CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

workflow-automation

You are a workflow automation architect who has seen both the promise and the pain of these platforms. You've migrated teams from brittle cron jobs to durable execution and watched their on-call burden drop by 80%.

Quality

42%

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

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/workflow-automation/SKILL.md

The canonical home for this skill is workflow-automation in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

36%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 has a genuinely useful platform tradeoff overview (n8n vs Temporal vs Inngest vs DBOS) and reasonable sectioning, but nearly everything else is skeleton or filler: anti-patterns with no explanations, a corrupted Sharp Edges table with truncated solutions, no code or commands, and a circular 'When to Use'. It reads like an unfinished outline rather than an instructive skill.

Suggestions

Rebuild the Sharp Edges table: give each row a real issue name (e.g. 'Non-idempotent payment retries'), and complete each solution with a concrete example, such as a short code snippet showing an idempotency key or an Inngest onFailure handler instead of a comment fragment ending in a colon.

Add executable content per platform — a minimal durable-workflow example (Inngest or Temporal step function) and one n8n production checklist — so the actionability hints ('use exponential backoff', 'set timeouts') become copy-paste-ready guidance.

Fill or remove the empty sections: give each Anti-Pattern 1-2 sentences on why it fails, replace the keyword-only Capabilities list and the circular 'When to Use' sentence with a concrete decision guide (which platform for which situation).

DimensionReasoningScore

Conciseness

The body is short but padded with non-earning tokens: a capabilities keyword list, Anti-Pattern headers with no content, a persona paragraph duplicating the description, and the circular filler 'This skill is applicable to execute the workflow or actions described in the overview.' Not 4 because the filler goes beyond minor trimming; not 2 because there is no concept over-explanation and the platform tradeoff paragraph is genuinely informative.

3 / 5

Actionability

High-level hints exist ('# ALWAYS use idempotency keys for external calls:', '# ALWAYS set timeouts on activities:', 'exponential backoff') but there is no code, no commands, no platform-specific examples, and every Sharp Edges 'solution' is a truncated comment fragment — e.g. 'Break long workflows into checkpointed steps:' explains nothing about how. Fits 'minimal concrete guidance; high-level hints but missing the specific steps'; not 1 because some actionable directives are stated, not 3 because nothing is executable or complete.

2 / 5

Workflow Clarity

The Patterns section sketches architectural concepts ('Steps execute in order, each output becomes next input') but presents no operational sequence for Claude to follow and no validation checkpoints anywhere. Fits 'rough sequence present but many gaps' loosely via the pattern sketches; not 3 because no actual steps for executing the skill's task are listed, only concept descriptions.

2 / 5

Progressive Disclosure

It is a single appropriately-sized file with clear section headers and no bundle references to manage, which is fine for its length. However, organization gaps exceed 'minor': the Sharp Edges table is malformed (every row's Issue column literally reads 'Issue' and solutions are cut off mid-comment), and Anti-Patterns sections are empty headers. Fits 'some structure but could be better organized'; not 4 because broken/placeholder content undermines navigation.

3 / 5

Total

10

/

20

Passed

Description

22%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 a second-person persona introduction rather than a capability description: it says nothing about what the skill does or when to invoke it, and contains no explicit trigger guidance. Its only redeeming quality is a handful of relevant domain keywords (cron jobs, durable execution).

Suggestions

Rewrite the description in third person stating concrete actions, e.g. 'Designs and implements automated workflows on n8n, Temporal, Inngest, and DBOS: durable execution, idempotency, retries, and scheduled/background jobs.'

Append an explicit trigger clause such as 'Use when the user asks to automate a workflow, replace cron jobs, add retries/durable execution to background tasks, or choose a workflow platform (n8n, Temporal, Inngest, DBOS).'

Drop the persona biography and the unverifiable statistic ('on-call burden drop by 80%') — they consume the description budget without aiding skill selection or invocation.

DimensionReasoningScore

Specificity

The description is a persona biography ('You are a workflow automation architect who has seen both the promise and the pain') with zero concrete skill actions; 'migrated teams from brittle cron jobs' and 'on-call burden drop by 80%' are past-tense character claims, not capabilities. It only marginally names the domain ('workflow automation architect') and is written in second person, which the guidelines penalize by reducing specificity by 1, landing at 1 rather than 2.

1 / 5

Completeness

Neither 'what does this skill do' nor 'when should it be used' is stated anywhere — the entire text is persona framing ('You've migrated teams... watched their on-call burden drop'). This matches the anchor 'missing both what and when', and the missing 'Use when...' clause would cap it at 3 regardless; it cannot reach 2 because even a vague 'what' of the skill's function is absent.

1 / 5

Trigger Term Quality

Contains some relevant domain keywords ('workflow automation', 'cron jobs', 'durable execution') but misses the natural phrases and synonyms a user would actually say ('automate tasks', 'job queue', 'scheduled jobs', 'background jobs', platform names like n8n/Temporal). Not 2 because several genuinely relevant keywords are present; not 4 because common variations users would speak are absent.

3 / 5

Distinctiveness Conflict Risk

The niche (durable workflow execution, cron-job migration) is somewhat specific, but the persona framing provides no explicit triggers to distinguish it from overlapping devops, scheduling, or backend skills. Fits 'somewhat specific but could still overlap with similar skills'; not 4 because there are no distinct trigger phrases establishing a clear niche.

3 / 5

Total

8

/

20

Passed

Validation

93%

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

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

administrakt0r/AI-Agents-Safe-Coding-Skills

Path

plugins/AI-Agents-Safe-Coding-Skills-claude/skills/workflow-automation/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.