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/research-pipeline.js

View on GitHub
// research-pipeline.js
//
// Native dynamic-Workflow variant of the formal research pipeline. The markdown
// flow at ./research-pipeline.md remains the cross-harness floor; this script is
// the deterministic-runtime FAST-PATH for Claude Code (+Factory) when the native
// Workflow tool is present. It mirrors the prose GATHER -> SYNTHESIZE -> VALIDATE
// -> DELIVER agent flow, replacing the research/{topic}/*.md disk round-trips
// with schema-validated typed agent() returns and a real parallel() barrier for
// the mandatory multi-agent gather.
//
// The prose pipeline MANDATES a minimum of 3 parallel research agents (sequential
// research is forbidden — A/B-validated). This workflow honors that as a FIXED
// 3-agent GATHER barrier of general-purpose workers that load the
// research-subagent-executor reference (the
// static-roster shape, like comprehensive-review-workflow.js Wave 1), then runs a
// dynamic SYNTHESIZE/VALIDATE/DELIVER tail through a worker that loads the
// research-coordinator reference (the prose pipeline's owning role). The prose SCOPE phase is a
// deterministic decision step (angle + depth selection from a fixed table), so it
// runs in-body before the barrier — no LLM round-trip (PHILOSOPHY: everything
// deterministic should be).
//
// Runtime contract (see ./comprehensive-review-workflow.js for the canonical
// description of the native primitives): meta is a pure object literal parsed
// before the body; parallel(thunks) is a hard barrier (failed slot -> null);
// agent({prompt, schema, model, agentType}) returns a typed object; budget.
// remaining() bounds the tail. No Date.now()/Math.random()/new Date().

import {
  mandatoryInjections,
  modelFor,
  referenceDirective,
  skillDirectives,
  validateModelOverride,
} from "./workflow-helpers.js";

export const meta = {
  name: "research-pipeline",
  description:
    "Formal research pipeline as a deterministic native Workflow: a deterministic scope step then GATHER -> SYNTHESIZE -> VALIDATE -> DELIVER. GATHER is a mandatory parallel barrier of >=3 general-purpose workers that load the research-subagent-executor reference (distinct angles, no shared file), each attaching its full skill stack (one exact Skill-tool call per skill) plus the /do mandatory injections; a worker loading the research-coordinator reference then synthesizes the typed findings in-memory, runs a source-quality VALIDATE gate, and DELIVERs the report. Mirrors research-pipeline.md; that markdown flow stays the cross-harness floor.",
  // --- Conformance contract (pure literal — no calls/variables; see
  //     scripts/validate-workflow-conformance.py + adr/native-fast-path-portable-floor.md
  //     Stage 3). STATIC validation pins the phases + the FIXED 3-agent GATHER
  //     barrier (the parallel-agents mandate, countable). DYNAMIC validation
  //     records the real dispatch trace and asserts SHAPE + SKILLS, NOT count,
  //     where dynamic:true. name + description stay BEFORE this nested object so
  //     the non-greedy meta-name parser in workflow-registry.py still resolves
  //     meta.name.
  contract: {
    // Phase titles entered at runtime via enterPhase(). GATHER (the barrier) is
    // the first entered phase; the deterministic scope step precedes it in-body.
    phases: ["gather", "synthesize", "validate", "deliver"],
    // GATHER is a FIXED barrier: 3 general-purpose research workers on every run
    // (the minimum-3 mandate from the prose pipeline). Each carries a `skills` LIST
    // (the full stack attached via one exact Skill-tool call per element). Distinct angles are a
    // RUNTIME property of the prompt, not the roster shape, so the static roster is
    // three identical-type entries (the gate pins the type + skills + count).
    roster: [
      { agentType: "general-purpose", skills: ["research", "testing"] },
      { agentType: "general-purpose", skills: ["research", "testing"] },
      { agentType: "general-purpose", skills: ["research", "testing"] },
    ],
    // The GATHER barrier dispatches at least the fixed 3 on every run (static).
    agents: { static: 3, dynamic: false },
    // SYNTHESIZE/VALIDATE/DELIVER are single coordinator passes, and GATHER can
    // scale ABOVE 3 angles for deeper requests (depth setting) — the count beyond
    // the fixed-3 floor is data-driven. Honest limit: the gate asserts SHAPE +
    // SKILLS for the tail, not COUNT.
    dynamic: true,
  },
};

// Map each dispatched agent to the FULL skill stack it invokes by name (one exact
// Skill-tool call per element). research-subagent-executor runs the research methodology
// and earns the source-quality verification gate; the coordinator synthesizes,
// validates, and delivers with the same stack. The literal skill names live in
// these `skills: [...]` arrays so the conformance gate resolves them; the body
// emits the directives by delegating each entry's list to skillDirectives().
const AGENT_SKILLS = {
  "research-subagent-executor": ["research", "testing"],
  "research-coordinator": ["research", "testing"],
};

// Repo agents are retired (plan 009). Gather workers and the coordinator are
// fresh general-purpose agents; each takes its role from a research-skill
// reference (referenceDirective).
const ROLE_REFS = {
  "research-subagent-executor": { skill: "research", file: "research-subagent-executor.md" },
  "research-coordinator": { skill: "research", file: "research-coordinator.md" },
};

