CtrlK
BlogDocsLog inGet started
Tessl Logo

thesis-tracker

AI Berkshire skill: 投资论文追踪:买入后的纪律系统. Source: skills/thesis-tracker.md.

56

Quality

63%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./codex-skills/thesis-tracker/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

77%

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

The body is a highly actionable, well-sequenced thesis-tracking workflow with concrete templates, tables, and validation checkpoints. Its main weaknesses are some motivational/philosophical padding and the absence of any bundle files or split-out references for progressive disclosure.

Suggestions

Trim the '设计理念' section and standalone quotes to the essential principle, or move them to a reference file, to reduce non-action tokens.

Split the reusable templates (5-sentence thesis, assumption/red-line/valuation tables) into a bundled reference file and link to it from the overview to improve progressive disclosure.

Add an explicit validate→fix→retry note around 'tools/financial_rigor.py verify-valuation' (what to do when verification fails) to strengthen the feedback loop.

DimensionReasoningScore

Conciseness

The body is mostly lean, concrete templates and tables, but the '设计理念' section and motivational quotes (李录, 凯恩斯, 段永平) add contextual/motivational padding that does not advance the action; it could be tightened without losing clarity.

2 / 3

Actionability

Provides copy-paste-ready artifacts: a 5-sentence thesis template, assumption/red-line/valuation-anchor tables, an explicit health-score formula, and a concrete command 'python3 tools/financial_rigor.py verify-valuation'.

3 / 3

Workflow Clarity

Clear two-mode sequence (建立论文 A0–A5, 追踪检查 B1–B7) with explicit checkpoints: assumption-status verification in B3, red-line trigger detection with mandated actions in B4, and valuation validation in A0.

3 / 3

Progressive Disclosure

No bundle files exist in references/scripts/assets, and all content (~220 lines) lives inline in one well-organized but monolithic file with no one-level-deep references to split-out detail; structure is good but file-based progressive disclosure is absent.

2 / 3

Total

10

/

12

Passed

Description

50%

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 a thin, metadata-laden title: a brief Chinese statement of the skill's purpose padded with 'AI Berkshire skill:' and 'Source:' labels. It conveys a domain but omits any 'Use when' trigger guidance and lists no concrete actions, leaving it at the mid-band across all dimensions.

Suggestions

Rewrite as a third-person capability statement listing concrete actions, e.g. 'Establishes, tracks, and scores investment theses after a buy...'.

Add an explicit 'Use when...' clause with natural trigger terms (e.g. 'use when reviewing a holding, checking a thesis, or deciding whether to hold/sell after earnings').

Remove the 'AI Berkshire skill:' prefix and 'Source: skills/thesis-tracker.md.' metadata from the description; keep those elsewhere if needed.

DimensionReasoningScore

Specificity

Names the domain ('投资论文追踪') and a general action framing ('买入后的纪律系统'), but only a single action is described rather than multiple concrete capabilities; the 'AI Berkshire skill:' prefix and 'Source:' metadata add no specificity.

2 / 3

Completeness

States a 'what' (a post-buy thesis-tracking discipline system) but provides no 'when'/'Use when' clause or equivalent explicit trigger guidance, which caps completeness at 2 per the guideline.

2 / 3

Trigger Term Quality

Contains some relevant investor-facing keywords ('投资论文', '追踪', '买入') but lacks common variations and any trigger guidance; the 'Source: skills/thesis-tracker.md.' fragment is metadata noise rather than a natural trigger term.

2 / 3

Distinctiveness Conflict Risk

The post-buy thesis-tracking niche is fairly specific and unlikely to conflict broadly, but the description offers no distinct explicit triggers that would separate it from adjacent research/analysis skills.

2 / 3

Total

8

/

12

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
xbtlin/ai-berkshire
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.