strategy-discovery

Strategy Discovery: evidence-gated facade over Alpha Zoo + the SDM strategy store — answers what strategies exist and what state they are in, with per-regime evidence instead of scenario tags; reports evidence freshness on every returned row and rebuilds the disposable evidence cache from local backtest runs.

Quality

72%

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 ./agent/src/skills/strategy-discovery/SKILL.md

Quality

Content

73%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 body is a strong, highly actionable skill definition with excellent workflow clarity and explicit validation, slightly held back by repetition across sections and a monolithic single-file structure that could benefit from one-level-deep reference files.

Suggestions

De-duplicate the refresh/fail-closed/disposable-cache semantics — state them once and cross-reference, instead of re-explaining in Purpose, Tools, Populating, Honest-Empty, and Composition.

Move the longer contract details (Evidence Row Contract, Decay & Freshness Contract, Multi-position caveat) into one-level-deep reference files (e.g. EVIDENCE.md, FRESHNESS.md) and summarize them inline with clear links.

Add one end-to-end example showing a query call and its returned rows to push actionability from 4 to 5.

Dimension	Reasoning	Score
Conciseness	The body is dense and domain-specific (no generic concept padding), but the refresh/fail-closed/disposable-cache semantics are restated across Purpose, Tools, Populating, Honest-Empty, and Composition sections, so it could be tightened.	3 / 5
Actionability	Provides concrete, executable guidance: a routing decision tree, full parameter tables with types/defaults/meaning, a copy-paste-ready manifest JSON example, and the exact CLI command — with only the absence of an end-to-end example call keeping it from a 5.	4 / 5
Workflow Clarity	Multi-step processes are explicitly sequenced with validation checkpoints: the 5-gate Hard-Gate Checklist in order, the 3-step Periodic recipe, the atomic-rebuild guarantee, and explicit failure handling via the skipped-list with stable tokens.	5 / 5
Progressive Disclosure	Well-organized with clear section headers and cross-skill references, but the entire skill is a single ~200-line inline file with no bundle files; some contract sections (Evidence Row, Decay & Freshness, Multi-position) could be split into one-level-deep reference files.	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 is specific and distinguishes the skill clearly, but it is jargon-heavy and lacks an explicit 'Use when' trigger clause, leaving the 'when' implicit and capping both completeness and trigger quality.

Suggestions

Add an explicit 'Use when ...' clause with natural trigger phrases (e.g. 'Use when the user asks what strategies exist, which strategies fit a regime, or wants to refresh stale backtest evidence').

Soften technical jargon ('evidence-gated facade', 'per-regime evidence') with plain-language synonyms a user would actually say.

Include common variations/synonyms like 'list strategies', 'find a strategy', 'check strategy state' to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions — 'answers what strategies exist and what state they are in', 'reports evidence freshness on every returned row', 'rebuilds the disposable evidence cache from local backtest runs' — with only minor coverage gaps.	4 / 5
Completeness	The 'what' is stated clearly and concretely, but there is no 'Use when...' clause or equivalent explicit trigger guidance in the description, which caps completeness at 3 per the rubric.	3 / 5
Trigger Term Quality	Contains some natural phrases ('what strategies exist', 'what state they are in') but leans on technical jargon ('evidence-gated facade', 'per-regime evidence') and omits common variations users would say like 'list strategies' or 'find a strategy'.	3 / 5
Distinctiveness Conflict Risk	The 'Strategy Discovery' niche over 'Alpha Zoo + the SDM strategy store' is clearly distinct from creation/backtest skills, with only minor overlap risk against the related alpha-zoo and strategy-dev-manager surfaces.	4 / 5
	Total	14 / 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: HKUDS/Vibe-Trading
Path: agent/src/skills/strategy-discovery/SKILL.md
Commit: 251b094

Reviewed: 3 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.