best-practice-research
[Omagy] Bounded best-practice research wrapper using official/upstream evidence first
Skill by shayne-snap
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/shayne-snap-best-practice-research
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: research
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/best-practice-research
What's inside
- Skill name
best-practice-research- Description
- [Omagy] Bounded best-practice research wrapper using official/upstream evidence first
- License
- MIT
- Instructions
- 117 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Best-Practice Research
Use this skill when a task depends on current external best practices,
version-aware guidance, standards, official recommendations, or upstream
behavior. This is a workflow wrapper: it routes evidence gathering and
synthesis; it is not a new research authority and it does not replace the
researcher lane.
## Purpose
Produce a cited, reusable best-practice answer or handoff that separates
current external evidence from repo-local facts and dependency-selection
decisions.
## Activate When
- The user asks for best practices, recommended approach, current guidance,
official recommendations, standards, or version-aware external behavior.
- `/omagy:ralplan`, `/omagy:deep-interview`, `/omagy:team`, or another Omagy
workflow needs current external evidence before planning or execution can be
correct.
- The task involves an already chosen technology and needs authoritative usage
guidance, migration notes, API behavior, lifecycle rules, or current safety
guidance.
## Do Not Activate When
- The answer is fully repo-local; use `omagy explore --prompt "<narrow lookup>" --json`
for codebase facts.
- The main question is whether to adopt, replace, upgrade, or compare
dependencies; route back to `/omagy:plan` with an explicit dependency
decision scope instead of deciding it inside this skill.
- The user only needs implementation against already-grounded requirements; use
`/omagy:ralph`, `/omagy:team`, or the direct executor lane as appropriate.
- The task can be answered from stable local project conventions without
current external lookup.
## Specialist Routing
1. Use `omagy explore --prompt "<narrow lookup>" --json` first for brownfield
facts: current code usage, local constraints, versions, config, and
integration points.
2. Use the Antigravity/Omagy researcher lane when available for
official/upstream docs, release notes, standards, migration guides,
source-backed examples, and current best-practice evidence for an already
chosen technology.
3. If no dedicated researcher lane is available, use the normal external
research path, cite official/upstream URLs, and explicitly mark any evidence
gap. Do not invent authority from memory.
4. Route dependency adoption, upgrade, replacement, or comparison decisions
back to `/omagy:plan` as a dependency decision; this skill may provide
source evidence but does not choose the dependency.
5. Return to the caller with explicit evidence, uncertainty, and any
implementation handoff constraints.
## Source-Quality Rules
- Prefer official documentation, upstream source, release notes, changelogs,
standards, and maintainer guidance.
- Include source URLs for material claims.
- State date/version context for current best-practice claims.
- Label third-party summaries as supplemental; do not use them before
official/upstream sources.
- Flag stale, conflicting, undocumented, or version-mismatched evidence.
- Do not over-fetch: gather the smallest evidence set that can support the
decision.
## Workflow
1. Classify the question: conceptual best practice, implementation guidance,
migration/version guidance, standards/compliance guidance, or mixed local +
external guidance.
2. Gather repo-local facts with `omagy explore --prompt "<narrow lookup>" --json`
when local usage or constraints affect the answer.
3. Gather external evidence with the researcher lane or normal external
research path when current or version-aware practice affects correctness.
4. Synthesize a concise answer with source quality, version/date context,
caveats, and an implementation or planning handoff.
5. Stop when the answer is grounded enough for the caller; otherwise report the
exact blocker or specialist handoff needed.
## Output Contract
```md
## Best-Practice Research: <question>
### Direct Recommendation
<actionable guidance or decision support>
### Evidence Used
- Official/upstream: <source URL> - <what it establishes>
- Supplemental, if any: <source URL> - <why it is secondary>
### Version / Date Context
<versions, dates, release channels, or unknowns>
### Repo-Local Context
<facts from omagy explore, or "not needed">
### Boundaries / Non-goals
<what this research does not decide>
### Handoff
<planning/execution/test implications>
```
## Stop Rules
- Stop after a source-backed recommendation is reusable by the caller.
