agentleFS
KotrotsosKotrotsos/claude-skills-non-coding/consultant-translator/SKILL.md

consultant-translator

Skill8 starsChanged 6 months agoMITView on GitHub

Use this skill when reading a consulting deliverable (Deloitte, McKinsey, Bain, Accenture, BCG, EY, KPMG, PwC, or in-house consulting) and needing to extract the actual recommendation under the framework layer. Triggers on phrases like "translate this consultant deck", "what is this deck actually saying", "summarize this McKinsey report", or when the user shares a consulting document. Produces a one-page operator-friendly translation with assumptions flagged.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Do not dismiss the work wholesale.

    line 61
  2. Distinctive:

    If the document is genuinely strong, say so.

    line 62
  3. Distinctive:

    When you see these, dig for the actual claim.

    line 79

≈ “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

Consultant-Speak Translator

When to use this skill

A consulting deliverable lands in the user's inbox. It has frameworks, color-coded matrices, and confidence-inspiring language. The user needs to know in plain English: what are they actually recommending, what is recycled from prior engagements, and what assumptions have not been stated.

Input the user provides

  • The consulting document (deck, report, memo, slides, PDF)
  • Optionally: the engagement context (what problem the firm was hired to solve, what stage the engagement is at)
  • Optionally: the user's reaction to the document so far

What this skill does

  1. Reads the entire document and identifies the actual recommendation under the framework layer
  2. Flags generic language that maps to nothing specific
  3. Identifies assumptions the document treats as obvious but are actually contestable
  4. Distinguishes engagement-specific analysis from boilerplate the firm uses across clients
  5. Produces a one-page translation in the structure below.

Output structure

# Translation: [Document title]
*Source: [firm name]. Page count: [n]. Read time saved: ~[estimate].*

## What they are actually recommending
2-3 sentences in plain language. Strip the frameworks, name the action.

## Their case (in 4 bullets)
- The evidence point that does the most work
- The assumption that holds it up
- The benchmark or comparison they lean on
- The risk they acknowledge

## What they are not saying
- Assumption [X] is treated as obvious. It is not.
- They use [framework term] to mean [specific thing]. The framework adds no insight beyond [thing].
- The cost projection assumes [Y], which may or may not hold for this organization.

## Recycled vs. specific
- Recycled: [specific phrases, slides, or claims that appear in their public materials or prior engagements]
- Specific to you: [the parts that demonstrate real engagement with your situation]

## Questions to push back on
- 2-4 sharp questions the user should ask before the next meeting with the firm.

## Honest read
2 sentences. Is this advice worth following, partially following, or pushing back on? Why?

Calibration notes

  • The "What they are not saying" section is the highest-value part. Most consulting documents are not wrong, they are incomplete in specific ways that the framework hides.
  • Be specific about which assumptions are contestable. "Assumes 8% organic growth" is useful. "Has questionable assumptions" is not.
  • Do not dismiss the work wholesale. Good consulting work exists. The job here is to extract the real recommendation from the packaging, not to undermine the engagement.
  • If the document is genuinely strong, say so. Calibration is honest assessment, not contrarianism.

Consulting clichés to watch for

These phrases tend to wrap one specific underlying claim, or nothing at all. When you encounter them, identify which:

  • "Strategic enabler" / "key enabler"
  • "Value chain transformation"
  • "Next-generation operating model"
  • "Holistic approach"
  • "End-to-end solution"
  • "Lever" (used as noun for "thing we could change")
  • "Capability uplift"
  • "Future-state architecture"
  • "North star metric" (only meaningful if a specific one is named)
  • "Center of excellence"

When you see these, dig for the actual claim. If there is no specific claim underneath, flag it.

When NOT to use this skill

  • Documents that are already written for operators (internal memos, peer-to-peer briefings)
  • Academic papers (different filter)
  • Vendor pitches (use a different evaluation lens)

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.