Workflow orchestrator

Skill Razaib-khan/ForgeWeave/src/forgeweave/templates/gemini/.gemini/skills/workflow-orchestrator

Behavioral execution framework for AI agents — define deterministic, portable skills & agents across OpenCode, Claude Code, Gemini CLI, and Qwen Code.

Install

npx -y skills add Razaib-khan/ForgeWeave --skill workflow-orchestrator

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Coordinates multi-skill execution pipelines (e.g., research → plan → build → test)

SKILL.md

3.1 KB, 641 tokens by cl100k_base, as published. Nobody here has run it

Workflow Orchestrator

Purpose

Coordinate the execution of multiple skills in sequence or parallel to achieve a complex goal. Handles dependency resolution, data passing between skills, error recovery, and progress reporting. The top-level orchestrator that makes multi-step agentic workflows reliable.

When to Use

A complex goal requires 3+ skills in sequence (e.g., research → plan → build → test)
Multiple independent subtasks can run in parallel
A pipeline needs retry logic or error recovery
The user wants a multi-step workflow executed end-to-end

When Not to Use

Only one skill is needed — invoke it directly
The steps are manual and need user approval at each stage
The workflow is a simple linear script — use a script instead

Inputs

Input	Type	Required	Description
`goal`	string	Yes	The overall objective
`pipeline_definition`	array	No	Explicit skill order if known (auto-generated if omitted)
`fallback_strategy`	enum	No (default: stop)	stop, retry, skip

Expected Outputs

Output	Description
Pipeline result	The output of the final skill
Execution trace	What ran, in what order, what each produced
Status report	Success, failures, and retries

Exact Workflow Steps

Accept the goal from the user or from a command
Decompose the goal into ordered skills using planner skill
Identify dependencies between skills (blocking, parallel, sequential)
Execute skills in dependency order:
- Parallel skills run concurrently
- Sequential skills run in order, passing outputs
After each skill, validate output using validation-engine
On failure: retry, skip, or stop based on fallback strategy
Report results to user with execution trace

Required Checks

All skills in the pipeline are available
Dependency order is correct (no cycles)
Each skill's output is valid before passing to next
Fallback strategy is defined for every pipeline step

Failure Modes

Failure Condition	Response
Required skill not available	Report missing skill and suggest alternatives
Pipeline step fails after retries	Report failure with partial results
Circular dependency detected	Restructure to eliminate the cycle

Examples

Example: Feature development pipeline

planner → decompose: code design, implement, test, document
architecture-designer → design module structure
code-builder → implement (depends on architecture-designer)
test-generator → create tests (parallel with docs)
validation-engine → validate all outputs
Report results

References

Reference	Path
Planner skill	`../planner/SKILL.md`
Validation Engine skill	`../validation-engine/SKILL.md`
Command Executor skill	`../command-executor/SKILL.md`

Gives 0 of the 12 instructions most automation workflows skills give in 641 tokens

Counted across 745 of the 1,008 authors here whose files we hold, read 2026-08-07

write conventional commit messagesin 36 of 745, across 35 files
delete branches after mergein 30 of 745, across 21 files
make atomic commitsin 25 of 745, across 15 files
write minimal code to pass testsin 22 of 745, across 10 files
re-snapshot after navigation or DOM changesin 21 of 745, across 13 files
use try-catch for error handlingin 20 of 745, across 8 files
run tests before committingin 20 of 745, across 12 files
write tests before implementationin 20 of 745, across 8 files
configure branch protection rulesin 19 of 745, across 5 files
explain the why in commit messagesin 19 of 745, across 9 files
refactor code while tests remain greenin 19 of 745, across 6 files
Interact with elements using refsin 19 of 745, across 11 files

Said here and by no other author read

decompose the goal into ordered skills
identify dependencies between skills
execute skills in dependency order
run independent subtasks concurrently
pass outputs to sequential skills
apply fallback strategy on failure

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.