warpdotdev/common-skills

research

Delegate noisy investigation to one or more subagents so the orchestrator's context stays clean, then work from the distilled answer.

Voir la source

Mode d’emploi

  1. Copiez la commande et examinez le paquet avant de l’installer dans votre environnement agent.
  2. Consultez le document original pour les outils, identifiants et environnements requis.
  3. Décrivez les entrées et le livrable souhaité ; comparez la sortie aux sources.
npx skills add https://github.com/warpdotdev/common-skills --skill research

Avant de commencer

  • L’installation n’inclut ni abonnement au modèle, ni quota API, ni accès aux fichiers.
  • Étoiles et installations reflètent l’activité, pas un test indépendant de qualité ou de sécurité.
Document Skill original

Rendu depuis le dépôt source en conservant titres, exemples, code, tableaux, liens et images.

Research

Use this skill to answer a question by delegating the work of finding the answer to a subagent, so that the byproducts of that work — file contents, log noise, dead-end reads — never enter your own context. You get back a distilled answer plus the evidence that supports it, and you stay sharp for the actual task.

Why this matters

Your context window is your most valuable and limited resource. Reading twenty files to discover that three of them mattered permanently pollutes your context with seventeen files of noise, degrading every subsequent decision you make. A subagent absorbs that noise on your behalf and hands you only the signal. Think of it as asking a colleague to dig through the archives and report back, rather than dumping the whole archive on your desk.

When to use it

Reach for research delegation when the cost of producing the answer is far greater than the answer itself. Strong signals:

  • You'd need to read many files to find the few that are relevant.
  • You'd need to wade through long test output, CI logs, or stack traces to extract a failure.
  • You'd need to survey how a pattern, API, or symbol is used across the whole repo.
  • You'd need to read and summarize a large diff or PR.
  • The question has several independent sub-parts that could be investigated separately.

Examples — good fits:

  • "What's the root cause of this failing test?" (the subagent reads the logs and traces the code; you get the cause)
  • "How is SessionManager used across the codebase?" (the subagent greps and reads; you get a summary with call sites)
  • "Summarize what this 4,000-line PR changes and why." (the subagent reads the diff; you get the shape of it)

Examples — do NOT delegate:

  • Reading 2–3 files you already know you need. Just read them directly; delegation adds latency for no context savings.
  • A single grep or one-line lookup. Do it yourself.
  • Anything where you need the raw material for your next step. If you're about to edit the files you'd be reading, delegating is counterproductive — you'd just have to re-read them yourself to make the change. Research delegation pays off when the output is a conclusion, not when it's material you'll work on directly.

The cost of a subagent is real (latency and tokens), so the test is always: does the noise I'd avoid outweigh that cost?

How to do it

Spawn locally with a search model

Always spawn research subagents as local agents, never remote — including when the parent is a factory or cloud agent.

Pick the model for the search task, not your own. Research subagents should search and distill, not analyze: use gpt-6-luna-medium for simple search, and gpt-6-luna-xhigh for more involved requests (for example, tracing data flow through call sites).

Single vs. parallel

Default to a single subagent. Spawn multiple subagents in parallel only when the question genuinely decomposes into independent sub-parts that don't need to share intermediate findings — for example, "how does auth work AND how does billing work AND how does the rate limiter work" are three independent investigations that can run at once. Parallelism is a capability worth using when the parts are truly independent, since separate subagents can investigate simultaneously; but don't force a single coherent question into artificial fragments.

Brief the subagent well

The subagent does not share your intent, so spell it out. A good research brief includes:

  • The exact question to answer.
  • Where to look (repo path, branch, suspected files/symbols if you know them).
  • That it is read-only — it should investigate and report, not modify files, unless the task explicitly calls for changes.
  • The output you want back (see below).

Ask for signal, not transcript

Tell the subagent to return a distilled answer plus its supporting evidence, not a raw dump. Specifically:

  1. The direct answer to the question.
  2. The key evidence: exact file paths and symbols (e.g. src/session.rs:142, fn reconnect), so you can jump straight to what matters.
  3. Anything surprising or any caveats/unknowns it hit.

The whole point is that the noise stays with the subagent. If a report comes back bloated, send a focused follow-up to the same subagent asking it to tighten the answer — it retains its context and can refine cheaply.

After you get the answer

Work from the distilled result. If you later find you need the underlying files to make edits, read them directly at that point — now you know exactly which ones matter, so you read three files instead of twenty.

Tâches connexes

du même dépôt

Autres Skills

Tous les Skills
warpdotdev
Communauté

council

Run a model-diverse subagent council to investigate the same problem from multiple perspectives, compare findings, and produce a final recommendation. Use this skill whenever the user asks for a council, second opinions, multiple agents/models to evaluate one question, parallel investigation, red-team/blue-team comparison, or help deciding between competing technical approaches.

Installations / 1h
2
GitHub Stars
718
Mis à jour
11 nov.
warpdotdev
Communauté

respond-to-pr-comments-in-blocklist

Interactively walk a user through PR review comments one at a time, collect a per-comment decision, then post agent-authored replies on GitHub and resolve the review threads once the user approves a preview. Use only when the user wants to reply to or resolve review threads on GitHub. Skip when the user only wants comments fetched or displayed (use pr-comments), or only wants the code changes made without posting anything back to GitHub.

Installations / 1h
2
GitHub Stars
718
Mis à jour
11 nov.
warpdotdev
Communauté

skill-doctor

Grades agent skills by scoring agent conversations for efficiency, code quality, procedure compliance, and verbosity, then drafts concrete skill edits and a shareable report. Use when the user wants their agent setup graded from real conversation history, or asks which of their installed skills are actually working.

Installations / 1h
3
GitHub Stars
718
Mis à jour
11 nov.
warpdotdev
Communauté

write-feature-docs

Draft a complete documentation page for a new Warp feature from its PRODUCT.md and/or TECH.md spec. Use when an engineer has written a spec and needs to produce a first-pass MDX draft for the warpdotdev/docs repo. Also handles features without specs by researching the codebase first. Invoke this skill whenever an engineer mentions writing docs for a feature, drafting a docs page, creating feature documentation, starting the eng-docs workflow, or converting a spec into documentation. Requires an

Installations / 1h
2
GitHub Stars
718
Mis à jour
11 nov.