Jeden Skill in Manus ausführen
mit einem Klick

Jeden Skill in Manus mit einem Klick ausführen

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.

In Manus ausführen

Überblick

Installationsbefehl

npx skills add https://github.com/vamseeachanta/workspace-hub --skill flywheel-closeout

Kopieren Sie diesen Befehl und fügen Sie ihn in Claude Code ein, um den Skill zu installieren

Quelle

vamseeachanta/workspace-hub

Sterne10

Forks6

Aktualisiert3. Juni 2026 um 01:14

SKILL.md

readonly

name: flywheel-closeout description: 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.

Flywheel Closeout

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

Workflow

Gather explicit source evidence: issue URLs, PR URLs, commit SHAs, handoff paths, and review artifacts.
Run uv run --no-project python scripts/workflow/flywheel_closeout.py with --mode propose.
Inspect manifest.json, report.html, and issue-drafts/.
Route local behavior changes to the local repo. Route skills, shared scripts, rules/checks, provider workflow, and review-artifact contracts to workspace-hub.
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.

Mehr aus diesem Repository

gleiches Repository

blender-worktree-test-hardening

vamseeachanta/workspace-hub

Recover and harden digitalmodel Blender automation work in isolated worktrees when uv/editable dependency paths break and local machines lack a Blender executable.

2026-06-0110

digitalmodel-orcawave-orcaflex-proof-workflows

vamseeachanta/workspace-hub

Class-level digitalmodel OrcaWave/OrcaFlex readiness, semantic-proof, fixture-proof, and closeout workflows.

2026-06-0110

digitalmodel-worktree-test-execution-with-shared-venv

vamseeachanta/workspace-hub

Run digitalmodel tests from isolated worktrees without uv editable-dependency failures by using the main repo's existing virtualenv and PYTHONPATH.

2026-06-0110

library-evaluation-integration

vamseeachanta/workspace-hub

Create evaluation scripts and integration tests for Python scientific libraries in the digitalmodel package. Follows the established pattern from fluids, ht, meshio, sectionproperties, and pygmt evaluations.

2026-06-0110

orcaflex-reporting-fixture-proof-pattern

vamseeachanta/workspace-hub

Build and extend fixture-backed OrcaFlex reporting proof paths in digitalmodel using stable metadata baselines, normalized HTML snapshots, and reusable reporting test helpers.

2026-06-0110

hermes-memory-bridge

vamseeachanta/workspace-hub

Architecture and scripts for syncing Hermes memory into git-tracked .claude/memory/ so all machines get context via git pull. Covers quality gate, drift detection, topic mirroring, and cron automation.

2026-06-0110

Quelle

vamseeachanta

vamseeachanta/workspace-hub

GitHub-Repository öffnen Creator-Repositorys ansehen

Installationsbefehl

Download

In Manus ausführen

Nützlich fürSOC

SoftwareentwicklerInformatik- und Mathematikberufe15-1252L4

name: flywheel-closeout description: 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.

Flywheel Closeout

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

Workflow

Gather explicit source evidence: issue URLs, PR URLs, commit SHAs, handoff paths, and review artifacts.
Run uv run --no-project python scripts/workflow/flywheel_closeout.py with --mode propose.
Inspect manifest.json, report.html, and issue-drafts/.
Route local behavior changes to the local repo. Route skills, shared scripts, rules/checks, provider workflow, and review-artifact contracts to workspace-hub.
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.