CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

73

Quality

91%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

The canonical home for this skill is first-principles-thinking in mindfold-ai/Trellis

SKILL.md
Quality
Evals
Security

Quality

Content

92%Weight 40%Scale 1-5

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

The content is highly actionable and well-structured, with a clear phased workflow, mandatory gates, validation checkpoints, and a clean progressive-disclosure layout pointing to five real reference files. The only weakness is mild verbosity and some redundancy between the inline summary tables and the reference files.

Suggestions

Tighten the inline Complementary Tools, Bias Awareness, and Problem Decomposition tables to a single reference line each, since each already has a dedicated reference file, to reduce redundancy and token cost.

Trim the 'How to identify axioms' and axiom-definition prose, which explains concepts Claude already understands, in favor of the concrete gate criteria.

Consider moving the Trellis Integration section into a reference file, as it is project-specific and inflates the body for users not on a Trellis-managed project.

DimensionReasoningScore

Conciseness

The body is mostly efficient prose with actionable structure, but at roughly 400 lines it includes some redundancy (e.g., Complementary Tools, Bias, and Decomposition tables that summarize material also covered in the reference files) and light over-explanation of concepts like what an axiom is.

4 / 5

Actionability

Provides copy-paste-ready templates (axiom block, assumption table, reasoning chain, full output format) with concrete examples and explicit minimum-depth requirements per phase, leaving no ambiguity about what to produce.

5 / 5

Workflow Clarity

A clearly sequenced 6-phase process with mandatory phase gates, a phase-artifact table, an anti-drift progress tracker, and an explicit validation checkpoint (3 questions plus a stress-test) that forms a feedback loop ensuring no phase is skipped.

5 / 5

Progressive Disclosure

The body acts as an overview that is well-organized into labeled sections and signals one-level-deep references (e.g., '> Deep methodology: references/axiom-based-reasoning.md'); all five referenced files exist on disk and are indexed in a closing reference table, making navigation easy.

5 / 5

Total

19

/

20

Passed

Description

91%Weight 40%Scale 1-5

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

The description is strong: it explicitly covers both what the skill does and when to use it, with an unusually thorough set of natural trigger phrases in English and Chinese. Specificity is the only slight weakness, as the described actions are conceptual rather than concretely enumerated operations.

DimensionReasoningScore

Specificity

Names the domain and several concrete actions such as 'decompose a problem to its fundamentals', 'evaluate decisions, designs, or strategies without relying on analogies, conventions, or "best practices"', and 'challenge assumptions', but the actions are conceptual rather than listing a comprehensive set of specific operations.

4 / 5

Completeness

Clearly states what the skill does ('Systematic first principles thinking... decompose a problem to its fundamentals') and explicitly answers when via a 'Use when...' clause with concrete trigger phrases.

5 / 5

Trigger Term Quality

Comprehensive coverage of natural trigger phrases in both English and Chinese including synonyms and natural phrasings like 'is this the right approach', 'why are we doing it this way', and 'challenge assumptions'.

5 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (first-principles / assumption-challenging reasoning) with distinct trigger phrases that minimize conflict risk, though it has minor overlap with general reasoning or critical-thinking skills.

4 / 5

Total

18

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_field

'metadata' should map string keys to string values

Warning

Total

15

/

16

Passed

Repository
mindfold-ai/Trellis
Reviewed

Table of Contents

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.