TacoSkill LAB
TacoSkill LAB
HomeSkillHubCreatePlaygroundSkillKit
© 2026 TacoSkill LAB
AboutPrivacyTerms
  1. Home
  2. /
  3. SkillHub
  4. /
  5. rigorous-reasoning
Improve

rigorous-reasoning

6.6

by athola

105Favorites
130Upvotes
0Downvotes

Triggers: conflict, disagreement, debate, ethical, controversial, pushback Prevents sycophantic reasoning through checklist-based analysis, categorical integrity, and evidence-following to uncomfortable conclusions. Triggers (conflict-based): disagreement, conflict, debate, ethical question, controversial claim, interpersonal analysis, competing values, adjudication, "who is right", moral dilemma, harm assessment Triggers (red-flag self-monitoring): "I agree that", "You're right", "Great point", "Absolutely", "That's a fair point", "I can see why", agreement without validation, softening conclusions, hedging without evidence, retracting under pressure Use when: analyzing conflicts or disagreements, evaluating ethical claims, adjudicating competing positions, noticing sycophantic thought patterns, making truth claims in contested territory DO NOT use when: routine implementation tasks with no contested claims DO NOT use when: simple factual questions with clear answers CRITICAL: This skill overrides default conversational tendencies toward agreement. Agreement requires validity, accuracy, or truth, not politeness.

reasoning

6.6

Rating

0

Installs

Testing & Quality

Category

Quick Review

Highly effective skill addressing a genuine LLM weakness (sycophantic reasoning). The description clearly articulates trigger conditions (conflict-based and self-monitoring patterns) that would enable a CLI agent to invoke appropriately. Structure is excellent with modular organization and clear separation of concerns. Task knowledge is comprehensive with actionable protocols, checklists, and recovery procedures. The skill is novel in targeting behavioral patterns that standard prompting struggles with, though some benefit depends on whether LLMs can reliably self-monitor for these patterns. Minor gaps: the description could be slightly more concise for faster CLI parsing, and real-world effectiveness of self-monitoring triggers needs validation. Overall, this is a well-designed skill that meaningfully addresses expensive multi-turn correction cycles.

LLM Signals

Description coverage8
Task knowledge9
Structure9
Novelty8

GitHub Signals

127
16
1
71
Last commit 0 days ago

Publisher

athola

athola

Skill Author

Related Skills

playwright-experttest-masterdebugging-wizard

Loading SKILL.md…

Try onlineView on GitHub

Publisher

athola avatar
athola

Skill Author

Related Skills

playwright-expert

Jeffallan

6.4

test-master

Jeffallan

6.4

debugging-wizard

Jeffallan

6.4

code-reviewer

Jeffallan

6.4
Try online