CtrlK
BlogDocsLog inGet started
Tessl Logo

agent-workflow-automation

Agent skill for workflow-automation - invoke with $agent-workflow-automation

58

6.33x
Quality

38%

Does it follow best practices?

Impact

95%

6.33x

Average score across 3 eval scenarios

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/agent-workflow-automation/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

27%

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 over-long catalog of GitHub Actions and swarm examples that are mostly non-executable due to corrupted path syntax, with no clear workflow sequencing or validation gates and a monolithic structure whose only references point to missing files.

Suggestions

Fix the corrupted path separators ('$' -> '/') so the YAML and JS examples are actually executable, or justify the substitution.

Collapse the redundant command/workflow examples into a concise quick-start and move the long template catalog into reference files.

Add a sequenced workflow with explicit validation checkpoints and feedback loops for deployment and batch CI operations.

DimensionReasoningScore

Conciseness

The body is ~600 lines of encyclopedic, heavily redundant examples — many near-duplicate 'npx ruv-swarm actions <verb>' command blocks and overlapping workflow templates — which pads the context without adding proportional value, the verbosity the rubric penalizes even when accurate.

1 / 3

Actionability

It provides concrete-looking YAML and bash snippets, but paths are corrupted with '$' separators (e.g. '.github$workflows$swarm-ci.yml', 'actions$checkout@v3', 'dist$index.js') and the 'mcp__claude-flow__swarm_init { ... }' blocks are not valid bash, so the examples are not copy-paste executable.

2 / 3

Workflow Clarity

Content is organized into feature sections but reads as a reference catalog rather than a sequenced process; for CI/CD automation involving deployment there are no explicit validation checkpoints or feedback loops, which caps workflow clarity at 2.

2 / 3

Progressive Disclosure

This is a monolithic wall of text with all detail inline, and the only file references ('.$swarm-pr.md', '.$swarm-issue.md', '.$sync-coordinator.md') use broken '$' paths and refer to bundle files that do not exist in references/scripts/assets.

1 / 3

Total

6

/

12

Passed

Description

50%

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 identifies the skill's domain and invocation command but omits concrete capabilities and any explicit 'use when' trigger guidance, leaving it generic and incomplete.

Suggestions

Replace the boilerplate with concrete actions, e.g. 'Create, optimize, and debug GitHub Actions CI/CD pipelines...'.

Add an explicit trigger clause: 'Use when the user asks to set up, fix, or optimize GitHub Actions workflows or CI/CD pipelines.'

Include natural trigger terms users would actually say (GitHub Actions, CI/CD, pipelines, workflow files).

DimensionReasoningScore

Specificity

The description names the domain ('workflow-automation') but lists no concrete actions; 'Agent skill for workflow-automation - invoke with $agent-workflow-automation' describes what kind of skill it is rather than what it does, so it sits above a fully vague description but below one that enumerates actions.

2 / 3

Completeness

It states a weak 'what' (an agent skill for workflow automation) but provides no 'Use when...' trigger guidance, and per the rubric a missing explicit trigger clause caps completeness at 2.

2 / 3

Trigger Term Quality

'workflow-automation' is a relevant keyword, but '$agent-workflow-automation' is a command invocation rather than natural language a user would say; common variations like CI/CD, GitHub Actions, or pipelines are missing.

2 / 3

Distinctiveness Conflict Risk

'workflow-automation' is somewhat specific and the '$agent-workflow-automation' command form is distinct, but the domain is broad enough that it could overlap with general CI/CD or automation skills.

2 / 3

Total

8

/

12

Passed

Validation

87%

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

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (640 lines); consider splitting into references/ and linking

Warning

relative_links

Relative link issues: 3 missing

Warning

Total

14

/

16

Passed

Repository
ruvnet/claude-flow
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.