drawdown-circuit-breaker

Evaluate account-level drawdown circuit breaker rules from trader-memory-core state and decide whether new trade risk is allowed today. Uses realized P&L, losing-streak cooldowns, and weekly/monthly drawdown limits without any external API.

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

88%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.

A well-structured, highly actionable skill body with executable commands, explicit validation and fail-closed feedback loops, and real one-level-deep references. The main weaknesses are mild verbosity in the dense validation prose and two dangling resource paths that are not present in the bundle.

Suggestions

Fix or qualify dangling resource references: either bundle requirements.txt and the trader-memory-core thesis.schema.json, or mark them as external dependencies owned by another skill.

Tighten the Step 1 duplicate-ID and fail-closed paragraphs into a short bulleted rule list, and unwrap the hard-wrapped lines in the Exchange Calendar Contract section.

Avoid duplicating the full defaults table in both SKILL.md and references/circuit_breaker_framework.md — keep a summary in the body and defer details to the reference.

Dimension	Reasoning	Score
Conciseness	The body is efficient and assumes competence — every section carries skill-specific policy (fail-closed rules, duplicate-ID handling, ET calendar semantics) rather than concepts Claude already knows. Not 5 because the dense validation paragraphs in Step 1 and the awkward hard-wrapped prose in the "Exchange Calendar Contract" section could be tightened, and the defaults table duplicates content in references/circuit_breaker_framework.md.	4 / 5
Actionability	Fully executable, copy-paste-ready guidance: complete CLI invocations with all flags (verified --state-dir and --output-dir have defaults, so even the abbreviated Step 3 command runs as-is), a JSON config example, a full decision-output schema, and a recommendation interpretation table. Covers the common cases end to end.	5 / 5
Workflow Clarity	A clear four-step sequence (read state, evaluate rules, override thresholds, interpret decision) with explicit validation checkpoints and a repair-and-rerun feedback loop ("Repair the warnings and rerun before taking new risk"), plus data_quality/warnings signaling for error recovery. The skill is read-only, so the destructive-operation cap does not apply.	5 / 5
Progressive Disclosure	Good structure: the body stays an overview, the Resources section clearly signals one-level-deep pointers, and both referenced bundle files (scripts/check_circuit_breaker.py, references/circuit_breaker_framework.md) exist. Not 5 because two referenced paths are absent from the bundle (skills/trader-memory-core/schemas/thesis.schema.json and the mentioned requirements.txt), leaving minor navigation gaps.	4 / 5
	Total	18 / 20 Passed

Description

70%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.

A specific, well-differentiated description with concrete capability language, but it lacks an explicit "Use when..." trigger clause, which both caps completeness and leaves natural trigger phrases implicit. Adding a trigger sentence with common synonyms (loss limits, trading halts, risk gates) would raise completeness and trigger-term quality.

Suggestions

Add an explicit trigger clause, e.g. "Use when screening or sizing new trades, after a losing streak, or when checking daily/weekly/monthly loss limits."

Include common user-facing synonyms such as "loss limit", "trading halt", or "risk gate" alongside "circuit breaker" to broaden natural trigger coverage.

Mention the concrete output (a circuit_breaker_decision JSON/markdown report) so the "what" fully covers what the skill produces.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions and mechanisms — "Evaluate account-level drawdown circuit breaker rules", "decide whether new trade risk is allowed today", "realized P&L, losing-streak cooldowns, and weekly/monthly drawdown limits" — with minor gaps such as no mention of the output artifact or input file types. Not 5 because coverage is not comprehensive; not 3 because it goes well beyond 1-2 actions.	4 / 5
Completeness	The "what" is clear and specific, but there is no "Use when..." clause or equivalent explicit trigger guidance; "whether new trade risk is allowed today" only weakly implies when to reach for the skill. Per the rubric guideline, a missing explicit trigger clause caps completeness at 3.	3 / 5
Trigger Term Quality	Contains natural domain keywords a trader would say — "drawdown", "circuit breaker", "losing-streak", "cooldown", "realized P&L" — but misses common variations like "loss limit", "trading halt", or "risk gate". Not 5 because synonym coverage is incomplete; clearly above 3 given multiple natural, specific terms.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche anchored to a named source system ("trader-memory-core state") with distinctive mechanisms ("losing-streak cooldowns", "weekly/monthly drawdown limits"), making confusion with generic risk-management or market-exposure skills unlikely. Matches the anchor for clear niche with distinct triggers and minimal conflict risk.	5 / 5
	Total	16 / 20 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: tradermonty/claude-trading-skills
Path: skills/drawdown-circuit-breaker/SKILL.md
Commit: eab8d5c

Reviewed: 8 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.