdown1.9 KB
references/pipeline-scaffolder/references/pipeline-spec-format.mdmarkdown36.8 KB
references/pipeline-scaffolder/references/step-menu.mdmarkdown21.5 KB
references/pipeline-scaffolder/scripts/assemble-skill.pyscript6.3 KB
references/pipeline-scaffolder/templates/phases/decision-planning.md.tmplother1.2 KB
references/pipeline-scaffolder/templates/phases/domain-extension.md.tmplother1.5 KB
references/pipeline-scaffolder/templates/phases/generation.md.tmplother427 B
references/pipeline-scaffolder/templates/phases/git-release.md.tmplother1.1 KB
references/pipeline-scaffolder/templates/phases/interaction.md.tmplother965 B
references/pipeline-scaffolder/templates/phases/learning-retro.md.tmplother1.5 KB
references/pipeline-scaffolder/templates/phases/observation.md.tmplother1.3 KB
references/pipeline-scaffolder/templates/phases/research-gathering.md.tmplother1.2 KB
references/pipeline-scaffolder/templates/phases/review.md.tmplother930 B
references/pipeline-scaffolder/templates/phases/safety-guarding.md.tmplother1.7 KB
references/pipeline-scaffolder/templates/phases/structuring.md.tmplother361 B
references/pipeline-scaffolder/templates/phases/synthesis-reporting.md.tmplother1.9 KB
references/pipeline-scaffolder/templates/phases/validation.md.tmplother1.1 KB
references/pipeline-scaffolder/templates/skill-template.md.tmplother12.0 KB
references/pipeline-test-runner.mdmarkdown16.7 KB
references/pl-ambiguity-triage.mdmarkdown2.7 KB
references/pl-check-dimensions.mdmarkdown7.4 KB
references/pl-check-errors.mdmarkdown824 B
references/pl-check-verdict-format.mdmarkdown3.2 KB
references/pl-check.mdmarkdown6.5 KB
references/pl-context-boundary.mdmarkdown1.6 KB
references/pl-depth-first-interview.mdmarkdown11.6 KB
references/pl-empirical-prototype.mdmarkdown825 B
references/pl-executor-ready-plan-template.mdmarkdown7.7 KB
references/pl-human-source-elicitation.mdmarkdown1.5 KB
references/pl-manage.mdmarkdown5.1 KB
references/pl-pause-confirm-and-errors.mdmarkdown2.1 KB
references/pl-pause-extract-decisions.mdmarkdown3.0 KB
references/pl-pause-gather-steps.mdmarkdown2.3 KB
references/pl-pause-synthesize-fields.mdmarkdown2.3 KB
references/pl-pause-write-templates.mdmarkdown5.3 KB
references/pl-pause.mdmarkdown6.5 KB
references/pl-plan-files.mdmarkdown8.4 KB
references/pl-pre-plan.mdmarkdown11.6 KB
references/pl-resume.mdmarkdown12.3 KB
references/pl-spec.mdmarkdown5.2 KB
references/pr-fix-loop.mdmarkdown10.3 KB
references/pr-fix-loop/references/message-formats.mdmarkdown1.6 KB
references/pr-fix-loop/references/publish.mdmarkdown5.4 KB
references/pr-fix-loop/references/review-checklist.mdmarkdown3.4 KB
references/pr-pipeline/references/pr-templates.mdmarkdown5.4 KB
references/pr-pipeline/references/preflight-checklist.mdmarkdown2.8 KB
references/pr-pipeline/references/retro-adr-phases.mdmarkdown2.7 KB
references/pr-pipeline/references/review-fix-loop.mdmarkdown2.0 KB
references/project-coordinator.mdmarkdown6.5 KB
references/project-coordinator/agent-capability-map.mdmarkdown5.4 KB
references/project-coordinator/communication-protocols.mdmarkdown4.5 KB
references/project-coordinator/coordination-playbook.mdmarkdown3.7 KB
references/project-coordinator/death-loop-prevention.mdmarkdown3.6 KB
references/project-coordinator/error-catalog.mdmarkdown2.7 KB
references/project-coordinator/parallel-execution-patterns.mdmarkdown2.8 KB
references/project-coordinator/preferred-patterns.mdmarkdown5.9 KB
references/project-coordinator/todowrite-integration.mdmarkdown5.6 KB
references/research-pipeline.jsscript15.2 KB
references/skill-creation-pipeline.mdmarkdown17.1 KB
references/system-upgrade.mdmarkdown12.8 KB
references/systematic-debugging.mdmarkdown11.0 KB
references/systematic-refactoring.mdmarkdown11.4 KB
references/toolkit-improvement.jsscript39.0 KB
references/toolkit-improvement.mdmarkdown20.5 KB
references/toolkit-improvement/references/adr-template.mdmarkdown10.5 KB
references/toolkit-improvement/references/agent-roster.mdmarkdown15.8 KB
references/workflow-helpers.jsscript12.1 KB
references/workflow-orchestrator.mdmarkdown20.8 KB
references/workflow-orchestrator/references/plan-template.mdmarkdown1.3 KB
references/workflow-orchestrator/references/task-patterns.mdmarkdown23.3 KB
references/workflow-orchestrator/scripts/assemble-plan.pyscript6.9 KB
references/workflow-orchestrator/scripts/validate.pyscript14.4 KB
references/workflow-orchestrator/templates/plan-template.json.tmplother904 B

