workflow-patterns

Featured

Argument shapes for the 5 built-in workflow patterns — deep-research, adversarial-review, code-review, multi-perspective, codebase-audit — runnable via the `workflow` tool's `name` input, without slash-command syntax. Use for requests like "research X", "fact-check/adversarially review this", "review this diff/PR", "analyze from multiple perspectives", or "audit the codebase for Y". Not for authoring a new workflow script — see workflow-authoring.

AI & Automation 540 stars 104 forks Updated yesterday MIT

Install

View on GitHub

Quality Score: 94/100

Stars 20%
91
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
50
License 10%
100
Description 5%
100

Skill Content

# Built-in workflow patterns pi-dynamic-workflows ships 5 curated, tested workflow patterns. Each is also a slash command (`/deep-research`, `/adversarial-review`, `/code-review`, `/multi-perspective`, `/codebase-audit`), but they are equally reachable from the `workflow` tool directly: call it with `name` set to the pattern name below and `args` matching its shape, instead of writing an equivalent script from scratch. Prefer this over authoring a new script whenever the request fits one of these shapes — the curated version is already reviewed and tested. A project or user saved workflow of the same name always takes precedence over a built-in of that name — on the slash command, too. These 5 names are reachable only at the `workflow` tool's top-level `name` input, not via the in-script `await workflow(savedName, childArgs)` helper — that helper resolves saved workflows only. Calling `workflow('deep-research')` from inside a script fails as an unknown saved workflow; use the top-level `name` input instead. ## Patterns | `name` | When to reach for it | `args` | | --- | --- | --- | | `deep-research` | Research a question across the web with cross-checked sources | `{ question: string, angles?: number, minSupport?: number }` — `angles` (default 4) is the number of distinct search queries; `minSupport` (default 2) is the minimum distinct sources required for a claim to survive cross-checking | | `adversarial-review` | Investigate a task/claim, then cross-check each finding ...

Details

Author
QuintinShaw
Repository
QuintinShaw/pi-dynamic-workflows
Created
3 months ago
Last Updated
yesterday
Language
TypeScript
License
MIT

Similar Skills

Semantically similar based on skill content — not just same category

AI & Automation Listed

dynamic-workflow-patterns

Pattern taxonomy, agent role combinations, model routing, unit-of-work sizing, and resilience discipline for Claude Code dynamic workflows. ALWAYS load this skill before authoring or running any Workflow tool script, and ALWAYS load it when the user mentions "workflow" or "ultracode" in any form -- or when the task calls for multi-agent orchestration such as fan-out, tournaments, adversarial verification, triage at scale, ranking large lists, deep verification of claims, or root-cause hunting; do not hand-roll a workflow from memory when this skill applies.

6 Updated 1 weeks ago
alex-feel
AI & Automation Solid

research-workflow

Dynamic Workflow asset for /lets:research --workflow. Not auto-triggered - a workflow script invoked via scriptPath by /lets:research. Holds the off-context per-sub-question web research -> per-claim skeptic cross-check -> synthesize chain.

17 Updated yesterday
restarter
AI & Automation Listed

workflow

Use when the user wants to design or scaffold a one-shot multi-agent fan-out / decomposition orchestration — review code across N dimensions, migrate N call-sites in parallel, research N sources, or split an implementation into parallel agents with per-agent model/effort assignment — landing as a written `.context/workflows/` workflow-spec (goal + fan-out shape + per-agent model table + gate policy) before the Workflow runs. Fires on "design a workflow to review X across N angles", "fan out agents to migrate every call-site", "orchestrate a multi-agent review of X", "decompose this into parallel agents with different models". Not for: executing a written multi-phase plan (/aidex:plan-exec); repeat-until-a-check-passes automation (/aidex:loop); planning multi-step work without orchestration (/aidex:plan); ecosystem audits (/aidex:aidex); project-state audits (/aidex:audit).

2 Updated 4 days ago
yacb2