// The mandated minimum gather size; a deeper request scales angles ABOVE this
// floor (the prose depth setting), never below it.
const MIN_GATHER_AGENTS = 3;
const COORDINATOR_ROLE = "research-coordinator";
const WORKER_AGENT = "general-purpose";

// Default research angles (mirrors the prose angle table). One distinct angle per
// gather agent; deeper depth adds more from the tail of this list.
const DEFAULT_ANGLES = [
  "current-state",
  "tradeoffs",
  "expert-opinions",
  "alternatives",
  "technical-details",
];

// --- Schemas (mirror the STYLE of comprehensive-review-workflow.js) -----------

// One angle's raw research output. Findings carry an evidence-strength note so
// SYNTHESIZE can rate consensus vs single-source (the prose Strong/Moderate/Weak
// gate). Mirrors the raw-{angle}.md structure as a typed object.
const CLAIM_SCHEMA = {
  type: "object",
  required: ["claim", "evidence"],
  properties: {
    claim: { type: "string" },
    evidence: { type: "string", enum: ["strong", "moderate", "weak"] },
    source: { type: "string" },
  },
};

const RAW_RESEARCH_SCHEMA = {
  type: "object",
  required: ["angle", "claims"],
  properties: {
    angle: { type: "string" },
    claims: { type: "array", items: CLAIM_SCHEMA },
    gaps: { type: "array", items: { type: "string" } },
    sources: { type: "array", items: { type: "string" } },
  },
};

// SYNTHESIZE output: consensus findings, contradictions, open gaps — the prose
// synthesis.md as a typed object.
const SYNTHESIS_SCHEMA = {
  type: "object",
  required: ["findings"],
  properties: {
    findings: {
      type: "array",
      items: {
        type: "object",
        required: ["title", "evidence_quality"],
        properties: {
          title: { type: "string" },
          evidence_quality: { type: "string", enum: ["strong", "moderate", "weak"] },
          summary: { type: "string" },
        },
      },
    },
    contradictions: { type: "array", items: { type: "string" } },
    open_gaps: { type: "array", items: { type: "string" } },
  },
};

// VALIDATE output: the prose Quality Assessment + research verdict gate.
const VALIDATION_SCHEMA = {
  type: "object",
  required: ["verdict"],
  properties: {
    verdict: { type: "string", enum: ["sufficient", "partial", "insufficient"] },
    coverage: { type: "string" },
    bias_flags: { type: "array", items: { type: "string" } },
    flagged_weak_findings: { type: "array", items: { type: "string" } },
  },
};

// DELIVER output: the final report descriptor (the prose report.md).
const REPORT_SCHEMA = {
  type: "object",
  required: ["executive_summary"],
  properties: {
    executive_summary: { type: "array", items: { type: "string" } },
    detailed_findings: { type: "string" },
    sources: { type: "array", items: { type: "string" } },
    limitations: { type: "array", items: { type: "string" } },
  },
};

// --- Helpers ------------------------------------------------------------------

// Defensive phase marker: the native runtime guarantees agent/parallel/budget,
// but does NOT document a phase() global. Guard the call so the real runtime
// never throws if phase is absent, while the conformance harness's mock records
// the entered phase. Phase titles match meta.contract.phases.
function enterPhase(title) {
  if (typeof phase === "function") {
    phase(title);
  }
}

// Build one gather agent's prompt for its assigned angle. skillDirectives emits
// one exact Skill-tool call per element of the research-subagent-executor skill stack
// (resolves path-independent inside a native Workflow agent() dispatch).
// mandatoryInjections() embeds the /do completeness/density/base-instructions/
// reference-loading block so a workflow agent gets the same context as a direct
// /do dispatch. Each agent gets a DISTINCT angle and writes its own typed result
// (no shared file), mirroring the prose raw-{angle}.md isolation that preserves
// distinct perspectives.
function gatherPrompt(angle, scope) {
  return (
    `You are the "${angle}" research worker.` +
    skillDirectives(AGENT_SKILLS["research-subagent-executor"]) +
    referenceDirective(ROLE_REFS["research-subagent-executor"]) +
    `\nYour angle: investigate the "${angle}" dimension of this research scope:\n` +
    `${JSON.stringify(scope)}\n` +
    `Return ONLY findings within your angle. Rate each claim's evidence strength ` +
    `(strong|moderate|weak); "strong" requires specific independent sources, not ` +
    `just agreement. List the gaps you could not fill and the sources you used. ` +
    `Stay within your angle — the coordinator synthesizes across angles.` +
    mandatoryInjections()
  );
}

// Build a coordinator prompt (SYNTHESIZE/VALIDATE/DELIVER). Same skill stack +
// mandatory injections as a direct /do dispatch of the coordinator.
function coordinatorPrompt(task, payload) {
  return (
    task +
    skillDirectives(AGENT_SKILLS[COORDINATOR_ROLE]) +
    referenceDirective(ROLE_REFS[COORDINATOR_ROLE]) +
    `\n${JSON.stringify(payload)}` +
    mandatoryInjections()
  );
}

