parabolic-short-trade-planner

Screen US equities for parabolic exhaustion patterns and generate conditional pre-market short plans, then evaluate intraday trigger fires from live 5-min bars. Phase 1 daily 5-factor scorer (MA extension / acceleration / volume climax / range expansion / liquidity), Phase 2 per-candidate plans for ORL break / first-red 5-min / VWAP fail with explicit borrow / SSR / manual-confirmation gating, Phase 3 one-shot intraday FSM that detects trigger fires and resolves concrete share counts. Covers Phase 1 + Phase 2 + Phase 3.

Quality

80%

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/parabolic-short-trade-planner/SKILL.md

Quality

Content

81%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 body: concrete commands for all three phases, explicit validation gating, a pre-entry checklist, and a clean one-level-deep reference layout that matches the actual bundle. The main defects are a dangling `requirements.txt` reference with no install command, and small pockets of time-sensitive/legacy detail that belong in the references.

Suggestions

Ship a requirements.txt (or vendor the dependency list) and replace "Install `requirements.txt`" with the concrete command, e.g. `pip install -r skills/parabolic-short-trade-planner/requirements.txt`.

Move the FINRA intraday-margin date detail (2026-06-04 phase-in dates) into `references/short_risk_management.md` and keep one line here, so time-sensitive content does not rot the main file.

Compress the per-candidate legacy earnings-field enumeration (or relocate it next to the earnings-aware screening reference) to tighten the main workflow.

Dimension	Reasoning	Score
Conciseness	Largely efficient — exact commands, flags, defaults, and output field names with no padding of concepts Claude already knows. Minor over-explanation remains: the inline FINRA date detail ("effective 2026-06-04, with broker phase-in allowed through 2027-10-20") is time-sensitive content that belongs in a reference, and the legacy-field enumeration ("earnings_within_2d is kept for backward compatibility") could be trimmed. Not score 3 — these are trimmable instances, not unnecessary explanations of known concepts.	4 / 5
Actionability	All three phases have copy-paste-ready bash commands with concrete flags, example paths, env-var prerequisites, and fixture fallbacks, and the "Reviewing a plan before entry" section gives a concrete checklist. The gap: "Install `requirements.txt` before running the planner" gives no install command, and no requirements.txt exists anywhere in the bundle — a dangling, non-executable step that keeps this at anchor 4 rather than 5.	4 / 5
Workflow Clarity	Clear three-phase sequence with numbered steps, per-phase prerequisites (env vars), named outputs, explicit phase-gating validation (grade-B filter, `plan_status` actionable vs watch_only, blocking vs advisory manual reasons), and a pre-entry review checklist; dry-run/fixture paths provide test-first recovery. The skill is detection-only ("never sends orders"), so the destructive-operation validation cap does not apply.	5 / 5
Progressive Disclosure	Good structure with a Resources section that signals five one-level-deep reference files, all of which exist and match their one-line descriptions; the referenced scripts, fixtures, and test files (`tests/test_schema_contract.py`, `scripts/tests/fixtures/dry_run_minimal.json`) all resolve in the bundle. Minor gap: the body points to a nonexistent `requirements.txt`, and some operational contract detail (the earnings-field enumeration) is inline rather than in a reference — anchor 4 rather than 5.	4 / 5
	Total	17 / 20 Passed

Description

71%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.

Highly specific and distinctive description with concrete multi-phase capabilities, weakened by the absence of any explicit "when to use this" trigger guidance and by jargon-heavy phrasing that crowds out natural user synonyms. The redundant closing "Covers Phase 1 + Phase 2 + Phase 3." adds no information.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks for a parabolic short watchlist, pre-market short plans, or intraday short-trigger monitoring on US equities."

Swap at least one jargon phrase for a natural synonym users would say (e.g. mention "Qullamaggie-style parabolic short watchlist" or "short screener") to improve trigger-term coverage.

Drop the redundant "Covers Phase 1 + Phase 2 + Phase 3." tail — the phase enumeration already states this.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions with comprehensive coverage: "Screen US equities for parabolic exhaustion patterns", "generate conditional pre-market short plans", "evaluate intraday trigger fires from live 5-min bars", each backed by named mechanics (5 named scoring factors, ORL break / first-red 5-min / VWAP fail triggers). No vague filler; every clause names a real capability.	5 / 5
Completeness	The "what" is explicit and detailed across three phases, but there is no "Use when..." clause or equivalent trigger guidance — the only use-conditions are phase labels. Per the judging guideline, a missing explicit trigger clause caps completeness at 3 (clear what, when absent).	3 / 5
Trigger Term Quality	Good natural keyword coverage ("parabolic", "short plans", "pre-market", "5-min bars", "VWAP fail", "borrow"), but leans on internal jargon ("FSM", "SSR", "ORL break") and misses natural user phrasings like "watchlist", "scanner", or "Qullamaggie" that the body itself uses. Fits anchor 4 (good coverage, a few natural terms missing) rather than 5 (comprehensive synonyms/extensions) or 3 (missing common variations).	4 / 5
Distinctiveness Conflict Risk	Clear niche (parabolic exhaustion short planning for US equities) with distinct triggers unlikely to fire for unrelated skills. Minor overlap risk with other equity screener skills (the body itself names vcp-screener / canslim-screener as neighbors), so anchor 4 fits better than 5.	4 / 5
	Total	16 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
referenced_paths_exist	Referenced path issues: 2 deeper-than-1-level	Warning

	Total	15 / 16 Passed

Repository: tradermonty/claude-trading-skills
Path: skills/parabolic-short-trade-planner/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.