flywheel-closeout

Use this at the end of substantial repo or agent waves to convert evidence-backed lessons into proposed durable assets: skills, scripts, rules/checks, prompt templates, docs, or issues. Always use it when the user mentions flywheel, wave closeout, repo ecosystem learning, durable asset promotion, or learning-to-tools.

5 stars

Best use case

flywheel-closeout is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Use this at the end of substantial repo or agent waves to convert evidence-backed lessons into proposed durable assets: skills, scripts, rules/checks, prompt templates, docs, or issues. Always use it when the user mentions flywheel, wave closeout, repo ecosystem learning, durable asset promotion, or learning-to-tools.

Teams using flywheel-closeout should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/flywheel-closeout/SKILL.md --create-dirs "https://raw.githubusercontent.com/vamseeachanta/workspace-hub/main/.claude/skills/coordination/flywheel-closeout/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/flywheel-closeout/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How flywheel-closeout Compares

Feature / Agentflywheel-closeoutStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Use this at the end of substantial repo or agent waves to convert evidence-backed lessons into proposed durable assets: skills, scripts, rules/checks, prompt templates, docs, or issues. Always use it when the user mentions flywheel, wave closeout, repo ecosystem learning, durable asset promotion, or learning-to-tools.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# Flywheel Closeout

Use this skill after meaningful agent waves, repeated defects, or cross-provider review cycles.

## Workflow

1. Gather explicit source evidence: issue URLs, PR URLs, commit SHAs, handoff paths, and review artifacts.
2. Run `uv run --no-project python scripts/workflow/flywheel_closeout.py` with `--mode propose`.
3. Inspect `manifest.json`, `report.html`, and `issue-drafts/`.
4. Route local behavior changes to the local repo. Route skills, shared scripts, rules/checks, provider workflow, and review-artifact contracts to `workspace-hub`.
5. Keep all outputs advisory in this first slice. Do not create issues, comments, labels, or approvals from this skill.

## Gates

Preserve the normal repo workflow: issue, plan, adversarial review, user approval, implementation, code/artifact review, legal/security scan, and pre-completion cleanup audit.

Missing flywheel evidence is advisory until a later approved enforcement issue hardens it.

Related Skills

orcawave-orcaflex-semantic-proof-wave-closeout

5
from vamseeachanta/workspace-hub

Close out an OrcaWave/OrcaFlex semantic-proof wave after a PR merges, split unrelated CI blockers, and seed the next semantic-proof issue wave without duplicating existing issues.

github-issue-closeout-race-safe

5
from vamseeachanta/workspace-hub

Close GitHub issues without losing the evidence comment when multiple agents or races may close the issue concurrently.

test-oversized-skill

5
from vamseeachanta/workspace-hub

A test fixture skill that exceeds 200 lines with multiple H2/H3 sections for split testing.

interactive-report-generator

5
from vamseeachanta/workspace-hub

Generate interactive HTML reports with Plotly visualizations from data analysis results. Supports dashboards, charts, and professional styling.

data-validation-reporter

5
from vamseeachanta/workspace-hub

Generate interactive validation reports with quality scoring, missing data analysis, and type checking. Combines Pandas validation, Plotly visualization, and YAML configuration for comprehensive data quality reporting.

agent-os-framework

5
from vamseeachanta/workspace-hub

Generate standardized .agent-os directory structure with product documentation, mission, tech-stack, roadmap, and decision records. Enables AI-native workflows.

OrcaFlex Specialist Skill

5
from vamseeachanta/workspace-hub

```yaml

repo-ecosystem-hygiene

5
from vamseeachanta/workspace-hub

Interpret the daily read-only repo ecosystem hygiene audit and route remediation through approved workflows.

domain-knowledge-sweep

5
from vamseeachanta/workspace-hub

Systematic multi-source research of an engineering domain. Spawns parent issue → 6 research subissues (Standards, Academic, Industry, LinkedIn-marketing, Code-audit, Synthesis) → gap implementation subissues. Replaces LinkedIn-only extraction with defensible comprehensive sourcing.

subagent-write-verification

5
from vamseeachanta/workspace-hub

Independently verify subagent-claimed file writes with filesystem and git checks before treating the artifact as real, before committing it, and before referencing the path in downstream prompts.

git-operation-serialization-preflight

5
from vamseeachanta/workspace-hub

Before any commit, stash, merge, reset, rebase, or checkout in a multi-agent or shared-checkout environment, run a bounded preflight to detect active git writers and stale index/config locks, then serialize the mutating step under a single-writer guarantee.

public-knowledge-graph-governance

5
from vamseeachanta/workspace-hub

Maintain public-safe knowledge graph artifacts for llm-wiki and similar markdown knowledge bases. Use when changing graph generators, validators, schema docs, weekly freshness checks, or public/private source-scope boundaries.