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 researcher.
Purpose
Produce a cited, reusable best-practice answer or handoff that separates current external evidence from repo-local facts and dependency-selection decisions. For pre-planning investigation, this is the ordinary first research wrapper: gather official/upstream evidence, then hand it to $ralplan or the caller as planning input. Do not present $best-practice-research as a final architecture component or as a validator-gated research loop.
Terminal By Default
This skill is terminal and read-only by default. It gathers evidence and produces a cited recommendation with a handoff, then stops. Do not write or edit files, create or amend commits, run mutating commands, or otherwise modify repository state under this skill — even when the question has clear implementation implications. When implementation is warranted, stop and hand off rather than continuing: name $ralplan for planning and $ultragoal, $team, or executor for execution, and resume only after the user explicitly switches to that workflow.
Activate When
- The user asks for best practices, recommended approach, current guidance, official recommendations, standards, or version-aware external behavior.
$ralplan, $deep-interview, $team, or another 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
explore for codebase facts.
- The main question is whether to adopt, replace, upgrade, or compare dependencies; use
dependency-expert.
- The user only needs implementation against already-grounded requirements; use
executor, $ralph, or $team as appropriate.
- The task can be answered from stable local project conventions without current external lookup.
Specialist Routing
- Use
explore first for brownfield facts: current code usage, local constraints, versions, config, and integration points.
- Use
researcher for official/upstream docs, release notes, standards, migration guides, source-backed examples, and current best-practice evidence for an already chosen technology.
- Use
dependency-expert only for adoption/upgrade/replacement/comparison decisions.
- 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
- Classify the question: conceptual best practice, implementation guidance, migration/version guidance, standards/compliance guidance, or mixed local + external guidance.
- Gather repo-local facts with
explore when local usage or constraints affect the answer.
- Gather external evidence with
researcher when current or version-aware practice affects correctness.
- Synthesize a concise answer with source quality, version/date context, caveats, and an implementation or planning handoff.
- Stop when the answer is grounded enough for the caller; otherwise report the exact blocker or specialist handoff needed.
Output Contract
## 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 explore, or "not needed">
### Boundaries / Non-goals
<what this research does not decide>
### Handoff
<planning/execution/test implications; name the next workflow — `$ralplan` for planning, `$ultragoal`/`$team`/`executor` for execution — and note that this skill stops here unless the user explicitly switches workflows>
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.
- This skill never implements. After delivering the recommendation and handoff, stop; do not modify repo files or repo state. Resume only when the user explicitly switches to a planning or implementation workflow named in the handoff.
Task: {{ARGUMENTS}}
1---2name: best-practice-research3description: "[OMX] Bounded best-practice research wrapper using official/upstream evidence first"4argument-hint: "<technology|decision|practice question>"5metadata:6 source: https://skillmd.com/skills/yeachan-heo-oh-my-codex/best-practice-research7---89# Best-Practice Research1011Use 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 `researcher`.1213## Purpose1415Produce a cited, reusable best-practice answer or handoff that separates current external evidence from repo-local facts and dependency-selection decisions. For pre-planning investigation, this is the ordinary first research wrapper: gather official/upstream evidence, then hand it to `$ralplan` or the caller as planning input. Do not present `$best-practice-research` as a final architecture component or as a validator-gated research loop.1617## Terminal By Default1819This skill is terminal and read-only by default. It gathers evidence and produces a cited recommendation with a handoff, then stops. Do not write or edit files, create or amend commits, run mutating commands, or otherwise modify repository state under this skill — even when the question has clear implementation implications. When implementation is warranted, stop and hand off rather than continuing: name `$ralplan` for planning and `$ultragoal`, `$team`, or `executor` for execution, and resume only after the user explicitly switches to that workflow.2021## Activate When2223- The user asks for best practices, recommended approach, current guidance, official recommendations, standards, or version-aware external behavior.24- `$ralplan`, `$deep-interview`, `$team`, or another workflow needs current external evidence before planning or execution can be correct.25- The task involves an already chosen technology and needs authoritative usage guidance, migration notes, API behavior, lifecycle rules, or current safety guidance.2627## Do Not Activate When2829- The answer is fully repo-local; use `explore` for codebase facts.30- The main question is whether to adopt, replace, upgrade, or compare dependencies; use `dependency-expert`.31- The user only needs implementation against already-grounded requirements; use `executor`, `$ralph`, or `$team` as appropriate.32- The task can be answered from stable local project conventions without current external lookup.3334## Specialist Routing35361. Use `explore` first for brownfield facts: current code usage, local constraints, versions, config, and integration points.372. Use `researcher` for official/upstream docs, release notes, standards, migration guides, source-backed examples, and current best-practice evidence for an already chosen technology.383. Use `dependency-expert` only for adoption/upgrade/replacement/comparison decisions.394. Return to the caller with explicit evidence, uncertainty, and any implementation handoff constraints.4041## Source-Quality Rules4243- Prefer official documentation, upstream source, release notes, changelogs, standards, and maintainer guidance.44- Include source URLs for material claims.45- State date/version context for current best-practice claims.46- Label third-party summaries as supplemental; do not use them before official/upstream sources.47- Flag stale, conflicting, undocumented, or version-mismatched evidence.48- Do not over-fetch: gather the smallest evidence set that can support the decision.4950## Workflow51521. Classify the question: conceptual best practice, implementation guidance, migration/version guidance, standards/compliance guidance, or mixed local + external guidance.532. Gather repo-local facts with `explore` when local usage or constraints affect the answer.543. Gather external evidence with `researcher` when current or version-aware practice affects correctness.554. Synthesize a concise answer with source quality, version/date context, caveats, and an implementation or planning handoff.565. Stop when the answer is grounded enough for the caller; otherwise report the exact blocker or specialist handoff needed.5758## Output Contract5960```md61## Best-Practice Research: <question>6263### Direct Recommendation64<actionable guidance or decision support>6566### Evidence Used67- Official/upstream: <source URL> — <what it establishes>68- Supplemental, if any: <source URL> — <why it is secondary>6970### Version / Date Context71<versions, dates, release channels, or unknowns>7273### Repo-Local Context74<facts from explore, or "not needed">7576### Boundaries / Non-goals77<what this research does not decide>7879### Handoff80<planning/execution/test implications; name the next workflow — `$ralplan` for planning, `$ultragoal`/`$team`/`executor` for execution — and note that this skill stops here unless the user explicitly switches workflows>81```8283## Stop Rules8485- Stop after a source-backed recommendation is reusable by the caller.86- Stop and route upward if the task becomes dependency comparison, broad architecture, or implementation.87- Do not continue researching when remaining work would only polish wording rather than change the recommendation.88- This skill never implements. After delivering the recommendation and handoff, stop; do not modify repo files or repo state. Resume only when the user explicitly switches to a planning or implementation workflow named in the handoff.8990Task: {{ARGUMENTS}}