CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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

77%

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 ./skills/drawdown-circuit-breaker/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

73%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 delivers an executable, well-sequenced workflow with strong validation and fail-closed feedback loops, and the bundle is organized with a real one-level-deep reference. It is dragged down by a dense inline edge-case paragraph in Step 1 and a dangling requirements.txt reference with no install command.

Suggestions

Move the Step 1 edge-case validation detail (duplicate thesis IDs, legacy terminal fallback, lifecycle history rules, non-finite ledger events) into references/circuit_breaker_framework.md, keeping only the fail-closed behavior summary in SKILL.md.

Replace "Install `requirements.txt`" with the actual command (e.g. `pip install -r requirements.txt`) and ship the file, or drop the mention if the script is stdlib-only.

Tighten the Exchange Calendar Contract section, which repeats the `--as-of` guidance already given in Step 2, and note in Resources which bundled paths exist versus external cross-skill paths.

DimensionReasoningScore

Conciseness

The body is mostly efficient (compact rule tables, ready-to-run commands, a single output example), but Step 1 inlines roughly 180 words of script-internal edge-case validation detail (duplicate thesis IDs, legacy terminal fallback, lifecycle history rules, non-finite ledger handling) that the script enforces automatically and that belongs in references/circuit_breaker_framework.md — more than the "minor instances" of the anchor above.

3 / 5

Actionability

Three complete, copy-paste CLI invocations with all flags, a JSON config example, and a full output JSON example cover the common cases, but "Install `requirements.txt` before running the checker" provides no install command and the file is absent from the bundle — a minor executability gap that keeps it below fully copy-paste ready.

4 / 5

Workflow Clarity

Four clearly sequenced steps each carry concrete commands, and the skill includes an explicit validation checkpoint plus feedback loop (data_quality/warnings fields, fail-closed HALTED on incomplete state, "Repair the warnings and rerun before taking new risk"); the operation is read-only analysis, so the destructive/batch cap does not apply.

5 / 5

Progressive Disclosure

Good structure with a Resources section and a verified one-level-deep reference (references/circuit_breaker_framework.md exists and contains no nested references), but two referenced paths do not resolve within the bundle (`requirements.txt`, `skills/trader-memory-core/schemas/thesis.schema.json`) and the dense edge-case content inlined in Step 1 would be better split out — minor organization gaps rather than the clean split of the top anchor.

4 / 5

Total

16

/

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.

The description is specific, third-person, and highly distinctive within its trading-risk niche, with good natural keyword coverage. Its main weakness is the complete absence of a "Use when..." trigger clause, which caps completeness and limits discoverability.

Suggestions

Add an explicit trigger clause, e.g. "Use before screening or sizing any new swing trade, after a losing trade, or when daily, weekly, or monthly loss limits may have been breached."

State the concrete output ("produces a circuit_breaker_decision JSON/markdown report") so the what-then-what outcome is fully specified.

Add one or two natural synonyms traders would say, such as "trading halt" or "risk gate", to broaden trigger coverage.

DimensionReasoningScore

Specificity

"Evaluate account-level drawdown circuit breaker rules" and "decide whether new trade risk is allowed today" name the domain with concrete actions and mechanisms ("realized P&L, losing-streak cooldowns, and weekly/monthly drawdown limits"), but only two core verbs are listed, leaving minor gaps versus the comprehensive multi-action coverage of the top anchor.

4 / 5

Completeness

The "what" is clear (evaluate drawdown circuit breaker rules and decide whether new trade risk is allowed), but there is no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 3 per the rubric guideline; it is not 4 because the "when" is entirely absent rather than merely imprecise.

3 / 5

Trigger Term Quality

Natural domain terms a trader would say are present ("drawdown", "circuit breaker", "losing-streak", "cooldown", "realized P&L"), matching good-but-not-comprehensive coverage; common synonyms like "trading halt" or "stop trading" are missing, so it does not reach the synonym-and-variation coverage of the 5 anchor.

4 / 5

Distinctiveness Conflict Risk

"drawdown circuit breaker rules from trader-memory-core state" carves out a clear niche with distinct triggers (realized P&L, losing-streak cooldowns, weekly/monthly drawdown limits) and would not plausibly fire for an unrelated skill.

5 / 5

Total

16

/

20

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

tradermonty/claude-trading-skills

Path

skills/drawdown-circuit-breaker/SKILL.md

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.