agentsclimarketplace
Sign in

Research

Skill yuri-semenenko/ai-engineering-workspace/codex/skills/research

Use when deciding a concrete technical question — comparing libraries, frameworks, APIs, or approaches — by gathering evidence from primary sources into a cited decision matrix with a recommendation and its uncertainty, ready to hand to an RFC or ADR. Lighter than a full research-report harness: bounded to what the decision needs.From its SKILL.md

Install
npx -y skills add yuri-semenenko/ai-engineering-workspace --skill research

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

2.0 KB, 342 tokens by cl100k_base, as published. Nobody here has run it

Research

Turn a technical question into a decision you can defend: evidence from primary sources, a cited comparison, and a recommendation that states its own uncertainty. The output feeds an RFC or ADR; it is not the decision document itself. Depth is proportional to the blast radius of the decision.

The Loop

  1. Frame the question and the criteria that will matter — those become the matrix columns. If the question is too broad to answer, ask one or two clarifiers and stop.
  2. Go to primary sources: official docs, specs, changelogs, benchmarks, the source itself, and the repo's own constraints. Date volatile facts.
  3. Capture evidence and cite as you go. Separate what the source says from your inference; keep a short trail of sources kept and dropped.
  4. Surface contradictions explicitly; what you cannot resolve becomes an open question, not a silent pick.
  5. Build the decision matrix: options as rows (include "do nothing / defer"), criteria as columns, cells filled with cited evidence.
  6. Recommend with uncertainty: the recommendation, your confidence, what would change it, and what remains unknown.
  7. Hand off to rfc (Options, Trade-offs) or adr (Alternatives Considered). Research is not the decision doc.

Guardrails

  • Primary sources over secondary. Cite load-bearing claims; date the volatile ones.
  • Not a literature review or a full report harness: bound the search to what the decision needs.
  • Flag uncertainty explicitly; keep contradictions visible.
  • Distinct from rfc (explores and decides at system altitude) and adr (records a settled decision). Research produces the cited evidence they consume.

What ships with it: 1 file

223 B alongside SKILL.md

agents/

Gives 0 of the 12 instructions most research analysis skills give in 342 tokens

Counted across 1,063 of the 1,754 authors here whose files we hold, read 2026-08-07

  • Generate a markdown reportin 32 of 1063, across 23 files
  • Cite each claim's sourcein 30 of 1063, across 15 files
  • Define the ideal customer profilein 20 of 1063, across 2 files
  • Search for companies matching the criteriain 20 of 1063, across 2 files
  • Assign a fit score from one to tenin 20 of 1063, across 2 files
  • Analyze the codebase to understand the productin 19 of 1063, across 1 file
  • Ask clarifying questions about the value propositionin 19 of 1063, across 1 file
  • Look for signals of immediate needin 19 of 1063, across 1 file
  • Identify the target decision maker rolein 19 of 1063, across 1 file
  • Suggest a personalized contact strategyin 19 of 1063, across 1 file
  • Provide conversation starters for outreachin 19 of 1063, across 1 file
  • Format results in a scannable markdown templatein 19 of 1063, across 1 file

Said here and by no other author read

  • frame the question and criteria first
  • date volatile facts
  • cite sources as you capture evidence
  • surface unresolved contradictions as open questions
  • build a decision matrix with cited evidence
  • include a do nothing option

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 326,629. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.