first-principles-thinking

Systematic first principles thinking for any problem domain. Use when the user says "analyze from first principles", "第一性原理", "从根本分析", "从零开始思考", "think from scratch", "question this design", "is this the right approach", "challenge assumptions", "挑战假设", "为什么要这样做", "有没有更好的方案", "why are we doing it this way", or needs to evaluate decisions, designs, or strategies without relying on analogies, conventions, or "best practices". Also triggers on "这个设计合理吗", "从本质上看", "回到基本面", "what's really true here", "what are we assuming", or any request to decompose a problem to its fundamentals.

Quality

87%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

85%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured methodology skill: clear sequenced phases with validation gates, concrete templates and tables, and clean one-level-deep references. The main drag on token efficiency is internal redundancy — gates and tool listings are restated in multiple tables.

Suggestions

Collapse the Phase Gates table (lines 188-197) and the Depth Standards table (lines 219-225) into the phase sections they restate, or keep only one consolidated gate summary, to remove duplicated content.

Merge the Phase 5 stress-test model table with the Complementary Tools Quick Reference so each complementary model appears in one place rather than two overlapping tables.

Reference files like axiom-based-reasoning.md are linked from multiple phases (Phase 0 and Phase 2); consolidate to a single canonical pointer plus the Reference Files table to reduce repeated cross-references.

Dimension	Reasoning	Score
Conciseness	The ~377-line body is mostly efficient and action-oriented (no padding about what concepts 'are'), but it repeats itself: the Phase Gates table and Depth Standards table re-summarize each phase's gate, and the Phase 5 stress-test table overlaps the Complementary Tools Quick Reference — so not every token earns its place.	2 / 3
Actionability	Highly actionable for an instruction-only skill: explicit gates ('≥3 axioms', '≥5 rows'), a copy-paste output-format template, an assumption-table schema with columns, and ✅/❌ depth examples give concrete executable guidance.	3 / 3
Workflow Clarity	Six phases (0-5) are clearly sequenced, each with an explicit validation Gate, a 'No artifact → no next phase' rule, an anti-drift progress tracker, and a Phase 5 validation checklist with feedback ('Go back and finish them').	3 / 3
Progressive Disclosure	All five referenced files exist under references/ and are signaled inline ('> Deep methodology: references/...') at one level deep, with a final Reference Files navigation table giving content + when-to-read; deep material is appropriately split out.	3 / 3
	Total	11 / 12 Passed

Description

90%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description: it pairs a clear what/when structure with unusually thorough bilingual trigger coverage and a distinctive first-principles niche. Its only weakness is that the 'what it does' half is somewhat abstract rather than a list of concrete actions.

Dimension	Reasoning	Score
Specificity	Names the domain ('first principles thinking for any problem domain') and a few actions ('decompose a problem to its fundamentals', 'evaluate decisions, designs, or strategies'), but does not list multiple concrete capabilities the way a score-3 anchor does; the 'what' leans abstract.	2 / 3
Completeness	Explicitly answers both what ('Systematic first principles thinking... decompose a problem to its fundamentals') and when ('Use when the user says...', 'Also triggers on...'), matching the score-3 anchor with explicit triggers.	3 / 3
Trigger Term Quality	Broad, natural coverage in both English ('analyze from first principles', 'think from scratch', 'challenge assumptions', 'why are we doing it this way') and Chinese ('第一性原理', '从本质上看', '回到基本面') — terms users would actually say.	3 / 3
Distinctiveness Conflict Risk	The first-principles framing and distinctive phrases ('decompose to its fundamentals', '从本质上看', '回到基本面') carve a clear niche unlikely to fire for unrelated skills, despite minor overlap with generic critique.	3 / 3
	Total	11 / 12 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_field	'metadata' should map string keys to string values	Warning

	Total	15 / 16 Passed

Repository: mindfold-ai/Trellis
Path: .agents/skills/first-principles-thinking/SKILL.md
Commit: 12e279a

Reviewed: 5 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.