- Stop and route upward if the task becomes dependency comparison, broad
architecture, or implementation.
- Do not continue researching when remaining work would only polish wording
rather than change the recommendation.
Task: {{ARGUMENTS}}From shayne-snap/oh-my-antigravity, MIT.
More from shayne-snap/oh-my-antigravity
- 0.516score
analyze
shayne-snap
Run read-only deep repository analysis with ranked synthesis, concrete evidence, and explicit Evidence/Inference/Unknown boundaries.
SkillCFreshness: C★ 4Claude Code +9 - 0.513score
pipeline
shayne-snap
Configurable pipeline orchestrator for sequencing Omagy stages.
SkillCFreshness: C★ 4Claude Code +9 - 0.513score
install
shayne-snap
Install, repair, or refresh the Omagy Antigravity plugin from the local checkout.
SkillCFreshness: C★ 4Claude Code +9 - 0.513score
memory
shayne-snap
Record and read durable Omagy project facts, directives, and working notes.
SkillCFreshness: C★ 4Claude Code +9 - 0.513score
migrate
shayne-snap
Detect and apply native Antigravity CLI skills and MCP migrations from other coding agents.
SkillCFreshness: C★ 4Claude Code +9 - 0.513score
note
shayne-snap
Persistent Omagy notepad for priority, working, and manual notes
SkillCFreshness: C★ 4Claude Code +9 - 0.513score
performance-goal
shayne-snap
Evaluator-gated performance optimization workflow with durable Omagy artifacts for agy.
SkillCFreshness: C★ 4Claude Code +9 - 0.513score
plugin
shayne-snap
Manage Antigravity plugins with safe install, doctor, remove, and lightweight index workflows.
SkillCFreshness: C★ 4Claude Code +9 - 0.513score
autoresearch
shayne-snap
Stateful validator-gated research loop with artifact-gated completion.
SkillCFreshness: C★ 4Claude Code +9 - 0.513score
autoresearch-goal
shayne-snap
Professor-critic research workflow with durable Omagy artifacts for agy.
SkillCFreshness: C★ 4Claude Code +9 - 0.513score
cancel
shayne-snap
Cancel the active Omagy workflow or all Omagy workflow state.
SkillCFreshness: C★ 4Claude Code +9 - 0.513score
doctor
shayne-snap
Diagnose the Oh My Antigravity installation and Antigravity CLI plugin lifecycle.
SkillCFreshness: C★ 4Claude Code +9
Signals
- Stars
- 4
- Forks
- 0
- Open issues
- 1
- Last commit (this folder)
- May 24, 2026 (5 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/shayne-snap/oh-my-antigravity
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from shayne-snap
- 0.516score
analyze
shayne-snap
Run read-only deep repository analysis with ranked synthesis, concrete evidence, and explicit Evidence/Inference/Unknown boundaries.
SkillCFreshness: C★ 4Claude Code +9 - 0.513score
cancel
shayne-snap
Cancel the active Omagy workflow or all Omagy workflow state.
SkillCFreshness: C★ 4Claude Code +9 - 0.513score
autoresearch
shayne-snap
Stateful validator-gated research loop with artifact-gated completion.
SkillCFreshness: C★ 4Claude Code +9 - 0.513score
autoresearch-goal
shayne-snap
Professor-critic research workflow with durable Omagy artifacts for agy.
SkillCFreshness: C★ 4Claude Code +9 - 0.513score
doctor
shayne-snap
Diagnose the Oh My Antigravity installation and Antigravity CLI plugin lifecycle.
SkillCFreshness: C★ 4Claude Code +9 - 0.513score
hud
shayne-snap
Show the current Omagy workflow, team, and hook activity HUD.
SkillCFreshness: C★ 4Claude Code +9
Cite this page
best-practice-research skill. Agent Mart. https://agentmart.dev/skills/shayne-snap-best-practice-research (last updated 2026-10-24)