CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

drafting

Draft a blog post or social post from an interview transcript using only the author's own words, where every body sentence is quoted, shaped, or a bare connective, with hooks and closings mined from the transcript first. Use after an interview, or when the author hands over a transcript, voice memo, or notes and asks for a draft in their voice.

Quality

97%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

100%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 an exemplary instruction-only skill: tight, concrete, and self-enforcing, with a numbered procedure, an explicit provenance audit as a validation checkpoint, and a ready-to-fill output template. There is no padding, no concepts Claude already knows, and no structural content that belongs in separate files.

DimensionReasoningScore

Conciseness

The body is lean and explains nothing Claude already knows; every section earns its tokens — the your-words rule, the three-kind sentence taxonomy with inline examples, a compact procedure, and a fill-in output template. This matches 'every token earns its place' rather than the level-4 anchor, which requires trimmable over-explanation that isn't present.

5 / 5

Actionability

As an instruction-only skill it provides fully executable guidance: a copy-paste-ready output template, concrete examples for each sentence kind ("So.", "Then the deploy.", `[GAP: …]`), and a specific ordered procedure with criteria for each step (beats: what happened, the decision, the cost, the unguarded position). Per the rubric's scoring notes, absence of code is not penalized when guidance is this actionable.

5 / 5

Workflow Clarity

The seven steps are clearly sequenced and include an explicit validation pass ('Audit provenance. Walk the body sentence by sentence and label each as quoted, shaped, or connective. Rewrite anything you can't label, or cut it') plus revision feedback loops (reshape, cut, or ask the author and add the answer to the transcript). This is not a destructive or batch operation, so no cap applies, and it matches the top anchor with explicit validation and error-recovery loops.

5 / 5

Progressive Disclosure

No bundle files exist and none are needed: the ~90-line skill is appropriately kept in a single file with well-organized, clearly headed sections and no nested or buried references. External skill references (`voice`, `allergist`, `taste-lens`, `guardrails-lens`) are clearly signaled at point of use, matching well-organized single-file structure.

5 / 5

Total

20

/

20

Passed

Description

92%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 that states concrete capabilities in third person and gives an explicit, well-phrased 'Use when' clause with natural trigger synonyms. The only gap is a handful of natural user phrasings (e.g., 'ghostwrite', 'write-up') that would widen trigger coverage.

DimensionReasoningScore

Specificity

The description lists multiple specific concrete actions — drafts blog/social posts from a transcript, restricts every body sentence to quoted/shaped/connective, and mines hooks and closings from the transcript first — with comprehensive coverage of the skill's scope. It fits the 'multiple specific concrete actions' anchor better than the level-4 anchor, which requires minor gaps in coverage that aren't visible here.

5 / 5

Completeness

Both questions are answered explicitly: the 'what' (draft posts from a transcript under the your-words constraint) and the 'when' ('Use after an interview, or when the author hands over a transcript, voice memo, or notes and asks for a draft in their voice') with concrete trigger phrases, matching the top anchor exactly.

5 / 5

Trigger Term Quality

Natural phrases a user would say are well covered ('interview transcript', 'voice memo', 'notes', 'draft', 'in their voice'), with synonyms across input formats. It falls just short of the comprehensive anchor — common phrasings like 'ghostwrite', 'write-up', or 'turn this interview into a post' are absent, matching 'good keyword coverage; a few natural terms missing'.

4 / 5

Distinctiveness Conflict Risk

The transcript-voice-drafting niche is clearly staked out with distinct triggers (transcript, voice memo, interview, in their voice), so it is unlikely to fire for unrelated writing or editing skills. It matches 'clear niche with distinct triggers; minimal conflict risk' rather than the level-4 anchor, which requires overlap risk with closely related skills.

5 / 5

Total

19

/

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

shortrib-labs/content-loop

Path

plugins/drafting/skills/drafting/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.