contextualize
Detect application-context mismatch after execution. Verifies applicability when correct output may not fit the actual context, producing contextualized execution. Type: (ApplicationDecontextualized, AI, CONTEXTUALIZE, ExecutionResult) → ContextualizedExecution. Alias: Epharmoge(ἐφαρμογή).
Install with Tessl CLI
npx tessl i github:jongwony/epistemic-protocols --skill contextualize42
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
7%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 description is written in highly abstract, academic language that fails to communicate concrete capabilities or usage triggers. The type signature notation and Greek alias suggest an internal or theoretical framework rather than a practical skill description. A user or Claude would have no clear understanding of when to select this skill or what specific actions it performs.
Suggestions
Replace abstract terminology with concrete action verbs describing what the skill actually does (e.g., 'Validates that generated code matches the user's project context' instead of 'Detect application-context mismatch').
Add an explicit 'Use when...' clause with natural language triggers that describe scenarios when this skill should be selected.
Remove the type signature notation and Greek alias, replacing them with plain language examples of inputs and outputs.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description uses highly abstract language like 'application-context mismatch', 'contextualized execution', and 'applicability' without describing any concrete actions. No specific tasks or operations are listed. | 1 / 3 |
Completeness | The 'what' is extremely vague (something about context mismatch detection), and there is no 'when' clause or explicit trigger guidance. The type signature format is not user-facing guidance. | 1 / 3 |
Trigger Term Quality | Contains only technical jargon ('ApplicationDecontextualized', 'CONTEXTUALIZE', 'ExecutionResult', 'Epharmoge') and a Greek alias. No natural keywords a user would actually say when needing this functionality. | 1 / 3 |
Distinctiveness Conflict Risk | The highly specialized jargon and Greek alias make it unlikely to accidentally trigger for common tasks, but the abstract nature means it's unclear what domain this actually serves, creating potential confusion rather than clear distinction. | 2 / 3 |
Total | 5 / 12 Passed |
Implementation
47%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill demonstrates excellent workflow structure with clear phase transitions and validation checkpoints, but suffers from severe verbosity. The formal type notation, philosophical references, and extensive protocol comparisons add significant token overhead without proportional value for Claude's execution. The content reads more like an academic specification than actionable guidance.
Suggestions
Remove or drastically reduce the formal notation (morphisms, type definitions) - Claude can follow natural language instructions without category theory syntax
Delete the philosophical references (Aristotle, Dewey, Ryle) and protocol comparison table - these explain concepts Claude already understands
Add a concrete, executable example showing the full protocol flow with actual tool calls and user responses
Move the 'Distinction from Other Protocols' table and formal definitions to a separate REFERENCE.md file, keeping only the essential workflow in SKILL.md
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose with extensive formal notation, philosophical references (Aristotle, Dewey, Ryle), and abstract type theory that Claude doesn't need explained. The 'Definition' section alone contains dense formal logic that could be reduced to a simple workflow description. | 1 / 3 |
Actionability | Provides some concrete guidance like the surfacing format template and phase descriptions, but relies heavily on abstract notation and pseudocode rather than executable examples. The 'Protocol' section describes what to do but lacks concrete, copy-paste ready implementations. | 2 / 3 |
Workflow Clarity | Clear three-phase workflow (Phase 0: Silent Gate → Phase 1: Surfacing → Phase 2: Adaptation) with explicit validation checkpoints, loop conditions, and convergence criteria. The phase transitions and loop termination conditions are well-defined. | 3 / 3 |
Progressive Disclosure | Content is structured with clear sections and tables, but everything is in one monolithic file. The extensive comparison table with other protocols and formal notation could be split into reference files. No external file references for advanced content. | 2 / 3 |
Total | 8 / 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.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- 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.