CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

agentic-workflow

Agentic Workflow Pattern

Quality

61%

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 ./.claude/skills/agentic-workflow/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 content is a well-structured, actionable guide with concrete multi-stage orchestration code and monitoring guidance. It is efficient and clear, with only minor redundancy and placeholder gaps preventing top scores.

Suggestions

Resolve the `<task>` placeholder by noting how the task identifier is derived, or link to where it is set.

Briefly define or point to the custom subagent types (oracle, plan-agent, validate-agent, agentica-agent, review-agent) so the Task calls are fully executable.

Add an explicit validate-fix-retry loop description for when the Review Agent's test run fails, to strengthen the feedback loop.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence, using terse bullets and code blocks, with only minor redundancy between the directory structure and key rules that could be trimmed.

4 / 5

Actionability

Each stage provides concrete, mostly copy-pasteable Task invocations and shell monitoring commands, with minor gaps from the undefined `<task>` placeholder and unspecified custom subagent types.

4 / 5

Workflow Clarity

Five stages are clearly sequenced with file-based handoffs and validation checkpoints (Validation Agent, Review Agent test runs, stuck detection), though explicit pass/fail retry loops are only loosely implied.

4 / 5

Progressive Disclosure

Content is well-organized under clear section headers in a single self-contained file with no nested references; minor inline redundancy keeps it just short of fully optimal.

4 / 5

Total

16

/

20

Passed

Description

28%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 terse title that names the skill's domain but specifies no concrete actions or usage triggers. It needs an explicit capabilities list and a 'Use when...' clause to be reliably discoverable.

Suggestions

Add concrete actions, e.g. 'Orchestrates a research-plan-validate-implement-review agent pipeline for implementation tasks'.

Append a 'Use when...' trigger clause, e.g. 'Use when implementing features that benefit from multi-agent research, planning, and validation.'

Include natural synonyms a user might say, such as 'multi-agent workflow', 'agent pipeline', or 'TDD implementation'.

DimensionReasoningScore

Specificity

The description 'Agentic Workflow Pattern' names the domain but states no concrete actions, matching the anchor for naming a domain with minimal or generic actions.

2 / 5

Completeness

It provides only a vague 'what' (a named pattern) and no 'when' trigger guidance; the missing 'Use when...' clause keeps it below completeness midpoint.

2 / 5

Trigger Term Quality

It offers only the technical phrase 'agentic workflow' with no natural user-facing synonyms or variations, sitting at the midpoint-low end of keyword coverage.

2 / 5

Distinctiveness Conflict Risk

The phrase targets a fairly specific niche (multi-agent orchestration) so overlap risk is moderate, though the brevity keeps it from being clearly distinct.

3 / 5

Total

9

/

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

parcadei/Continuous-Claude-v3

Path

.claude/skills/agentic-workflow/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.