CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

framing-doc

Create a framing document from conversation transcripts. Use when the user has transcripts (VTT, call notes, etc.) and wants to produce a frame that captures the problem worth solving and why it was chosen over alternatives.

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

High

Do not use without reviewing

SKILL.md
Quality
Evals
Security

Quality

Content

81%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 body is a well-sequenced, highly actionable instruction skill: a complete output template, explicit evidence-traceability rules, and a built-in review feedback loop. Its main costs are redundancy — the evidence discipline is stated twice — and the overlong optional-section digression, plus no use of bundle files for content that could be split out.

Suggestions

Merge "The Key Discipline: Evidence, Not Editorializing" and "Reviewing the Frame" into one section — both state the same keep/cite/mark-implied/drop rule, so the draft-time and review-time pass can be covered once.

Condense the "Less about / More about" section's three prose paragraphs (What it does / When to include it / How it surfaces) into a short trigger rule plus the template, and drop the domain-specific coaching example.

Move the full document-format template (or the detailed section-by-section guidance) into a references/ file so SKILL.md stays a lean overview with a clearly signaled pointer.

DimensionReasoningScore

Conciseness

The body is mostly substantive, skill-specific guidance with no filler about what transcripts are, but it is not tight: "The Key Discipline: Evidence, Not Editorializing" and "Reviewing the Frame" restate the same keep/cite/mark-implied/drop rule twice, and the "Less about / More about" section spends three prose paragraphs plus a worked coaching example ("AI that advises coaches on what to program") that could be condensed. This matches anchor 3 (mostly efficient, some unnecessary explanation that could be tightened) rather than anchor 4's minor-instances bar.

3 / 5

Actionability

For an instruction-only skill the guidance is fully concrete: a copy-paste-ready markdown document template with placeholders, an explicit options-landscape table schema, specific upfront questions to ask the user, and unambiguous decision rules ("If you can point to a specific person and moment → keep it, cite it... If you can't trace it back → drop it"). Specific examples cover the common cases, matching the top anchor.

5 / 5

Workflow Clarity

The sequence is clear and ordered — gather inputs ("Before You Start"), draft the sections, apply the evidence discipline while writing, then a post-draft validation pass — and "Reviewing the Frame" is an explicit feedback loop: examine each bullet, ask for its evidence, cite or drop, and re-verify the options table with willingness to shrink it. Not a destructive or batch operation, so no cap applies; this matches the checkpoint-with-error-recovery top anchor.

5 / 5

Progressive Disclosure

The single file is well-sectioned with clear headers and no nested or buried references (no bundle files exist). However, at ~190 lines it exceeds the simple-skill threshold, and inline material — notably the extended "Less about / More about" explainer and the full document template — could arguably live in a reference file. Good structure with minor organization gaps matches anchor 4 rather than the well-signaled external-reference structure of anchor 5.

4 / 5

Total

17

/

20

Passed

Description

82%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.

A strong description with an explicit, well-formed 'Use when...' clause, a clear niche, and good natural trigger terms including a file format. Its only weakness is that it names a single high-level action rather than enumerating the concrete capabilities the skill performs.

Suggestions

Enumerate the concrete actions the skill performs (e.g., 'Extract verbatim speaker quotes, survey the options landscape with signal strength, and draft problem/outcome bullets') instead of the single 'create a framing document' action, to raise specificity.

Add one or two common synonyms such as 'meeting recordings' or 'interview transcripts' alongside VTT and call notes to broaden natural trigger coverage.

DimensionReasoningScore

Specificity

The description names the domain ("conversation transcripts") and one concrete action ("Create a framing document"), elaborated as producing "a frame that captures the problem worth solving and why it was chosen over alternatives". It stays at a single named action rather than the several specific actions of anchor 4, but is well above the generic minimalism of anchor 2.

3 / 5

Completeness

It explicitly answers both parts: what ("Create a framing document from conversation transcripts... a frame that captures the problem worth solving and why it was chosen over alternatives") and when ("Use when the user has transcripts (VTT, call notes, etc.) and wants to produce a frame"). Both are concrete and paired with explicit trigger phrases, matching the top anchor.

5 / 5

Trigger Term Quality

Natural terms include "transcripts", "VTT", "call notes", and "framing document" — good coverage with a file extension (VTT). Common variations a user might say ("meeting recordings", "interview transcripts", "meeting notes") are missing, so it falls just short of comprehensive anchor 5 but clearly beats the 3-anchor's missing-synonyms profile.

4 / 5

Distinctiveness Conflict Risk

This is a clear niche — producing framing documents from conversation transcripts — with distinctive triggers ("framing document", "frame", "VTT", "call notes") that no adjacent skill (summarization, transcription) would claim. Minimal conflict risk, matching anchor 5 rather than the minor-overlap profile of anchor 4.

5 / 5

Total

17

/

20

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

rjs/shaping-skills

Path

framing-doc/SKILL.md

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.