references/fan-out-workflow.py

View on GitHub
"""Antigravity CLI (agy) Python run_workflow template for parallel fan-out and synthesis.

Counterpart to skills/process/workflow/references/fan-out-workflow.js for the
Antigravity `run_workflow` tool (Python async orchestration).

Runtime globals provided by Antigravity's `run_workflow` harness:
  - phase(title: str) -> None
  - await agent(prompt: str, *, schema: dict | type | None = None,
                role: str | None = None, type_name: str = "self",
                workspace: str = "inherit", model: str = "inherit")
  - await parallel(coroutines_or_callables)
  - trajectory(agent_result) -> list[dict]

Every worker prompt begins with a line-anchored `[do-route]` marker so
`hooks/agy-hook-adapter.py` + `hooks/routing-decision-recorder.py` record one
routing decision row per dispatched worker.

The repo's specialist agents are retired (plans/009). Each roster entry is a
general-purpose worker whose skills carry the domain: `{"skills": [...],
"lens": ..., "workspace": ..., "model": ...}`. The Antigravity `type_name`
defaults to `<primary-skill>-worker`, the persona
`scripts/build-subagent-spec.py --skill <primary-skill>` defines. A legacy
`agentType` other than general-purpose is coerced to general-purpose and the
marker carries `fallback=invalid-agent:<name>`, as `build-dispatch.py` does.
"""

from __future__ import annotations

import json
import re
from typing import Any

MAX_ROSTER_SIZE = 10
WORKER_AGENT = "general-purpose"
_READ_ONLY_SKILLS = frozenset({"review", "security", "research", "assessment", "code-quality"})
_NAME_RE = re.compile(r"^[a-z0-9][a-z0-9-]*$")

FINDING_SCHEMA: dict[str, Any] = {
    "type": "object",
    "required": ["title"],
    "properties": {
        "title": {"type": "string"},
        "location": {"type": "string"},
        "severity": {"type": "string", "enum": ["critical", "high", "medium", "low", "info"]},
        "detail": {"type": "string"},
    },
}

WORKER_SCHEMA: dict[str, Any] = {
    "type": "object",
    "required": ["verdict", "summary"],
    "properties": {
        "verdict": {"type": "string", "enum": ["PASS", "CONCERN", "BLOCK", "INFO"]},
        "summary": {"type": "string", "minLength": 1},
        "findings": {"type": "array", "items": FINDING_SCHEMA},
        "lens": {"type": "string"},
    },
}

SYNTH_SCHEMA: dict[str, Any] = {
    "type": "object",
    "required": ["verdict", "summary"],
    "properties": {
        "verdict": {"type": "string", "enum": ["PASS", "CONCERN", "BLOCK", "INFO"]},
        "summary": {"type": "string", "minLength": 1},
        "key_findings": {"type": "array", "items": FINDING_SCHEMA},
        "recommendations": {"type": "array", "items": {"type": "string"}},
    },
}

