CtrlK
BlogDocsLog inGet started
Tessl Logo

draft-follow-ups

Use when drafting finite evidence-backed follow-ups while treating clear negative replies and stop requests as terminal.

60

Quality

68%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/draft-follow-ups/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

75%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 lean, well-structured instruction-only skill with concrete gates, an explicit output format, and a quality checklist that together make it highly actionable. It falls just short of top marks because guardrail content partly repeats the workflow, no worked output example is shown, and the file marginally exceeds the simple-skill line.

Suggestions

Add one fully worked example showing the complete structured output for a contact (e.g. Avery's overview request) to push actionability and workflow clarity toward 5.

De-duplicate the prohibition list between workflow steps 5-6 and the Guardrails section, or explicitly frame Guardrails as a consolidation, to trim tokens.

If the example or output-format detail grows, move it into a referenced file to keep the overview lean and let progressive disclosure score higher.

DimensionReasoningScore

Conciseness

The body is dense and purposeful with no padding or explanation of concepts Claude already knows, though the Guardrails section repeats prohibitions already stated in workflow steps 5-6 (invention, stop-after-negative). Not a 5 because that deliberate reinforcement costs some tokens.

4 / 5

Actionability

Concrete decision rules, exact status labels (STOP, NEEDS VERIFICATION, NOT READY TO SEND, DRAFT FOR HUMAN REVIEW), and an explicit per-contact output format make the guidance directly executable. Not a 5 because no fully worked output example demonstrates the structured result end-to-end.

4 / 5

Workflow Clarity

A clearly sequenced 7-step workflow with explicit validation gates and a separate readiness assessment, plus a Quality check checklist; validation is present so the batch/destructive cap does not apply. Not a 5 because there is no concrete validate-fix-retry error-recovery loop demonstrated.

4 / 5

Progressive Disclosure

No bundle files exist and the single self-contained file is well-organized into clearly headed sections (Purpose, Required inputs, Workflow, Output format, Guardrails, Quality check, Example invocation) with no nested references. Not a 5 because at ~56 lines it sits just above the under-50 simple-skill threshold that would let well-organized sections alone score 5.

4 / 5

Total

16

/

20

Passed

Description

62%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 is third-person, concise, and pairs an explicit 'Use when' trigger with a recognizable niche, giving solid completeness and distinctiveness. It is held back by mid-range specificity and trigger-term coverage that omit common synonyms a user would actually say.

Suggestions

Add common user-facing synonyms to the trigger, e.g. 'opt-out', 'unsubscribe', or 'outreach follow-up', so the skill surfaces for natural phrasings.

Name one or two more concrete capabilities (e.g. 'classify reply meaning and label drafts for human review') to lift specificity toward comprehensive coverage.

Tighten the 'when' clause to state the scenario explicitly, such as 'Use when managing contact outreach follow-ups...', to reduce overlap with generic drafting skills.

DimensionReasoningScore

Specificity

Names the domain ('drafting finite evidence-backed follow-ups') and one to two concrete behaviors ('treating clear negative replies and stop requests as terminal'), but coverage is not comprehensive. Not a 4 because it does not list several distinct actions with only minor gaps.

3 / 5

Completeness

The 'Use when...' clause explicitly supplies both the what (draft evidence-backed follow-ups and treat stops as terminal) and the when (drafting follow-ups). Not a 5 because the trigger context is slightly less explicit and lacks the synonym/extension breadth of the top anchor.

4 / 5

Trigger Term Quality

Includes some relevant natural terms ('drafting', 'follow-ups', 'stop requests', 'negative replies') but misses common synonyms a user might say such as 'opt-out', 'unsubscribe', or 'outreach'. Not a 4 because keyword coverage lacks the natural variations users would commonly invoke.

3 / 5

Distinctiveness Conflict Risk

The compliance-tinged follow-up drafting niche with terminal-stop handling is mostly distinct from other skills. Not a 5 because the broad word 'drafting' carries minor overlap risk with general drafting or messaging skills.

4 / 5

Total

14

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
llaskin/AI-SDR-Skill-Pack
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.