CtrlK
BlogDocsLog inGet started
Tessl Logo

risk-manager

Monitor portfolio risk, R-multiples, and position limits. Creates hedging strategies, calculates expectancy, and implements stop-losses.

52

Quality

58%

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 ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/risk-manager/SKILL.md

The canonical home for this skill is risk-manager in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

50%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 body is a compact, well-sectioned overview of risk-management focus areas and a numbered approach, but it leans on generic instruction boilerplate and offers only one concrete formula with no validation checkpoints. Its single external reference is a broken path, undercutting progressive disclosure.

Suggestions

Replace generic Instruction bullets with concrete, executable guidance — e.g. explicit position-sizing formula, a VaR calculation snippet, or a stop-loss placement rule.

Add validation checkpoints to the Approach sequence (e.g. 'Confirm total portfolio risk stays below X% before adding a position') given the financial consequences.

Fix or remove the dangling 'resources/implementation-playbook.md' reference; if a playbook is intended, create it under references/ and link with a clear 'See ... for details' signal.

DimensionReasoningScore

Conciseness

The body is mostly lean, but generic Instructions boilerplate ('Clarify goals, constraints, and required inputs', 'Apply relevant best practices and validate outcomes') adds little Claude doesn't already know; not a 4 because those padded lines could be trimmed, not a 2 because most content earns its place.

3 / 5

Actionability

One concrete detail — the expectancy formula '(Win% × Avg Win) - (Loss% × Avg Loss)' — but most Approach steps are high-level ('Size positions based on account risk percentage') with no executable specifics; matches score-3 (some concrete guidance, incomplete), below 4 for missing key execution details.

3 / 5

Workflow Clarity

A clear numbered 1–7 sequence exists, but there are no validation checkpoints or feedback loops despite stop-loss/position-sizing steps carrying financial risk; matches score-3 (steps listed, checkpoints missing/implicit), below 4 for absent validation.

3 / 5

Progressive Disclosure

Sections are reasonably organized (Use when, Focus Areas, Approach, Output), but the sole external reference 'resources/implementation-playbook.md' points to a non-existent path with no such bundle file present; not a 4 because the only reference is broken, not a 2 because section structure is sound.

3 / 5

Total

12

/

20

Passed

Description

66%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 clearly states what the skill does with several concrete, domain-specific actions and natural trigger terms, but it omits any 'Use when...' guidance, leaving the activation context implicit. It is specific and distinctive yet falls short on completeness.

Suggestions

Add an explicit trigger clause, e.g. 'Use when managing portfolio risk, sizing positions, or designing hedges and stop-losses.'

Include common synonyms users might say — drawdown, VaR, Kelly criterion, position sizing — to broaden natural trigger coverage.

Tighten actions toward granular outputs (e.g. 'compute expectancy and R-multiples', 'set stop-loss and take-profit levels') to push specificity toward comprehensive.

DimensionReasoningScore

Specificity

Lists several concrete actions — 'Monitor portfolio risk, R-multiples, and position limits', 'Creates hedging strategies', 'calculates expectancy', 'implements stop-losses' — with only minor coverage gaps, matching the score-4 anchor; not a 5 because the actions stay at domain level rather than granular specifics.

4 / 5

Completeness

The 'what' is clear, but there is no 'Use when...' clause or equivalent explicit trigger guidance, which per the guidelines caps completeness at 3; not a 4 because 'when' is entirely missing rather than merely weak.

3 / 5

Trigger Term Quality

Natural trading terms a user would say ('portfolio risk', 'R-multiples', 'hedging strategies', 'stop-losses') give good coverage; not a 5 because common synonyms like drawdown, VaR, or Kelly are absent.

4 / 5

Distinctiveness Conflict Risk

The trading-risk niche ('R-multiples', 'expectancy', 'hedging', 'stop-losses') is mostly distinct with only minor overlap risk; not a 5 because it lacks explicit trigger phrases that fully separate it from adjacent finance skills.

4 / 5

Total

15

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-Skills
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.