// Build the angle list for this run: the fixed-3 floor (quick/standard), scaled
// up only for `deep` (the prose depth setting allows 3-5 angles). Deterministic —
// no LLM round-trip needed to scope. The default/standard path dispatches exactly
// the mandated 3 (matching the static contract roster); `deep` scales above it
// (honestly covered by contract.dynamic:true).
function anglesForDepth(depth) {
  const count = depth === "deep" ? 5 : MIN_GATHER_AGENTS;
  return DEFAULT_ANGLES.slice(0, count);
}

// --- Workflow body ------------------------------------------------------------
//
// run({scope, tier, depth, modelOverride}):
//   - scope: the research descriptor (primary question + sub-questions + source
//     types). Passed to every gather agent and into synthesis.
//   - tier: right-size tier (carried through; this pipeline scales angles by
//     `depth`, the prose pipeline's own dial, not by review tier).
//   - depth: quick | standard | deep — scales the gather angle count ABOVE the
//     mandated 3. Default standard.
//   - modelOverride: a model the owner named for this task. When set, every
//     agent runs on it. Unset: gather agents run the `gather` model, SYNTHESIZE
//     and DELIVER inherit the session model (`lead`), and VALIDATE runs the
//     `work` model.

export default async function run({ scope, tier, depth, modelOverride } = {}) {
  // Reject a bad model name before any dispatch.
  validateModelOverride(modelOverride);
  const effectiveDepth = typeof depth === "string" ? depth : "standard";
  const minTailBudget = 8000;

  // SCOPE (deterministic, in-body): select the distinct angles + depth from the
  // prose decision table. No agent dispatch — scoping is a deterministic choice.
  const angles = anglesForDepth(effectiveDepth);

  // Phase GATHER: the mandatory parallel barrier. At LEAST 3 research-subagent-
  // executor agents, each on a DISTINCT angle, dispatched in one parallel() call
  // (sequential research is forbidden by the prose pipeline). Failed slots resolve
  // to null and are filtered; the barrier never drops below the mandated floor.
  enterPhase("gather");
  const rawResults = await parallel(
    angles.map((angle) => () =>
      agent({
        prompt: gatherPrompt(angle, scope),
        schema: RAW_RESEARCH_SCHEMA,
        model: modelFor("gather", modelOverride),
        agentType: "general-purpose",
      }),
    ),
  );
  const raw = rawResults.filter((x) => x != null);

  // Phase SYNTHESIZE: one coordinator over the typed raw results in-memory (no
  // disk). Identifies consensus, contradictions, gaps; rates evidence quality.
  enterPhase("synthesize");
  let synthesis = null;
  if (raw.length > 0 && budget.remaining() >= minTailBudget) {
    synthesis = await agent({
      prompt: coordinatorPrompt(
        `Synthesize these ${raw.length} typed per-angle research results into ` +
          `consensus findings, contradictions, and open gaps. Rate each finding's ` +
          `evidence quality (strong only when backed by specific independent ` +
          `sources, not mere agreement). Raw results (typed, in-memory):\n`,
        raw,
      ),
      schema: SYNTHESIS_SCHEMA,
      model: modelFor("lead", modelOverride),
      agentType: WORKER_AGENT,
    });
  }

  // Phase VALIDATE: source-quality + coverage + bias gate before delivery (the
  // prose Phase 4 quality assessment). One coordinator pass over the synthesis.
  enterPhase("validate");
  let validation = null;
  if (synthesis && budget.remaining() >= minTailBudget) {
    validation = await agent({
      prompt: coordinatorPrompt(
        `Run the research-quality gate over this synthesis: confirm "strong" ` +
          `findings are backed by specific independent sources (not shared bias), ` +
          `flag load-bearing weak findings, assess source diversity, and return a ` +
          `verdict (sufficient|partial|insufficient). Synthesis (typed):\n`,
        synthesis,
      ),
      schema: VALIDATION_SCHEMA,
      model: modelFor("work", modelOverride),
      agentType: WORKER_AGENT,
    });
  }

  // Phase DELIVER: the final formatted report (the prose report.md), built from
  // the validated synthesis. One coordinator pass.
  enterPhase("deliver");
  let report = null;
  if (synthesis && budget.remaining() >= minTailBudget) {
    report = await agent({
      prompt: coordinatorPrompt(
        `Produce the final research report from the validated synthesis: an ` +
          `executive summary (3-5 bullets), detailed findings per angle with ` +
          `sources, and explicit gaps/limitations. Synthesis + validation (typed):\n`,
        { synthesis, validation },
      ),
      schema: REPORT_SCHEMA,
      model: modelFor("lead", modelOverride),
      agentType: WORKER_AGENT,
    });
  }

  return {
    depth: effectiveDepth,
    tier: typeof tier === "number" ? tier : null,
    angles,
    gather_agents_ran: raw.length,
    synthesis,
    validation,
    report,
    budget_remaining: budget.remaining(),
  };
}
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