claude-devfleet

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

Quality

84%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

76%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 is actionable and well-structured with concrete tool-call examples, but its batch/auto-merge workflow lacks explicit validation checkpoints, capping workflow clarity. Some redundancy across the Examples and Workflow sections could be trimmed.

Suggestions

Add an explicit validation/verification checkpoint after auto-merge (e.g. confirm merge succeeded and tests pass before auto-dispatching dependent missions) to lift workflow_clarity above the batch-operation cap of 3.

Consolidate the three overlapping Examples (Full auto / Manual / Sequential) into one canonical walkthrough plus a short variations table to reduce redundancy with the Workflow section.

Add a brief validate→fix→retry feedback loop for failed missions beyond just "read its report before retrying", e.g. re-dispatch only after confirming the failure cause is resolved.

Dimension	Reasoning	Score
Conciseness	Mostly lean and efficient with no padding of concepts Claude already knows, but the three Examples sections repeat the Plan→Dispatch→Monitor→Report workflow near-verbatim and could be consolidated.	4 / 5
Actionability	Provides concrete, copy-paste-ready tool invocations with arguments (e.g. create_mission(..., auto_dispatch=true, depends_on=["..."])) covering the common plan/auto/manual/sequential cases.	5 / 5
Workflow Clarity	The Plan→Dispatch→Monitor→Report sequence is clearly numbered, but this batch/auto-merge operation lacks explicit validation checkpoints (e.g. verify auto-merge succeeded, validate before proceeding), which caps workflow clarity at 3 per the rubric.	3 / 5
Progressive Disclosure	Well-organized into clear sections (When to Use, Setup, How It Works, Tools, Workflow, Examples, Guidelines) with no bundle files needed; minor gaps are the overlapping Examples and absence of a one-level-deep reference structure.	4 / 5
	Total	16 / 20 Passed

Description

92%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 specific, trigger-rich, and clearly distinguishes the skill's niche. It explicitly covers both what the skill does and when to use it with natural phrasing.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "plan projects, dispatch parallel agents in isolated worktrees, monitor progress, and read structured reports" — giving comprehensive coverage of capabilities rather than minor gaps.	5 / 5
Completeness	Explicitly answers both what (orchestrate/plan/dispatch/monitor/report) and when ("Use when dispatching parallel coding agents across isolated worktrees and tracking their reports") with concrete triggers.	5 / 5
Trigger Term Quality	Strong natural phrases users would say ("dispatch parallel agents", "isolated worktrees", "tracking their reports"), but lacks the comprehensive synonym/file-extension spread of a 5.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (multi-agent coding orchestration across isolated worktrees) with distinct triggers and minimal overlap risk with other skills.	5 / 5
	Total	19 / 20 Passed

Validation

93%

Warnings & errors only

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

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: affaan-m/ECC
Path: skills/claude-devfleet/SKILL.md
Commit: 06c5e11

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

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.