ib-stop-loss

Downside stop-loss management for PMCC, naked LEAPS, and stock positions in IB. Computes stop prices, detects alerts, and places conditional combo orders. Dry-run by default. Requires TWS or IB Gateway running locally.

Quality

73%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Medium

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/ib-stop-loss/SKILL.md

Quality

Content

76%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 SKILL.md body is highly actionable with executable commands, a complete JSON schema, and clear structure, but its workflow for destructive order placement lacks an explicit validation feedback loop, and some inline reference material could be split out.

Suggestions

Add an explicit validate-then-execute checkpoint: instruct Claude to run a dry-run first, review the alert/position output with the user, and only then re-run with --execute.

Move the detailed JSON output schema and/or the Architecture function inventory into a reference file under references/ to keep SKILL.md a lean overview.

Trim the opening restatement of the description and condense the JSON example to the essential fields.

Dimension	Reasoning	Score
Conciseness	The body is efficient and assumes Claude's competence (no basic-concept padding), with only minor trimming opportunities such as the long inline JSON output schema and the opening line that restates the description.	4 / 5
Actionability	Provides copy-paste-ready commands with flag variants, a full arguments table, a complete JSON output schema, explicit order-ID naming conventions, and named architecture functions — fully executable guidance covering the common cases.	5 / 5
Workflow Clarity	Steps are sequenced (run script, format report, report to user) and dry-run is the safe default, but for destructive/batch operations (placing/cancelling real orders) there is no explicit validate-then-execute feedback loop, which caps workflow clarity at 3.	3 / 5
Progressive Disclosure	Well-organized into clear sections with the single bundle file (scripts/stop_loss.py) correctly referenced and no nested references; minor organization gaps since the JSON schema and architecture sections are inlined rather than split out.	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 and clearly niche-distinct, with good natural trigger terms, but it lacks an explicit 'Use when...' activation clause and only states a runtime precondition instead, which caps its completeness.

Suggestions

Add an explicit 'Use when...' clause stating when Claude should activate this skill (e.g. 'Use when managing downside risk on IB LEAPS/PMCC/stock positions or when the user asks to set or check stop-loss orders').

Mention orphan-order cancellation among the concrete actions so the capability list is more comprehensive.

Consider adding a natural synonym like 'stop orders' alongside 'stop-loss' to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ('Downside stop-loss management for PMCC, naked LEAPS, and stock positions in IB') and several concrete actions ('Computes stop prices, detects alerts, and places conditional combo orders'), with minor coverage gaps (e.g. orphan-order cancellation not mentioned).	4 / 5
Completeness	The 'what' is clear and concrete, but there is no 'Use when...' trigger clause — only a runtime precondition ('Requires TWS or IB Gateway running locally') — so the 'when' is weakly implied at best, capping completeness at 3.	3 / 5
Trigger Term Quality	Includes natural user-facing phrases like 'stop-loss', 'stop prices', and 'alerts', but lacks synonyms or common variations beyond those core terms.	4 / 5
Distinctiveness Conflict Risk	A clear niche (IB portfolio stop-loss for PMCC/naked LEAPS/stock) with highly specific triggers and minimal overlap risk with other skills.	5 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: staskh/trading_skills
Path: .claude/skills/ib-stop-loss/SKILL.md
Commit: 9a1bf57

Reviewed: 5 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.