CtrlK
BlogDocsLog inGet started
Tessl Logo

claude-devfleet

Orchestrate multi-agent coding tasks via Claude DevFleet — plan projects, dispatch parallel agents in isolated worktrees, monitor progress, and read structured reports.

60

Quality

70%

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 ./skills/claude-devfleet/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

72%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is highly actionable with concrete tool calls and a clear sequenced workflow, and it is well-organized as a self-contained skill. The main weaknesses are mild redundancy across the example/workflow sections and the absence of a strong validation feedback loop for batch dispatch.

Suggestions

Consolidate the repeated plan→dispatch→monitor→report narrative so the flow is stated once authoritatively and examples only show variants.

Add an explicit validation checkpoint in the dispatch workflow, e.g. verify agent slot availability and re-check mission status with a defined retry/recovery loop on failure.

Make the failure-recovery loop concrete: on a failed mission, specify read report → diagnose → re-dispatch with adjusted prompt rather than leaving it as a guideline.

DimensionReasoningScore

Conciseness

The body is mostly lean (tool table, commands, steps), but the plan→dispatch→monitor→report flow is restated across 'How It Works', 'Workflow', and 'Examples', adding redundancy that could be tightened.

2 / 3

Actionability

Concrete tool signatures with parameters, an exact `claude mcp add` command, and copy-paste-ready example call sequences give fully executable, specific guidance.

3 / 3

Workflow Clarity

Steps are clearly sequenced and there is some validation (confirm plan before dispatch, read report before retry), but the core parallel/batch dispatch flow lacks an explicit validate→fix→retry checkpoint loop, capping clarity at 2 for a batch-operation context.

2 / 3

Progressive Disclosure

No bundle files exist, so the skill is self-contained with well-organized sections (When to Use, Setup, How It Works, Tools, Workflow, Examples, Guidelines) and no nested references.

3 / 3

Total

10

/

12

Passed

Description

67%

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 specific and distinctive, naming concrete orchestration actions tied to a named tool. It falls short on completeness and trigger-term quality because it omits an explicit 'Use when' trigger and leans on technical phrasing.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when you need to run multiple Claude Code agents in parallel on a coding project.'

Broaden trigger terms with natural user phrasings like 'parallel coding', 'multiple agents', or 'fan out agents'.

Keep the concrete action list but ensure a clear 'when' trigger appears directly in the description, not only the body.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'plan projects, dispatch parallel agents in isolated worktrees, monitor progress, and read structured reports' — matching the anchor for listing several specific concrete actions.

3 / 3

Completeness

The 'what' is strong, but there is no 'Use when...' clause or equivalent explicit trigger in the description; the 'when' guidance lives only in the body, so per the guidelines completeness is capped at 2.

2 / 3

Trigger Term Quality

Relevant keywords like 'multi-agent coding tasks' and 'parallel agents' appear, but coverage of natural variations a user would say is partial and the phrasing leans technical ('Claude DevFleet', 'isolated worktrees').

2 / 3

Distinctiveness Conflict Risk

The named 'Claude DevFleet' tool plus the multi-agent/worktree niche is clearly distinguishable and unlikely to trigger for the wrong skill.

3 / 3

Total

10

/

12

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.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository
affaan-m/ECC
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.