CtrlK
BlogDocsLog inGet started
Tessl Logo

bear-research

Use this skill for building the strongest possible bearish case, identifying downside risks, negative technical patterns, and adverse fundamental factors.

56

Quality

62%

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

Fix and improve this skill with Tessl

tessl review fix ./packages/tentacles/Trading/Mode/ai_trading_mode/resources/skills/bear_researcher/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

57%

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

The content is well-organized with a concrete output template and clear bear-case sequence, but it is held back by minor concept over-explanation, generic best-practice padding, absent data-gathering methods, and lack of explicit validation checkpoints. It reads as a solid reference framework more than a fully executable, lean workflow.

Suggestions

Tighten conciseness by removing explanations of basic concepts Claude already knows (e.g., the death-cross parenthetical) and trimming the generic Best Practices items.

Improve actionability by specifying concrete data sources or methods for identifying the listed technical/fundamental patterns rather than only listing them.

Add an explicit validation/self-check checkpoint in the bear-case workflow (e.g., verify each cited risk against current data and confirm counter-bull rebuttals address the strongest bull points before finalizing).

DimensionReasoningScore

Conciseness

The body is mostly lean bullet lists, but includes minor unnecessary explanations of concepts Claude already knows (e.g., "Death cross (50 MA crosses below 200 MA)") and a somewhat generic 8-item Best Practices section ("Be intellectually honest", "Avoid confirmation bias"). It is not a 3 because of this padding; not a 1 because the bulk is efficient reference material rather than verbose prose.

2 / 3

Actionability

It gives concrete guidance — specific indicator checklists, a structured bear-case template, and a copy-paste JSON output example — but no data sources or methods for actually identifying the patterns. It is not a 3 because the analysis guidance is a checklist rather than fully executable steps; not a 1 because the output template and indicator lists are concrete and actionable as a framework.

2 / 3

Workflow Clarity

Section 4 provides a clear numbered sequence (Core Thesis → Key Risks → Price Targets → Timeline → Catalysts) and the counter-bull section acts as a soft balancing step, but there are no explicit validation checkpoints. It is not a 3 because no explicit validate/verify step or feedback loop is present; not a 1 because a clear sequence does exist.

2 / 3

Progressive Disclosure

No bundle files exist and the single SKILL.md is well-organized into clearly headed sections (Overview, five numbered Instruction subsections, Output Format, Best Practices) with easy navigation and no nested references. It is not a 2 because the content is appropriately self-contained and well-structured for its scope rather than poorly organized or in need of splitting.

3 / 3

Total

9

/

12

Passed

Description

67%

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 distinguishes a clear bearish-analysis niche, but its trigger-term variety is limited and it lacks an explicit situational 'when' clause, relying on an implied trigger. Tightening the when-guidance and broadening natural keywords would raise the weaker dimensions.

Suggestions

Add an explicit situational trigger, e.g. "Use when the user asks for a bearish case, downside analysis, or short thesis for a trading position."

Broaden natural trigger terms to include variations users actually say, such as "short thesis", "sell case", or "bear argument", alongside the current formal phrasing.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions — "building the strongest possible bearish case, identifying downside risks, negative technical patterns, and adverse fundamental factors" — matching the anchor that names several specific actions. It is not a 2 because it goes beyond naming a single domain action to enumerate several distinct bearish-analysis activities.

3 / 3

Completeness

The description clearly states what the skill does but the "when" is only implied via "Use this skill for..." rather than an explicit situational trigger (e.g., "when the user asks for a bearish analysis"). Per the guideline, a missing explicit 'Use when...' situational trigger caps completeness at 2; it is not a 1 because both what and an implied when are present.

2 / 3

Trigger Term Quality

It includes relevant domain keywords ("bearish case", "downside risks", "technical patterns", "fundamental factors") but misses common variations a user might naturally say (e.g., "short thesis", "sell case", "bear argument"). It is not a 3 because the term set is formal and lacks the variation coverage of the top anchor; not a 1 because several natural trading terms are present.

2 / 3

Distinctiveness Conflict Risk

The bearish-analysis niche ("bearish case", "downside risks") is a clear, distinct trigger unlikely to fire for unrelated skills. It is not a 2 because the directional specificity (bear/downside) separates it from generic market-analysis skills.

3 / 3

Total

10

/

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
Drakkar-Software/OctoBot
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.