CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

find-the-first-jobs

Finds the work that eats the owner's time and repeats most, and proposes the first jobs AI could take on. Use when Andrew or the owner asks where the time goes, what to automate or hand to AI first, or to diagnose the business.

Quality

85%

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

SKILL.md
Quality
Evals
Security

Quality

Content

86%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.

A lean, well-structured instruction-only skill: every token adds non-obvious guidance, the method and output are specified concretely, and safety constraints (human-only items, drafts-only, change nothing) are explicit. The only gaps are the absence of a sample plan format and fallback handling for sparse data.

DimensionReasoningScore

Conciseness

Every line instructs something Claude could not infer ("What you cannot know without being told", the count-times-minutes method, provenance labeling, drafts-only constraint); there is no padding and no explanation of concepts Claude already knows.

5 / 5

Actionability

The guidance is concrete and executable for an instruction-only skill — count occurrences in email/calendar/files, ask the owner for per-task minutes, multiply, label each number as counted or estimated, propose the top three jobs with a defined three-part breakdown, write a "plan" to the company brain. Minor gaps: no example of the plan's structure and it presumes the location of the "company brain" is already known.

4 / 5

Workflow Clarity

The sequence is clear — read the company brain, then email/calendar/files, rank the work, propose three jobs, write the plan, summarize to the owner — and the labeling requirement ("Label every number as counted... or as the owner's estimate") acts as a data-quality checkpoint. It falls short of the top anchor only because there are no fallback steps for sparse data or an unresponsive owner; the destructive/batch validation cap does not apply since the skill is read-only.

4 / 5

Progressive Disclosure

This is a self-contained skill under 50 lines with no bundle files (no references/, scripts/, or assets/ exist) and no external references needed; the body is well organized into an intro line, a labeled constraint list, and a closing output instruction, which merits the top score for a simple skill.

5 / 5

Total

18

/

20

Passed

Description

78%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 well-formed description with third-person voice, a clear what, and an explicit 'Use when' clause with natural trigger phrases. Its main weakness is specificity: it summarizes the outcome in two actions rather than naming the concrete analysis steps and deliverables it performs.

Suggestions

Name the concrete actions and deliverable in the 'what' clause, e.g., "Counts recurring tasks in email, calendar and files, ranks them by owner hours, and drafts the first three jobs to hand to AI".

Mention the data sources it reads (email, calendar, files) so the capability scope is explicit and distinguishable from generic business-diagnosis skills.

Add one or two natural trigger synonyms such as "save the owner time" or "delegate to AI" to broaden keyword coverage.

DimensionReasoningScore

Specificity

"Finds the work that eats the owner's time and repeats most" and "proposes the first jobs AI could take on" name the domain with two concrete actions, but the description does not list several specific actions (e.g., counting recurring tasks, ranking by owner hours, drafting a plan), so it matches the 1-2-concrete-actions anchor rather than the 'several specific actions' anchor.

3 / 5

Completeness

It explicitly answers both questions: the 'what' ("Finds the work... and proposes the first jobs AI could take on") and an explicit 'when' with three concrete trigger phrases ("Use when Andrew or the owner asks where the time goes, what to automate or hand to AI first, or to diagnose the business"), matching the top anchor.

5 / 5

Trigger Term Quality

Trigger phrases like "where the time goes", "what to automate", "hand to AI first", and "diagnose the business" are natural things an owner would say, but common synonyms such as "save me time", "delegate", or "offload" are missing, placing it just below comprehensive coverage.

4 / 5

Distinctiveness Conflict Risk

The niche (first-jobs-for-AI triage for a business owner) and owner-specific triggers ("Andrew or the owner") are distinct, but "diagnose the business" is broad enough to overlap with general business-analysis skills, leaving minor conflict risk.

4 / 5

Total

16

/

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

4W-dev/andrewrendon-plugin

Path

plugins/andrewrendon/skills/find-the-first-jobs/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.