CtrlK
BlogDocsLog inGet started
Tessl Logo

frame

Multi-perspective investigation. Recommends analytical lenses or assembles a team to analyze from selected viewpoints when the right framework is absent, producing a framed inquiry. Type: (FrameworkAbsent, AI, SELECT, Inquiry) → FramedInquiry. Alias: Prothesis(πρόθεσις).

47

Quality

35%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./prothesis/skills/frame/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Discovery

35%

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 attempts to define a specialized analytical skill but relies heavily on abstract jargon, a formal type signature notation, and a Greek alias that would be opaque to most users. While it conveys the general idea of multi-perspective analysis, it lacks natural trigger terms and an explicit 'Use when...' clause, making it difficult for Claude to reliably select this skill from a large pool.

Suggestions

Add an explicit 'Use when...' clause with natural language triggers, e.g., 'Use when the user wants to analyze a problem from multiple perspectives, needs different viewpoints, or asks for a multi-angle investigation when no clear framework exists.'

Replace jargon like 'analytical lenses', 'FramedInquiry', and the type signature with plain language that users would naturally use, such as 'multiple viewpoints', 'different angles', 'perspective analysis'.

Include concrete examples of what the skill produces, e.g., 'Generates a structured analysis examining a topic through contrasting viewpoints such as economic, ethical, and technical perspectives.'

DimensionReasoningScore

Specificity

It names a domain ('multi-perspective investigation') and some actions ('recommends analytical lenses', 'assembles a team to analyze from selected viewpoints', 'producing a framed inquiry'), but the actions are abstract and conceptual rather than concrete and grounded. Terms like 'analytical lenses' and 'framed inquiry' are jargon-heavy rather than clearly actionable.

2 / 3

Completeness

The 'what' is partially addressed (recommends analytical lenses, assembles a team for multi-perspective analysis), but the 'when' is only implied through the type signature notation ('FrameworkAbsent') rather than stated with an explicit 'Use when...' clause. Per the rubric, a missing explicit trigger guidance caps completeness at 2.

2 / 3

Trigger Term Quality

The description uses highly specialized and abstract terminology ('FrameworkAbsent', 'FramedInquiry', 'Prothesis(πρόθεσις)', 'analytical lenses') that no user would naturally say. There are no natural keywords a user would use when needing this skill, such as 'analyze from multiple angles', 'different perspectives', or 'brainstorm approaches'.

1 / 3

Distinctiveness Conflict Risk

The type signature and alias give it a unique identity within what appears to be a structured skill taxonomy, but the core concept of 'multi-perspective investigation' and 'analytical lenses' is broad enough to overlap with general analysis, brainstorming, or reasoning skills. The niche is somewhat defined but not crisply bounded.

2 / 3

Total

7

/

12

Passed

Implementation

35%

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

This skill defines a sophisticated multi-agent investigation protocol with clear phases and validation checkpoints, but is severely undermined by extreme verbosity and over-formalization. The formal type theory notation (categorical meets, morphisms, type signatures) consumes enormous token budget while adding little actionable value beyond what structured prose would provide. The actionable templates and tool grounding are genuinely useful but are buried under layers of specification that make the skill difficult to follow efficiently.

Suggestions

Drastically reduce the formal notation sections (FLOW, MORPHISM, TYPES, CATEGORICAL NOTE) — replace with concise prose descriptions or move to a separate reference file. The algebraic specification duplicates what the Phase descriptions already explain in actionable terms.

Move the TOOL GROUNDING, MODE STATE, COMPOSITION, Known Limitations, and Adversarial Guards sections to a separate reference file, keeping only a brief summary with links in the main SKILL.md.

Consolidate the multiple overlapping workflow representations (FLOW, MORPHISM, PHASE TRANSITIONS, LOOP, and the Phase sections) into a single clear sequence — currently the same workflow is described 4-5 times in different formalisms.

Trim the distinction table to only the 2-3 most commonly confused protocols rather than listing all 12, and move the full table to a reference file.

DimensionReasoningScore

Conciseness

This skill is extremely verbose and over-engineered. It includes extensive formal type theory notation, categorical theory references, exhaustive edge case documentation, and adversarial guards that massively inflate token count. Much of the formal specification (type definitions, morphism chains, phase transition algebra) could be condensed dramatically without losing actionability. The content explains concepts and formalisms at length that don't earn their token cost.

1 / 3

Actionability

The skill provides concrete templates (spawn prompts, synthesis output format, Constitution interaction formats) and specific tool calls (TeamCreate, TaskCreate, SendMessage), which is good. However, the actionable content is buried under layers of formal notation and abstract specification, making it harder to extract executable guidance. The formal flow notation is not directly executable and serves more as specification than instruction.

2 / 3

Workflow Clarity

The phases (0-4) are clearly sequenced with explicit transitions and validation checkpoints (Mission Brief confirmation, trigger detection before synthesis). However, the workflow is obscured by excessive formal notation and parallel specification systems (FLOW, MORPHISM, PHASE TRANSITIONS, LOOP sections all describe overlapping sequences). The redundant representations of the same workflow create confusion rather than clarity. Validation steps exist but are buried.

2 / 3

Progressive Disclosure

The skill references external files appropriately (references/conceptual-foundations.md, references/isolation-rationale.md) and uses section headers. However, the main file itself is monolithic — containing extensive type definitions, formal specifications, rules, adversarial guards, and known limitations that could be split into reference files. The inline content is far too dense for an overview document.

2 / 3

Total

7

/

12

Passed

Validation

90%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (574 lines); consider splitting into references/ and linking

Warning

Total

10

/

11

Passed

Repository
jongwony/epistemic-protocols
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.