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 contextualize

What are skills?

Review — 27%

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/skill

Learn more

Validation — 11 / 11 Passed

Validation for skill structure

SKILL.md

Review

Evals

Evaluation results

72%

Data Pipeline Module Review

Mismatch identification and structured surfacing format

Criteria

Without context

With context

Mismatch aspect field

50%

Mismatch description field

100%

Evidence from result

100%

Evidence from context

100%

Severity assignment

100%

PEP 585 type hints identified

100%

Match statement identified

100%

Surfacing format: natural integration

37%

50%

Progress indicator present

Confirm and Dismiss options

12%

Phase 0 as internal analysis

37%

62%

Activation justified by predicate

70%

100%

Without context: $0.3610 · 1m 40s · 16 turns · 21 in / 5,875 out tokens

With context: $0.8972 · 3m 55s · 30 turns · 196 in / 12,944 out tokens

71%

-3%

Monitoring Stack Configuration Review

Severity ordering and one-at-a-time mismatch surfacing

Criteria

Without context

With context

Critical mismatch identified

100%

Significant mismatch identified

100%

62%

Minor mismatch identified

100%

62%

Critical surfaced first

100%

Significant before Minor

66%

58%

One mismatch per log entry

100%

Progress indicator per entry

33%

Minor entry has Dismiss as default

Evidence from configuration

100%

Evidence from deployment context

100%

Without context: $0.2090 · 1m 14s · 8 turns · 13 in / 4,086 out tokens

With context: $0.5865 · 2m 38s · 18 turns · 269 in / 8,632 out tokens

92%

19%

Post-Execution Review Policy Documentation

Skip condition recognition and activation gate

Criteria

Without context

With context

Snapshot A: trivial skip

100%

Snapshot B: read-only skip

100%

Snapshot C: mechanical skip

100%

Snapshot D: explicit-spec skip

100%

Snapshot E: activation warranted

100%

Snapshot E: correct/unwarranted predicate

61%

100%

Snapshot F: user-approval skip

100%

Flip conditions noted

20%

Correctness as prerequisite

37%

100%

Snapshot E: specific evidence

100%

Without context: $0.1746 · 1m 1s · 7 turns · 10 in / 3,102 out tokens

With context: $0.3476 · 1m 43s · 13 turns · 296 in / 4,911 out tokens

Evaluated: about 12 hours ago
Agent: Claude Code

Table of Contents

Data Pipeline Module Review Monitoring Stack Configuration Review Post-Execution Review Policy Documentation

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.