investor-lenses

Named investor reasoning frameworks packaged as reusable analytical lenses — 12 lenses (deep value, quality franchise, inversion, scuttlebutt growth, GARP, cycle positioning, debt cycle, forensic short, cost drag, right-business, weak-system contrarian, three questions) that stack on top of evidence already gathered, each with ordered priority signals, hard disqualifiers, and documented failure modes.

Quality

83%

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

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 an exemplary overview-style skill: lean, opinionated, and tightly structured around a falsifiable procedure with explicit checkpoints and an output contract. Its only modest gap is the lack of any executable code/command, which is justified for an instruction-only analytical skill.

Dimension	Reasoning	Score
Conciseness	The body is lean and efficient, assuming Claude's competence; it never explains what an investor or a balance sheet is, and every section (what a lens is, the five-step run, stacking protocol, anti-patterns, output contract) earns its place, matching the anchor 5 "every token earns its place".	5 / 5
Actionability	Concrete, executable procedural guidance is given (ordered priority signals, hard disqualifier vetoes, the binding output contract) rather than vague direction, but there is no copy-paste code or command — appropriate for an instruction-only skill per the scoring notes, placing it at anchor 4 (mostly executable, minor gaps) rather than anchor 5.	4 / 5
Workflow Clarity	The five-step run is a clear numbered sequence with explicit validation checkpoints ("Freeze the evidence before choosing the lens", "Hit a hard disqualifier → stop and report the veto", "Run the misuse check") and a feedback loop against the risky act of lens shopping, matching anchor 5.	5 / 5
Progressive Disclosure	The SKILL.md is a clear overview with a lens-index table of one-level-deep references, all 12 referenced files exist under references/ and are linked per-lens, and detail is appropriately split out (verified each body link resolves to a real file), matching the anchor 5 "clear overview with well-signaled one-level-deep references; easy navigation".	5 / 5
	Total	19 / 20 Passed

Description

67%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 specific and distinct, clearly conveying the skill's purpose and naming all 12 lenses. Its main weakness is the absence of an explicit, natural-language "Use when…" trigger clause and trigger terms phrased the way a user would actually ask for the skill.

Suggestions

Add an explicit "Use when…" clause naming the situations a user would voice, e.g. "Use when weighing an investment thesis against a named investor's methodology, or when you need a falsifiable second opinion on already-gathered evidence."

Replace some framework jargon ("GARP", "forensic short") with natural trigger phrases users say ("is this cheap enough", "the accounting smells", "is the multiple sane after years of growth").

Lead with the skill's action before enumerating the 12 lenses, so the trigger terms appear before the long parenthetical list.

Dimension	Reasoning	Score
Specificity	Names 12 concrete frameworks plus specific structural actions ("ordered priority signals, hard disqualifiers, and documented failure modes"), landing above anchor 3 (1-2 actions) but short of the fully comprehensive anchor 5 since the per-lens actions are uniform rather than distinctly enumerated.	4 / 5
Completeness	The "what" is explicit (reusable analytical lenses with priority signals, disqualifiers, failure modes) and a "when" is implied ("stack on top of evidence already gathered", situation framing), but there is no explicit "Use when…" trigger clause, so it sits between anchor 3 (clear what, weak when) and anchor 5 (explicit trigger phrase).	4 / 5
Trigger Term Quality	Domain terms like "deep value", "GARP", "forensic short", and "cycle positioning" are present, but they are framework jargon rather than the natural phrases a user would say; common user variations and synonyms are missing, matching the anchor 3 "some relevant keywords but missing common variations".	3 / 5
Distinctiveness Conflict Risk	The named-investor-lens-as-falsifiable-procedure niche is clearly distinct with minimal conflict risk, but minor overlap remains with a generic analysis or stock-screening skill, so it is mostly distinct rather than a clean anchor 5.	4 / 5
	Total	15 / 20 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/investor-lenses/SKILL.md
Commit: 251b094

Reviewed: 3 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.