frame

Multi-perspective framing. Fires when the right framework is absent: places analytical lenses, hands off lens↔substrate pairs. Type: (FrameworkAbsent, AI, DESIGN, Inquiry) → FramedInquiry

Quality

30%

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 ./prothesis/skills/frame/SKILL.md

Quality

Content

27%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 skill body is a dense, jargon-heavy specification that restates its own boundary clauses repeatedly and front-loads abstract notation over concrete, executable guidance. It has a sequenced phase model and a couple of real reference pointers, but overall it is verbose and far from token-efficient.

Suggestions

Move the FLOW/MORPHISM/TYPES/U-BINDING notation block into a reference file and keep SKILL.md as a concise overview pointing to it.

Deduplicate the repeated 'frame does NOT realize isolation/arrange/execute/synthesize' boundary statements; state the boundary once.

Replace abstract morphism notation with concrete, ordered user-facing steps (render Mission Brief → propose lenses → selection gate → bind substrate → handoff) with explicit validation checkpoints.

Dimension	Reasoning	Score
Conciseness	The body is severely verbose: it repeatedly re-explains the same boundary clauses ('frame does NOT realize isolation, arrange, execute, or synthesize' appears many times) and elaborates dense pseudo-formal notation throughout, matching anchor 1.	1 / 5
Actionability	Beyond the reusable per-perspective directive template and one-line lens rendering rule, the bulk is abstract morphism/flow notation with no executable steps; concrete guidance is minimal and high-level, fitting anchor 2.	2 / 5
Workflow Clarity	Phases 0–3 are sequenced with explicit transitions and a validation-adjacent checkpoint (the Z zero-candidate guard with modify/supply routing), but there are no concrete verification/feedback steps and the heavy notation obscures the checkpoints, matching anchor 3.	3 / 5
Progressive Disclosure	Two real references (conceptual-foundations.md, round-composition.md) are signaled inline, but the body still inlines a large monolithic notation block that should live in a separate file, so structure is present but partial per anchor 3.	3 / 5
	Total	9 / 20 Passed

Description

33%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 conveys an abstract 'what' but no explicit natural-language trigger, leaning heavily on invented jargon rather than phrases users would actually say. It lacks a clear 'Use when...' clause, which caps its completeness.

Suggestions

Add an explicit 'Use when...' clause naming natural trigger phrases (e.g. 'when the user faces a contested design, value, or interpretation problem and no analytical framework is in play').

Replace jargon terms ('epistemic lenses', 'substrate', 'lens↔substrate pairs') with everyday language users would actually say, and include synonyms.

Lead with a concrete one-line statement of what the skill produces before introducing the type signature.

Dimension	Reasoning	Score
Specificity	Names the domain ('Multi-perspective framing') and a couple concrete actions ('places analytical lenses', 'hands off lens↔substrate pairs'), but the actions are abstract and not comprehensive like anchor 3.	3 / 5
Completeness	It states a vague 'what' (placing lenses, handing off pairs) but gives no explicit 'Use when...' trigger clause; per the rubric a missing 'when' caps completeness and anchor 2 fits best.	2 / 5
Trigger Term Quality	Only one or two generic-ish keywords ('framing', 'framework') and jargon ('epistemic', 'substrate'); it lacks the natural phrases a user would say and reads as technical jargon per anchor 2.	2 / 5
Distinctiveness Conflict Risk	The domain is somewhat specific ('framework-absent multi-perspective framing') but the abstract phrasing could overlap with other analytical/decision skills, matching anchor 3.	3 / 5
	Total	10 / 20 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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: jongwony/epistemic-protocols
Path: prothesis/skills/frame/SKILL.md
Commit: ed3cc09

Reviewed: 1 day 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.