Research Best Practices

What it does

When your agent uses it

• Tasks that involve MCP servers

Example prompts

• “/research-best-practices”

Requirements

• Node.js

Workflow steps

7 steps, taken from the first numbered list in SKILL.md.

1. 1Consult tech stack — Read specs/tech-stack.md first. Most technology decisions, versions, and patterns should already be resolved from…
2. 2Inventory — List the technologies, SDKs, and services needed for the current feature/slice that are NOT already covered by…
3. 3Check skills — Scan .github/skills/ for existing skills that cover any of these technologies
4. 4Research each technology — For each item in the inventory
5. 5Check versions — Verify that the package versions in package.json are current; note any that need updating
6. 6Summarize findings — Produce a concise research summary
7. 7Record in state — Save key findings in state.json under the current feature's metadata so future sessions don't repeat the research

What it can do on your machine

Read from SKILL.md and the folder at commit 8e76618. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Research Best Practices loads about 1.4k tokens when it runs. Until then it costs about 79 tokens; SKILL.md has 573 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~79

When it runs · the whole SKILL.md, loaded when a task matches

~1.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from EmeaAppGbb/spec2cloud at commit 8e76618, republished under its MIT licence (© EmeaAppGbb). 573 words, ~1,366 tokens.

name

research-best-practices

description

Research current best practices, latest package versions, and official guidance before writing implementation code. Uses MCP tools (Microsoft Learn, Context7, DeepWiki) and available Copilot skills to ground decisions in up-to-date, first-party documentation rather than stale training data.

## Research Summary: <feature-name>

### Technologies Researched
| Technology | Version | Source | Key Finding |
|------------|---------|--------|-------------|
| @azure/cosmos | 4.2.0 | MS Learn | Use `iterateAll()` instead of `fetchAll()` for large datasets |
| next.js | 15.1.0 | Context7 | Server Actions stable; use `revalidatePath` for cache invalidation |

### Patterns to Follow
- <pattern description> (source: <link>)

### Anti-patterns / Deprecations
- <what to avoid> (source: <link>)

### Package Updates Needed
- <package>: <current> → <recommended> (reason)

### Skills Available
- <skill-name>: <how it applies>

© EmeaAppGbb, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .github/skills/research-best-practices of EmeaAppGbb/spec2cloud.

Open the folder on GitHubat commit 8e76618