adr-writer
Use when capturing an architecture decision so it survives turnover — produces an ADR-NNNN.md from context, options considered,…
Use when the user asks for a sourced briefing on a topic that spans multiple web sources and requires citations.
$ npx -y skills add oxbshw/LLM-Agents-Ecosystem-Handbook --skill research-summarizer --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/research-summarizerContext preview
The summary Claude sees to decide when to auto-load this skill.
Use when the user asks for a sourced briefing on a topic that spans multiple web sources and requires citations.
name: research-summarizer description: Use when the user asks for a sourced briefing on a topic that spans multiple web sources and requires citations. version: 0.1.0
| Name | Type | Required | Notes | |---|---|---|---| | `topic` | string | yes | the question to research | | `depth` | "shallow" \| "deep" | no | default "shallow" (5–7 sources); "deep" → 10–15 | | `audience` | string | no | shapes vocabulary level (e.g., "executive", "engineer") |
A Markdown file `briefing.md` following the structure in `references/report-template.md`.
1. **Plan**: produce 3–7 sub-questions covering breadth and depth 2. **Search + fetch**: for each sub-question, run `web_search` then `fetch_url` for top 2–3 hits 3. **Cluster**: group findings by claim; load `references/clustering-rules.md` 4. **Draft**: fill `references/report-template.md` — every claim needs a `[n]` citation 5. **Validate**: every citation resolves; no domain dominates (≥ 3 distinct domains for shallow, ≥ 5 for deep) 6. **Self-review** against success criteria below
A practical operating manual for building, evaluating, securing, and shipping modern LLM agent systems. Modern agents are not "a prompt + a tool."
Use when capturing an architecture decision so it survives turnover — produces an ADR-NNNN.md from context, options considered,…
Use when reviewing a proposed REST or GraphQL API change before merge — checks contract clarity, backwards compatibility, errors,…
Use when first encountering a new dataset — produces a structured profile (schema, missingness, distributions, outliers, gotchas)…
Use after an incident is resolved — drafts a blameless postmortem from timeline notes, alerts, and chat threads.
Use when opening a PR — produces a clean PR description (what / why / how to verify / risks) from a branch diff against base.
Use when planning the next sprint — turns ticket intake + team capacity into a planned sprint with explicit non-goals.