Skip to content
Skills Library
Other · Research

research

/research

Use when asked to investigate or find something out - in data, documents, code or on the web.

Licence
MIT
Last repository change
27.10.2026

Assessment and security

92/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content27 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
1
Scripts
0
HTML comments
0
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 27.10.2026, without references to retired models or APIs.

Licence

MIT, open: use and modify while retaining author attribution.

What it does and when to use it

Use when asked to investigate or find something out - in data, documents, code or on the web.

Original author description

Use when asked to investigate or find something out - in data, documents, code or on the web.

How it works

SKILL.md has no level-two headings · 34 lines, 400 words

SKILL.md preview
---
name: research
description: Use when asked to investigate or find something out - in data, documents, code or on the web.
---

Research is interactive, so the user can:
- follow the process as it goes, instead of a separate, potentially expensive review of the end result
- steer early, before a red herring or a suboptimal path costs much, and mistakes accumulate

Research is read-only: never modify tracked files, config or live state.

Terms:

- **unverified claim** - a single statement the answer could rest on, not yet verified, so it cannot be relied upon. Examples: a suspicion from the user, the claim inside the task question itself, your own educated guess, a hypothesis surfacing mid-research.
- **verified claim** - a claim confirmed by checked evidence, or stated by the user from their own knowledge. Verification is always explicitly scoped: the claim holds under the conditions the evidence covered, which can be as broad as "always", or as narrow as exactly one setup; the same claim under different conditions is a new, unverified claim.

Workflow:

1. Split the input into the questions, the user's verified claims, and the unverified claims that could lead toward answers.
2. Show the list, propose the claim whose verification is cheapest while moving an answer closest, together with how you plan to verify it; wait for the user's go-ahead.
3. Execute exactly what was agreed. Stop and present for the user's review as soon as:
   - you verified or refuted the claim you were working on;
   - you could not verify it within the agreed scope;
   - you found a contradiction to an already verified claim: lay both out - resolving contradictions is the user's call.
4. Go to 2 if any question remains unanswered; otherwise produce the final report per the rules below.

Verification methods:

- reading documentation: cheapest, when it exists and is reliable;
- reading the code: settles a claim directly, but expensive and easy to misread when the codebase is complicated;
- a probe - throwaway script, query, client call from a scratch directory: often the most reliable, especially when code is complicated or unavailable and the probe itself is simple.

Final report rules, whether it lands in chat or a file:

- Lead with the answer, then the evidence. Cite file:line, table, query or sample size for anything the answer rests on.
- Only verified claims make the report; a disproved one enters as its verified opposite.
- No process narrative: what you found, not the order you found it in.

Versions

RepositoryScoreLicence
This page · skhoroshavin/tandem-skills92MIT
Insilico-org/plsi100MIT
boshu2/agentops100Apache-2.0
udecode/plate100MIT
rjmurillo/ai-agents100MIT
rjmurillo/ai-agents100MIT
rjmurillo/ai-agents100MIT
taishi-i/awesome-japanese-nlp-resources100CC0-1.0
niekcandaele/claude-helpers100MIT

Identical content appears in 4 other GitHub folders. We show one copy with the highest score.

Database snapshot: 13.11.2026 · package version 85e206ddf8d0 (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 90web-research
    Use this skill for requests related to web research; it provides a structured approach to conducting comprehensive web research.
  • 100web-research
    Searches multiple web sources, synthesizes findings, and produces cited research reports using delegated subagents. Use when the user asks to research a topic online, search the web, look something up, find current information, compare options, or produce a research report.
  • 82review
    Use when asked to review any kind of artifact, including code, documents and configs.
  • 95web-search
    This skill should be used when users need to search the web for information, find current content, look up news articles, search for images, or find videos. It uses DuckDuckGo's search API to return results in clean, formatted output (text, markdown, or JSON). Use for research,…

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.