bottleneck-hunter

AI Berkshire skill: 供应链瓶颈猎手：AI驱动的全球产业链瓶颈套利. Source: skills/bottleneck-hunter.md.

Quality

67%

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

Fix and improve this skill with Tessl

tessl review fix ./codex-skills/bottleneck-hunter/SKILL.md

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 strong, highly actionable research workflow with explicit sequencing, validation checkpoints, and concrete tooling/thresholds. Its weaknesses are length (conciseness) and a monolithic single-file structure with no progressive disclosure of templates or scan modes into reference files.

Suggestions

Split the report templates and hourly-scan mode into reference files (e.g. references/report-templates.md) and link them from SKILL.md to improve progressive disclosure.

Tighten repeated content — the full-scan and hourly-scan templates overlap and could share one parameterized template to cut length.

Move the detailed valuation red/yellow/green-light tables into a reference file while keeping the hard gates inline, reducing the inline token load without losing actionability.

Dimension	Reasoning	Score
Conciseness	The ~490-line body is substantive and mostly free of concepts Claude already knows, but it is padded by repeated report templates, dual scan modes, and criteria tables that could be tightened; it earns 'mostly efficient but could be tightened' rather than the lean anchor.	2 / 3
Actionability	Guidance is concrete and executable throughout: exact WebSearch query templates, real tool invocations ("python3 tools/twstock_data.py", "python3 tools/financial_rigor.py"), numeric valuation thresholds (PS>30x, 市值>TAM 20%), and copy-ready output templates — matching the fully-executable anchor.	3 / 3
Workflow Clarity	Steps 1-7 are explicitly sequenced with validation checkpoints ("估值检查必须执行不可跳过", mandatory 必填字段, 第五步正向/反向验证) and feedback loops (升级/降级/解除 bottlenecks), matching the clear-sequence-with-explicit-validation anchor.	3 / 3
Progressive Disclosure	No bundle directories (references/scripts/assets) exist and the skill is a single ~490-line file with all templates, criteria, and scan modes inline; sections are well-organized but content that should be split into referenced files is not, and the under-50-line simple-skill exception does not apply.	2 / 3
	Total	10 / 12 Passed

Description

57%

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 identifies a clear, distinctive niche but reads more like a source-tagged label than an invocation guide: it states the domain yet lacks a 'Use when...' trigger and carries meta-noise ('AI Berkshire skill', 'Source: ...'). Specificity and completeness are mid-tier because only one high-level action is named and no usage trigger is given.

Suggestions

Add an explicit usage trigger, e.g. 'Use when analyzing supply-chain bottlenecks, finding chokepoint arbitrage opportunities, or screening bottleneck-exposed stocks.'

List two or three concrete actions (e.g. 'maps supply-chain layers, scores bottleneck severity, screens listed companies') to lift specificity from one action to several.

Remove the meta-noise ('AI Berkshire skill:', 'Source: skills/bottleneck-hunter.md.') so the description frontmatter is purely user-facing.

Dimension	Reasoning	Score
Specificity	Names a concrete domain ("全球产业链瓶颈套利" / global supply-chain bottleneck arbitrage) and an action (套利/挖掘), but stops at one high-level action rather than listing multiple specific operations, matching the 'names domain and some actions but not comprehensive' anchor.	2 / 3
Completeness	It states what the skill does but provides no "Use when..." trigger or equivalent usage guidance; per the rubric a missing explicit trigger caps completeness at 2.	2 / 3
Trigger Term Quality	"供应链瓶颈" and "产业链瓶颈套利" are natural domain terms a user might say, but coverage is thin with no common variations, and the meta-noise ("AI Berkshire skill", "Source: skills/bottleneck-hunter.md") crowds out usable triggers.	2 / 3
Distinctiveness Conflict Risk	The niche is sharp and specific (AI-driven supply-chain bottleneck arbitrage) with distinctive trigger terms, making it unlikely to fire for unrelated skills; not the level below because it is clearly more specific than 'works with document files'.	3 / 3
	Total	9 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: xbtlin/ai-berkshire
Path: codex-skills/bottleneck-hunter/SKILL.md
Commit: 634a399

Reviewed: 1 day 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.