MANDATORY_INJECTIONS = (
    "\n\nBefore starting work, consult the Reference Loading Table in each loaded skill's SKILL.md "
    "and read the references that match this task.\n\n"
    "Deliver the finished product. Ship the complete thing.\n\n"
    "Follow the Dense-Complete Writing rules in `skills/shared-patterns/base-instructions.md`.\n\n"
    "Follow its Google Developer Documentation Style rules and precedence.\n\n"
    "Before starting work, also load `skills/shared-patterns/base-instructions.md` for universal operational rules.\n\n"
    "End your reply with this exact final line, nothing after it: "
    "`route-fit: <ok|wrong-skill|needs-coordinator|underspecified>` — "
    "your honest read of whether this skill fits the task."
)


def validate_name(value: str, label: str) -> str:
    """Validate an agent or skill identifier against [a-z0-9][a-z0-9-]*."""
    cleaned = str(value or "").strip().lower()
    if not cleaned or not _NAME_RE.match(cleaned):
        raise ValueError(f"Invalid {label}: {value!r}")
    return cleaned


def default_workspace_for_skill(skill: str) -> str:
    """Default workspace to 'inherit' for review and research skills, and 'branch' for implementers."""
    cleaned = skill.strip().lower()
    if cleaned in _READ_ONLY_SKILLS or "review" in cleaned or "research" in cleaned:
        return "inherit"
    return "branch"


def validate_roster(roster: list[dict[str, Any]]) -> list[dict[str, Any]]:
    """Validate the caller-supplied worker roster (1..MAX_ROSTER_SIZE)."""
    if not isinstance(roster, list) or not (1 <= len(roster) <= MAX_ROSTER_SIZE):
        raise ValueError(f"roster must be a non-empty list of at most {MAX_ROSTER_SIZE} entries")
    validated: list[dict[str, Any]] = []
    for i, entry in enumerate(roster):
        raw_skills = entry.get("skills") or []
        if not isinstance(raw_skills, list) or not raw_skills:
            raise ValueError(f"roster entry {i} requires at least one skill")
        skills = [validate_name(s, "skill") for s in raw_skills]
        legacy = str(entry.get("agentType") or "").strip().lower()
        fallback = f"invalid-agent:{validate_name(legacy, 'agentType')}" if legacy and legacy != WORKER_AGENT else ""
        ws = str(entry.get("workspace") or "").strip()
        if not ws:
            ws = default_workspace_for_skill(skills[0])
        type_name = str(entry.get("type_name") or f"{skills[0]}-worker").strip()
        validated.append(
            {
                "agentType": WORKER_AGENT,
                "fallback": fallback,
                "type_name": type_name,
                "skills": skills,
                "lens": str(entry.get("lens") or "").strip(),
                "workspace": ws,
                "model": str(entry.get("model") or "inherit").strip(),
            }
        )
    return validated


def build_worker_prompt(entry: dict[str, Any], scope: dict[str, Any], complexity: str = "complex") -> str:
    """Build a worker prompt with a line-start [do-route] marker and mandatory injections."""
    primary_skill = entry["skills"][0]
    stack = entry["skills"][1:]
    stack_token = f" stack={{{','.join(stack)}}}" if stack else ""
    model_token = entry.get("model") or "gemini-4-argon"
    fallback_token = f" fallback={entry['fallback']}" if entry.get("fallback") else ""
    marker = (
        f"[do-route] agent={entry['agentType']} skill={primary_skill} "
        f"complexity={complexity} model={model_token} health=-{stack_token}{fallback_token}"
    )
    skill_calls = "\n".join(
        f"Read and follow ~/.gemini/skills/{s}/SKILL.md before starting work." for s in entry["skills"]
    )
    lens = f"Apply this lens: {entry['lens']}." if entry.get("lens") else "Apply the skill's lens."
    return (
        f"{marker}\n\n"
        f"You are a `{entry['agentType']}` worker for the `{primary_skill}` skill. {lens}\n"
        f"{skill_calls}\n\n"
        f"## Task Specification (auto-extracted)\n\n"
        f"**Request (verbatim):** {scope.get('request_verbatim', scope.get('intent', 'Execute assigned scope'))}\n"
        f"**Intent:** {scope.get('intent', 'Complete the analysis and implementation within the lens.')}\n"
        f"**Acceptance criteria:** Return schema-valid output with concrete file:line evidence.\n"
        f"**Relevant file locations:** {scope.get('files', '.')}\n"
        f"**Decisions:** {scope.get('decisions', 'Follow repository conventions.')}\n"
        f"**Prior results:** {scope.get('prior_results', 'None')}\n\n"
        f"## Repo state\n\n"
        f"Work this scope:\n{json.dumps(scope, indent=2)}"
        f"{MANDATORY_INJECTIONS}"
    )


