agentleFS
Sign inStart free
ray5273ray5273/kr-research-kit/skills/kr-sector-plan/SKILL.md

kr-sector-plan

Skill2 starsChanged 8 days agoMITView on GitHub

Scope Korean sector and industry research before drafting. Use when the user needs to define the exact sector, coverage boundary, time horizon, decomposition axes, deliverable mode, or research questions for a Korea-focused sector report, brief, comparison, or update. Do not use for writing the final sector report itself.

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 6 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill to turn a vague Korea sector request into an execution-ready research brief.

    line 8
  2. Distinctive:

    Keep the deliverable to planning.

    line 14
  3. Very specific:

    If the workspace is writable and the user wants a reusable planning artifact, write the brief to …

    line 15
  4. Distinctive:

    Read references/workflow.md for planning rules.

    line 30
  5. Distinctive:

    Read references/output-format.md for the required brief shape.

    line 31
  6. Distinctive:

    Prefer narrowing the scope over pretending the sector boundary is obvious.

    line 35
  7. Distinctive:

    Avoid numeric estimates at this stage unless the user explicitly asked for a scoping estimate and provided a source.

    line 38

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Korean Sector Plan

Use this skill to turn a vague Korea sector request into an execution-ready research brief.

Quick Start

  • Define the exact sector first. Resolve whether the user means a product category, a value-chain slice, a policy theme, or a listed-company basket.
  • Lock the output mode early: quick brief, full report, comparison, audit, or update.
  • Keep the deliverable to planning. Do not drift into writing the actual report or filling in unsupported numbers.
  • If the workspace is writable and the user wants a reusable planning artifact, write the brief to analysis-example/kr-sector/<sector>-리서치브리프.md.

Workflow

  1. Clarify the target sector. Normalize the user's wording into a sector definition that another agent can execute.
  2. Set the report boundary. Pin geography, time horizon, value-chain depth, end-market slices, and whether listed-company coverage is required.
  3. Choose the output mode. Route the request into quick brief, full report, comparison, audit, or update.
  4. List the key questions. State what the downstream research needs to answer, what can be omitted, and which assumptions are allowed.
  5. Hand off cleanly. Produce a short research brief and tailored outline that downstream sector skills can consume directly.

Read references/workflow.md for planning rules. Read references/output-format.md for the required brief shape.

Operating Rules

  • Prefer narrowing the scope over pretending the sector boundary is obvious.
  • Separate user intent from your assumptions.
  • Flag where the sector name overlaps with adjacent themes such as cloud, AI infrastructure, utilities, or software services.
  • Avoid numeric estimates at this stage unless the user explicitly asked for a scoping estimate and provided a source.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free