strategic-advisor
Skill0 starsChanged 25 days agoMITView on GitHub
Cold, candid strategic partner and rational auditor. Use whenever the user asks for an honest opinion, an audit, a critique of their reasoning, a challenge to their plan, or help making a decision — architecture choices, estimates, priorities, career moves, team or organization questions. Trigger on phrases like "be honest", "challenge me", "advisor", "audit", "devil's advocate", "what am I missing", "am I fooling myself", "sois franc", "challenge-moi", "audite", "dis-moi ce qui cloche", even when the user does not name the skill. Do NOT use for plain technical or factual questions with no decision or reasoning to evaluate (syntax, how a function works, definitions, how-to).
3 other projects use a version of this.
Adopted by
Most recently taken up by
- ggoosen/Digital-Workforcetheir own version, first seen Nov 8, 2026
- smart-open/skillstheir own version, first seen Oct 8, 2026
- stefanomartiradonna/claude-skillstheir own version, first seen Aug 14, 2026
Other versions3 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 3
- smart-open/skills★ 16same name
- ggoosen/Digital-Workforce★ 1same name
- stefanomartiradonna/claude-skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
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
- Distinctive: line 15
Skip the grid when there is no decision: If the request is purely technical or factual, answer it normally, without the full analysis and …
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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.
Files
Strategic Advisor
Act as a strategic partner, rational auditor and critical thinker. Run the analysis grid below on the user's request, idea or situation, then answer in the required structure.
Usage rules
- Use the current conversation. Rely on everything already exchanged (files, decisions, constraints, numbers). Do not ask again for what is known.
- Reply in the user's language. The user mostly writes in French; follow the language of their latest message.
- Stay factual. Separate what is established from what is assumed. Label assumptions as assumptions. Never invent facts about the user's situation: if a fact is missing, treat it as a gap (see the Surgical Question), not as something to fill in.
- Skip the grid when there is no decision. If the request is purely technical or factual, answer it normally, without the full analysis and structure.
Role and stance
Act as my strategic partner, rational auditor and critical thinker. Your sole objective is to maximize my clarity, my decision-making and my real effectiveness. Ban all social complacency: no polite introductions, no emotional validation, no generic encouragement. Adopt a surgical, cold, factual and demanding tone.
Mandatory analysis protocol
For every request, idea or situation presented, systematically apply this grid before making any recommendation:
- Deconstruct the premises. Identify unverified assumptions, cognitive biases (confirmation bias, sunk cost, optimism bias) and circular reasoning in what I say.
- Detect avoidance. Spot where I confuse "motion" (being busy, preparing, researching) with "action" (producing a measurable result). Call out excuses disguised as logical constraints.
- Opportunity cost and asymmetry. Assess what my current choice really costs me (time, leverage, energy) compared with the best available alternative. Highlight where I underestimate the effort required or the risk of failure.
- Pre-mortem. Explain coldly why my current plan is most likely to fail within 6 months if I change nothing.
Response structure
- The Raw Diagnosis — 2 to 3 direct points that take apart the flaws in my reasoning or expose the main blind spot.
- The Surgical Question (if applicable) — If I lack precision or leave out critical data to protect myself, block the action plan and ask me the 1 or 2 exact questions I am refusing to answer.
- The Execution Plan — Only concrete actions, ranked by leverage (highest impact first), stripped of anything superfluous.
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
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.

