CtrlK
BlogDocsLog inGet started
Tessl Logo

pre-trade-discipline-gate

Evaluate a local pre-trade checklist before manual order entry, blocking planless, oversized, revenge-risk, market-regime-blocked, or circuit-breaker-blocked entries while journaling the decision for trader-memory-core review.

69

Quality

87%

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

SKILL.md
Quality
Evals
Security

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: concrete input/output examples, executable commands, and a decision table with explicit error-recovery guidance, with detail correctly delegated to bundle files. Remaining improvements are minor — trimming slight redundancy in Key Principles and tightening the Resources section's references.

DimensionReasoningScore

Conciseness

The body is efficient: a concrete JSON example, full CLI invocations, a decision table, and terse rule bullets, with no explanation of concepts Claude already knows. It is not a 5 because the 'Key Principles' section partially restates the Overview and Rules, and edge-case notes like the binary-float round-trip detail could be trimmed or moved to the reference file.

4 / 5

Actionability

Guidance is fully executable: a copy-paste-ready candidate JSON example, two complete CLI commands with all flags, an explicit decision table mapping each outcome to its meaning, exact output filenames, and exit-code semantics including the --fail-on-non-go and --as-of variations. This matches the 5 anchor's 'copy-paste ready commands; specific examples cover the common cases'.

5 / 5

Workflow Clarity

The three steps (prepare checklist → run gate → interpret decision) are clearly sequenced with concrete commands, and validation is built in: the decision table defines every outcome including REVIEW_REQUIRED recovery ('do not place orders until reviewed'), and exit-code behavior is documented for pipeline use. The skill is a read-only gate, so the destructive/batch validation cap does not apply.

5 / 5

Progressive Disclosure

Good structure: the body is a lean overview, the rule engine lives in scripts/check_pre_trade_discipline.py and rule definitions in references/discipline_gate_framework.md, both one level deep and real files. It falls short of 5 because the Resources section uses bare paths rather than clearly signaled links, and one listed path (skills/trader-memory-core/schemas/thesis.schema.json) is external to this bundle, so navigation is slightly less clean than the 5 anchor.

4 / 5

Total

18

/

20

Passed

Description

80%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 dense, specific, third-person description that clearly conveys what the skill does and when it applies within its trading-workflow niche. Its main gap is the absence of an explicit 'Use when...' trigger clause with natural user-facing phrases, which leaves completeness and trigger coverage just short of the top anchors.

Suggestions

Add an explicit trigger clause, e.g. 'Use when a manual entry order is about to be placed at the broker, after a recent loss, or when the user asks to run a pre-trade checklist.'

Include natural synonym phrases users might say, such as 'trade discipline', 'impulse trade', or 'before placing a trade', to strengthen trigger matching.

Mention the produced artifact (pre_trade_discipline_decision) so downstream consumers can identify the skill by its output.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions — "Evaluate a local pre-trade checklist", "blocking planless, oversized, revenge-risk, market-regime-blocked, or circuit-breaker-blocked entries", "journaling the decision" — comprehensively covering what the skill does. It is not below the 5 anchor since coverage of the gate's capabilities is complete, unlike the 4 anchor's 'minor gaps'.

5 / 5

Completeness

The 'what' is explicit (evaluate, block, journal) and the 'when' is stated as "before manual order entry", so both are present. It stays at 4 rather than 5 because the timing condition is embedded in a single clause rather than explicit trigger phrases (e.g., 'Use when the user is about to place a manual order'), and other triggers like post-loss cooldowns are only implied.

4 / 5

Trigger Term Quality

Natural terms traders would say are present: "pre-trade checklist", "manual order entry", "revenge-risk". It misses common variations such as "trade discipline", "impulse trade", or "before placing a trade", matching the 4 anchor ('good keyword coverage; a few natural terms missing') rather than the 5 anchor's synonym-and-extension completeness.

4 / 5

Distinctiveness Conflict Risk

The pre-trade gate niche is distinct, with its role (checklist evaluation and journaling) clearly separated from the market-regime and circuit-breaker skills it consumes. It is not a 5 because mentioning "circuit-breaker-blocked" and "market-regime-blocked" creates minor overlap risk with those closely related sibling skills.

4 / 5

Total

17

/

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
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.