exposure-coach

Generate a one-page Market Posture summary with net exposure ceiling, growth-vs-value bias, participation breadth, and new-entry-allowed vs cash-priority recommendation by integrating signals from breadth, regime, and flow analysis skills.

Quality

73%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/exposure-coach/SKILL.md

Quality

Content

75%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.

This is a strong, highly actionable skill body with an executable command, clear tables, explicit validation pitfalls, and a well-organized one-level-deep bundle. Its main weakness is token efficiency: duplicated caveat prose and full dual-format output examples (with a hard-coded date) could be tightened or moved to a reference file.

Suggestions

Consolidate the two overlapping caveat paragraphs (regime-report degradation and theme-detector ingestion) into one terse degradation-rules block, or move them into references/exposure_framework.md.

Trim the Output Format section to one compact example (or a field-description table) instead of full JSON and markdown blocks, and remove the hard-coded generation date from the example.

Promote the post-run check of `inputs_provided`/`inputs_missing` into a numbered Step 3 item (e.g. "Validate: confirm no supplied input appears in `inputs_missing`; if it does, report the dimension degraded") so the feedback loop is structural rather than prose.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient (tables, a complete command, terse principles), but the two long inline caveat paragraphs on regime-report degradation and theme-detector ingestion are repetitive of each other, and the full JSON plus markdown output examples (including a hard-coded date, "2026-03-16T07:00:00Z") inflate the token budget; the degradation rules belong in a reference file.	3 / 5
Actionability	The body provides a fully executable, copy-paste-ready bash invocation with all eight input flags and an output directory, a concrete file-pattern table per upstream skill, explicit recommendation-to-action mappings, and exact output filenames — the common case is completely covered.	5 / 5
Workflow Clarity	The four-step workflow is clearly sequenced and includes an explicit post-run validation checkpoint ("inspect the generated JSON fields `inputs_provided` and `inputs_missing`... report the affected dimension as degraded and keep confidence capped") with error-recovery guidance; however, this validation lives in embedded prose rather than a numbered step with a fix-and-retry loop, so it falls just short of the anchor above.	4 / 5
Progressive Disclosure	The Resources section clearly signals the script and both reference files, all of which exist in the bundle and are only one level deep (no nested references inside them), and the threshold/mapping detail is appropriately split out of SKILL.md; minor gaps remain in that the output-format examples and ingestion caveats are inlined rather than referenced.	4 / 5
	Total	16 / 20 Passed

Description

58%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 does a good job of stating concretely what the skill produces, but it completely lacks a "when to use" trigger clause, which caps completeness and weakens trigger-term quality. Adding an explicit usage trigger with natural phrasing would lift two dimensions.

Suggestions

Append an explicit trigger clause such as "Use when deciding how much capital to commit to equities, before opening new positions, or when market signals conflict and a unified exposure posture is needed."

Add natural user phrasings as trigger terms (e.g. "how much should I be invested right now", "market risk level", "raise cash or stay invested") alongside the technical output-state labels.

Clarify the integration mechanism slightly (e.g. "by scoring JSON outputs from eight upstream analysis skills") to close the remaining specificity gap.

Dimension	Reasoning	Score
Specificity	The description names several concrete outputs — "net exposure ceiling", "growth-vs-value bias", "participation breadth", "new-entry-allowed vs cash-priority recommendation" — which is strong specificity, but "integrating signals from breadth, regime, and flow analysis skills" stays somewhat abstract about the mechanics, leaving minor gaps versus the comprehensive anchor.	4 / 5
Completeness	The "what" is clearly and concretely stated (a one-page Market Posture summary with four named components), but there is no "Use when..." clause or equivalent trigger guidance anywhere in the description, which per the judging guidelines caps completeness at 3.	3 / 5
Trigger Term Quality	Relevant domain keywords like "exposure ceiling", "growth-vs-value", and "cash-priority" are present, but common natural variations a trader would actually say (e.g. "how much capital to commit", "position sizing", "market risk") are missing, and the output-state terms ("new-entry-allowed vs cash-priority") are not trigger phrases.	3 / 5
Distinctiveness Conflict Risk	The synthesis/orchestration niche is distinct — it explicitly integrates outputs of the named breadth/regime/flow skills rather than duplicating them — but because it references those upstream skill families, there is minor overlap risk with the upstream analysis skills themselves.	4 / 5
	Total	14 / 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/exposure-coach/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.