CtrlK
BlogDocsLog inGet started
Tessl Logo

ftd-detector

Detects Follow-Through Day (FTD) signals for market bottom confirmation using William O'Neil's methodology. Dual-index tracking (S&P 500 + NASDAQ) with state machine for rally attempt, FTD qualification, and post-FTD health monitoring. Use when user asks about market bottom signals, follow-through days, rally attempts, re-entry timing after corrections, or whether it's safe to increase equity exposure. Complementary to market-top-detector (defensive) - this skill is offensive (bottom confirmation).

70

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

72%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is actionable and well-structured with good progressive disclosure, but it is held back by redundancy with the frontmatter and a missing validation/error-recovery step in the execution workflow. Tightening the duplicated sections and adding a brief failure-handling checkpoint would raise the weaker dimensions.

Suggestions

Remove the "Complementary to Market Top Detector" block and the English/Japanese "When to Use" bullet lists from the body, since they duplicate the frontmatter description and trigger terms.

Add a brief validation/error-recovery checkpoint in Phase 1 (e.g., what to do if the FMP API call fails or returns insufficient data) to turn the workflow into a feedback loop.

Consider moving the state-machine definitions and score tables into a reference file, keeping the body as a lean overview that points to ftd_methodology.md for the detailed rules.

DimensionReasoningScore

Conciseness

The body is mostly efficient (tables, state diagram, workflow phases) but repeats material already in the description — the "Complementary to Market Top Detector" section and the English/Japanese "When to Use" bullet lists largely duplicate the frontmatter triggers — so it could be tightened. It is not the lean, every-token-earns-its-place level.

2 / 3

Actionability

Provides a copy-paste-ready executable command ("python3 skills/ftd-detector/scripts/ftd_detector.py --api-key $FMP_API_KEY"), enumerates what the script does, names output files, and specifies prerequisites (env var, flag, Python version), matching the fully-executable anchor.

3 / 3

Workflow Clarity

A clear 3-phase sequence with state-branching guidance exists, but there is no validation or error-recovery checkpoint for script/API failures — only the happy path is described — which matches the steps-listed-but-validation-gaps anchor.

2 / 3

Progressive Disclosure

The body is a concise overview pointing to two real one-level-deep references (ftd_methodology.md, post_ftd_guide.md) with a "When to Load References" navigation section, matching the clear-overview-with-well-signaled-references anchor.

3 / 3

Total

10

/

12

Passed

Description

100%

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 strong across all dimensions: it states concrete capabilities, includes natural user-facing trigger terms, explicitly answers what and when, and clearly distinguishes itself from the complementary top-detector skill. No significant weaknesses.

DimensionReasoningScore

Specificity

Lists several concrete actions — "Detects Follow-Through Day signals", "Dual-index tracking (S&P 500 + NASDAQ)", and "state machine for rally attempt, FTD qualification, and post-FTD health monitoring" — matching the multiple-specific-actions anchor.

3 / 3

Completeness

Clearly answers both what ("Detects FTD signals... with state machine...") and when via an explicit "Use when..." clause listing concrete triggers, matching the both-what-and-when anchor.

3 / 3

Trigger Term Quality

Natural phrases a user would say appear throughout — "market bottom signals", "follow-through days", "rally attempts", "re-entry timing after corrections", "whether it's safe to increase equity exposure" — giving good coverage of common variations.

3 / 3

Distinctiveness Conflict Risk

Occupies a clear niche (offensive bottom confirmation) and explicitly contrasts itself with market-top-detector (defensive), so distinct triggers make it unlikely to fire for the wrong skill.

3 / 3

Total

12

/

12

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.

Validation16 / 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.