async def run_fan_out_workflow(
    *,
    scope: dict[str, Any],
    roster: list[dict[str, Any]],
    synth_agent_type: str = "general-purpose",
    tier: int | None = None,
    phase_fn: Any = None,
    agent_fn: Any = None,
    parallel_fn: Any = None,
    trajectory_fn: Any = None,
) -> dict[str, Any]:
    """Execute parallel worker fan-out followed by typed in-memory synthesis."""
    workers = validate_roster(roster)
    synthesizer = validate_name(synth_agent_type, "synth_agent_type")

    _phase = phase_fn or globals().get("phase")
    _agent = agent_fn or globals().get("agent")
    _parallel = parallel_fn or globals().get("parallel")
    _trajectory = trajectory_fn or globals().get("trajectory")

    if callable(_phase):
        _phase("fan-out")

    async def _invoke_worker(w: dict[str, Any]) -> Any:
        prompt = build_worker_prompt(w, scope)
        try:
            return await _agent(
                prompt,
                schema=WORKER_SCHEMA,
                role=f"{w['skills'][0]} worker ({w['lens'] or w['skills'][0]})",
                type_name=w.get("type_name") or "self",
                workspace=w.get("workspace") or default_workspace_for_skill(w["skills"][0]),
                model=w.get("model", "inherit"),
            )
        except Exception as exc:
            return {
                "verdict": "BLOCK",
                "summary": f"Worker {w['type_name']} execution failed: {exc}",
                "findings": [
                    {
                        "title": f"Worker execution failure ({w['type_name']})",
                        "location": "run_workflow",
                        "severity": "critical",
                        "detail": str(exc),
                    }
                ],
                "lens": w.get("lens", ""),
                "error": str(exc),
            }

    if callable(_parallel):
        raw_results = await _parallel([_invoke_worker(w) for w in workers])
    else:
        raw_results = [await _invoke_worker(w) for w in workers]

    results = [r for r in raw_results if r is not None]
    trajectories = []
    if callable(_trajectory):
        for r in results:
            try:
                t = _trajectory(r)
                if t is not None:
                    trajectories.append(t)
            except Exception:
                pass

    if callable(_phase):
        _phase("synthesize")

    synthesis = None
    if results and callable(_agent):
        synth_prompt = (
            f"You are `{synthesizer}`. Synthesize these {len(results)} typed worker results "
            f"into one verdict + summary. Merge overlapping findings, preserve the highest severity, "
            f"and provide actionable recommendations.\n\n"
            f"Typed worker results:\n{json.dumps(results, indent=2)}"
            f"{MANDATORY_INJECTIONS}"
        )
        synthesis = await _agent(
            synth_prompt,
            schema=SYNTH_SCHEMA,
            role=f"Synthesizer ({synthesizer})",
            type_name="self",
            workspace="inherit",
            model="inherit",
        )

    return {
        "tier": tier,
        "workers_ran": len(results),
        "roster": workers,
        "trajectory_steps": [len(t) for t in trajectories if isinstance(t, list)],
        "synthesis": synthesis,
    }
planning-and-task-breakdownaddyosmani/agent-skillsBreaks work into ordered tasks. Use when you have a spec or clear requirements and need to break work into implementable tasks. Use when a task feels too large to start, when you need to estimate scope, or when parallel work is possible.Stars: 119kUpdated Claude CodeCodexVerifiedInstall
screenpipethedotmack/claude-memSearch screen and audio history recorded by Screenpipe and optionally save selected context into claude-mem. Use when the user asks to recall desktop activity, a meeting, or something seen in another app through Screenpipe.Stars: 118kUpdated Claude CodeCodexVerifiedInstall
contact-widgetnexu-io/open-designSelf-contained floating chat widget with welcome screen, social links, meeting button, and message input. Single HTML file, zero dependencies.Stars: 108kUpdated Claude CodeCodexVerifiedInstall
meeting-notesnexu-io/open-designMeeting notes page — title bar with attendees, agenda checklist, decisions block, action items table with owners + dates, and a "next meeting" footer. Use when the brief mentions "meeting notes", "minutes", "1:1 notes", "all-hands recap", or "会议纪要".Stars: 108kUpdated Claude CodeCodexVerifiedInstall