dev-lifecycle

AI DevKit · Orchestrator for structured SDLC phase skills. Use when the user wants to run the full lifecycle or choose the next phase across requirements, design, planning, implementation, testing, and review.

Quality

86%

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

88%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 a well-structured, highly actionable orchestrator with explicit validation checkpoints and feedback loops. Its only weakness is mild redundancy in task-tracing guidance and limited use of deeper reference files.

Dimension	Reasoning	Score
Conciseness	The body is dense and actionable and assumes Claude's competence without explaining known concepts, but task-tracing guidance is restated across Startup Validation, Plan Before Execution, and Rules, which could be consolidated.	4 / 5
Actionability	Provides copy-paste-ready commands throughout (`npx ai-devkit@latest skill list`, `lint --feature <name>`, `init -a -e claude --built-in --yes`, `task list --json`) plus a real referenced script `scripts/check-status.sh <feature-name>`, covering the common cases.	5 / 5
Workflow Clarity	Startup Validation is a numbered sequence with explicit checkpoints (rerun lint, exit-0 probes, stop-and-report on failure), Plan Before Execution adds an approval gate, and Backward Transitions provide feedback loops for error recovery.	5 / 5
Progressive Disclosure	Clear section structure with a routing table and one real one-level-deep reference (`scripts/check-status.sh`, verified present), but at ~100 lines most material is inline with no further split, leaving minor organization gaps versus anchor 5.	4 / 5
	Total	18 / 20 Passed

Description

83%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 clearly answers what the skill does and when to use it, with concrete trigger phrases and a distinct orchestrator niche. It is slightly held back by the abstract term 'orchestrator' and a few missing natural synonyms.

Dimension	Reasoning	Score
Specificity	Names the domain ('Orchestrator for structured SDLC phase skills') and concrete actions ('run the full lifecycle', 'choose the next phase') across six named phases, but 'orchestrator' is mildly abstract, leaving minor coverage gaps versus the anchor 5.	4 / 5
Completeness	Explicitly states both the what ('Orchestrator for structured SDLC phase skills') and the when ('Use when the user wants to run the full lifecycle or choose the next phase across...') with concrete trigger phrases, matching the anchor 5.	5 / 5
Trigger Term Quality	Includes natural phrases a user would say ('run the full lifecycle', 'choose the next phase') plus the phase names, but is missing common synonyms a user might naturally use.	4 / 5
Distinctiveness Conflict Risk	The full-lifecycle/next-phase orchestrator niche has distinct triggers and minimal conflict risk, with only minor overlap with the individual phase skills it routes to.	4 / 5
	Total	17 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: codeaholicguy/ai-devkit
Path: skills/dev-lifecycle/SKILL.md
Commit: d56e554

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.