cash-flow-projection
Patrones para proyección de cash flow y forecasting financiero. Incluye algoritmos de proyección a fin de mes, detección de gastos recurrentes programados, y visualización de tendencias. Usar cuando se trabaje con proyecciones, predicciones o gráficos de futuro.
Install with Tessl CLI
npx tessl i github:iru97/Savvy-ai --skill cash-flow-projection66
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Discovery
85%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a well-structured skill description that clearly defines its financial forecasting domain with specific capabilities and explicit usage triggers. The main weakness is moderate trigger term coverage - while it includes key terms, it could benefit from additional natural language variations users might employ when seeking cash flow or financial projection help.
Suggestions
Add more natural trigger term variations such as 'flujo de caja', 'presupuesto futuro', 'pronóstico financiero', or 'estimaciones de gastos' to improve discoverability
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'algoritmos de proyección a fin de mes' (month-end projection algorithms), 'detección de gastos recurrentes programados' (scheduled recurring expense detection), and 'visualización de tendencias' (trend visualization). | 3 / 3 |
Completeness | Clearly answers both what (cash flow projection patterns, month-end algorithms, recurring expense detection, trend visualization) AND when ('Usar cuando se trabaje con proyecciones, predicciones o gráficos de futuro') with explicit trigger guidance. | 3 / 3 |
Trigger Term Quality | Includes some relevant keywords like 'proyecciones', 'predicciones', 'gráficos de futuro', 'cash flow', 'forecasting financiero', but misses common variations users might say like 'presupuesto', 'flujo de caja', 'pronóstico', or file types. | 2 / 3 |
Distinctiveness Conflict Risk | Clear niche focused specifically on financial forecasting and cash flow projection with distinct triggers; unlikely to conflict with general data analysis or other financial skills due to specific focus on projections and future predictions. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
42%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides comprehensive, executable Dart code for cash flow projection but suffers from severe verbosity - it's essentially a full implementation dump rather than a skill guide. The content would be more effective as a brief overview with key patterns and references to detailed implementation files, rather than 500+ lines of inline code that Claude could generate from a concise specification.
Suggestions
Reduce to a 50-100 line overview with key algorithms described conceptually, moving full implementations to separate reference files (e.g., RECURRENCE_DETECTOR.dart, PROJECTOR.dart)
Remove Equatable boilerplate, getters, and other code Claude can infer - focus only on the novel business logic
Add validation checkpoints: what to do when recurrence detection finds no patterns, how to handle insufficient historical data, error recovery for projection failures
Split into progressive disclosure structure: SKILL.md (overview + quick start) → ALGORITHMS.md (detection logic) → VISUALIZATION.md (chart code) → EXAMPLES.md (use cases)
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose with ~500+ lines of Dart code that Claude could generate on demand. The skill explains basic concepts (what cash flow projection is, how recurrence detection works) that Claude already knows, and includes full class implementations with getters, Equatable boilerplate, and extensive comments. | 1 / 3 |
Actionability | The code is fully executable Dart with complete class definitions, algorithms, and concrete examples. The use cases at the end provide specific scenarios with expected inputs/outputs. Code is copy-paste ready for a Flutter/Dart project. | 3 / 3 |
Workflow Clarity | The three-step process (Detect → Project → Alert) is clearly labeled, but there are no validation checkpoints or error handling guidance. Missing feedback loops for when detection fails or projections are inaccurate. | 2 / 3 |
Progressive Disclosure | Monolithic wall of code with no references to external files. All implementation details are inline when they could be split into separate reference files (e.g., RECURRENCE_DETECTION.md, ALERT_GENERATION.md). The skill would benefit from a concise overview pointing to detailed implementations. | 1 / 3 |
Total | 7 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (604 lines); consider splitting into references/ and linking | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 9 / 11 Passed | |
- 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.