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).

Quality

17%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./epharmoge/skills/contextualize/SKILL.md

Quality

Discovery

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 nearly impenetrable, relying on abstract academic terminology, a formal type signature, and a Greek alias rather than plain language. It fails to communicate concrete actions, natural trigger terms, or explicit usage conditions. A user or Claude selecting from a list of skills would have no practical understanding of when or why to choose this skill.

Suggestions

Rewrite using plain language that describes concrete actions, e.g., 'Checks whether an execution result actually fits the user's original context and adjusts the output accordingly.'

Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when execution output seems correct but may not match the user's actual application context or intent.'

Remove or demote the type signature and Greek alias to supplementary metadata rather than the primary description content.

Dimension	Reasoning	Score
Specificity	The description uses highly abstract, jargon-heavy language like 'application-context mismatch', 'contextualized execution', and a type signature. No concrete actions a user would recognize are listed.	1 / 3
Completeness	The 'what' is buried in abstract language and the 'when' is entirely missing — there is no 'Use when...' clause or equivalent explicit trigger guidance. Both dimensions are very weak.	1 / 3
Trigger Term Quality	There are no natural keywords a user would say. Terms like 'ApplicationDecontextualized', 'Epharmoge(ἐφαρμογή)', and 'ContextualizedExecution' are opaque technical/academic jargon that no user would naturally use in a request.	1 / 3
Distinctiveness Conflict Risk	The description is so niche and jargon-laden that it's unlikely to accidentally trigger for the wrong skill, but it's also so vague that it's unclear what domain it actually serves, making it hard to assess true distinctiveness.	2 / 3
	Total	5 / 12 Passed

Implementation

27%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This skill reads as a formal academic specification rather than actionable guidance for Claude. The content is extremely verbose, presenting the same workflow through multiple overlapping formal representations (flow notation, morphisms, phase transitions, convergence conditions) without a single concrete worked example. While the underlying protocol has clear structure, the presentation prioritizes theoretical completeness over practical usability, and the entire specification is crammed into one monolithic file.

Suggestions

Add a concrete worked example showing the full protocol applied to a real scenario (e.g., generating a deployment script that assumes wrong environment), demonstrating Phase 0 detection through Phase 2 adaptation with actual surfacing text.

Consolidate the overlapping formal representations (FLOW, MORPHISM, PHASE TRANSITIONS, LOOP, CONVERGENCE) into a single clear workflow section, moving the formal type theory to a separate FORMAL_SPEC.md reference file.

Cut the philosophical references (Dewey, Ryle, Aristotle), the extensive distinction table comparing 10 protocols, and the detailed advisory relationship descriptions — these consume significant tokens without adding actionable guidance.

Split content into SKILL.md (quick overview + core workflow + surfacing template) with references to separate files for formal specification, mismatch taxonomy, and cross-protocol relationships.

Dimension	Reasoning	Score
Conciseness	Extremely verbose at ~400+ lines of dense formal specification. Includes extensive formal logic notation, type theory, morphisms, and philosophical references (Dewey, Ryle, Aristotle) that are unnecessary for actionable guidance. Much of this is abstract framework definition rather than practical instruction.	1 / 3
Actionability	The Phase 0/1/2 protocol steps and surfacing format provide some concrete guidance with specific presentation templates and TaskCreate examples. However, the skill is overwhelmingly abstract and formal rather than executable — no concrete worked example showing the protocol applied to a real scenario, and the formal notation dominates over practical instruction.	2 / 3
Workflow Clarity	The Phase 0→1→2 sequence is clearly defined with transitions and loop conditions, and validation/re-scan steps are present. However, the workflow is buried in dense formal notation and competing sections (FLOW, MORPHISM, PHASE TRANSITIONS, LOOP, CONVERGENCE) that present the same information in multiple overlapping representations, making it hard to follow the actual operational sequence.	2 / 3
Progressive Disclosure	Monolithic wall of text with no references to external files. All content — formal specification, comparison tables, UX safeguards, rules, mismatch taxonomy — is inlined in a single massive document. The formal type definitions, distinction tables, and operational rules could easily be split into referenced files.	1 / 3
	Total	6 / 12 Passed

Validation

100%

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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: jongwony/epistemic-protocols
Commit: 9342160

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.