research-discipline

A short self-bias checklist to run at the START of any investment research task (stock screen / sector study / company deep-dive). Four biases that systematically warp AI research — leader-bias (only big caps), English-bias (miss JP/KR/TW players), narrative-bias (chase concept labels), confirmation-bias (only bullish evidence) — plus recency-bias. Load this first, then research with the corrections in mind. Not a workflow, just a 60-second attitude reset that materially improves coverage and honesty.

Quality

92%

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

100%

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

A tight, well-organized instruction skill that delivers concrete copy-paste query corrections, a clear sequenced workflow with a verification checkpoint, and clean one-level cross-references to sibling skills, with no redundant concept explanations.

Dimension	Reasoning	Score
Conciseness	Lean table-based body that assumes Claude's competence and never pads with definitions of what a bias is; every row and the short "How to apply" list earn their tokens.	3 / 3
Actionability	The Correction column gives copy-paste-ready, executable guidance ("add `small cap` / `mid cap` / `supply chain` to queries", "search the bear case ('X risks / problems / bear case')", "Cite at least one disconfirming data point"), which is concrete and specific despite being instruction-only.	3 / 3
Workflow Clarity	A clear 4-step apply sequence with an explicit post-research re-check checkpoint ("did I cite any disconfirming evidence? did I miss a non-English player? is any key figure stale?"), satisfying the simple-skill allowance for a clean sequenced workflow.	3 / 3
Progressive Disclosure	Under 50 lines with no external bundle files needed; sections are well-organized (bias table, apply steps, sibling-skill cross-references) and the cross-references point one level out to complementary skills rather than nesting into bundle files.	3 / 3
	Total	12 / 12 Passed

Description

85%

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 pairing concrete bias-correction examples with an explicit when-trigger and a distinct niche. Its only weakness is trigger-term quality, where good natural domain terms are mixed with jargon bias names a user would not naturally say.

Suggestions

Add an explicit "Use when..." clause with common user phrasings (e.g., "Use when researching a stock, screening a sector, or doing a company deep-dive") to broaden natural trigger coverage.

Soften or supplement the internal bias labels (leader-bias, English-bias, narrative-bias, confirmation-bias) with plain-language synonyms a user might actually say so they read as triggers rather than jargon.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions and bias-correction pairs ("only big caps", "miss JP/KR/TW players", "chase concept labels", "only bullish evidence") rather than a single vague domain description.	3 / 3
Completeness	Clearly answers both what ("A short self-bias checklist... Four biases...") and when with an explicit trigger ("to run at the START of any investment research task (stock screen / sector study / company deep-dive)"), so it is not capped at 2 by the missing-Use-when rule.	3 / 3
Trigger Term Quality	Includes natural domain terms a user would say ("investment research", "stock screen", "sector study", "company deep-dive"), but the named biases ("leader-bias", "narrative-bias") are technical jargon users would not naturally say and common phrasing variations are not covered.	2 / 3
Distinctiveness Conflict Risk	Has a clear niche (a self-bias attitude reset for investment research) with distinct triggers and explicit differentiation from sibling skills (financial_rigor, cross_validate, report_audit), making misfires unlikely.	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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: HKUDS/Vibe-Trading
Path: agent/src/skills/research-discipline/SKILL.md
Commit: 8643fcd

Reviewed: 2 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.