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

83%

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 strong orchestrator skill: fully executable commands, explicit validation and recovery loops in every workflow, a clear routing table, and well-defined backward transitions. Its only real costs are repetition of task-tracing and lint rules across sections and the absence of any reference files to split the ~105 lines of operational detail.

Dimension	Reasoning	Score
Conciseness	The body is dense and command-driven with no explanations of concepts Claude already knows; every section is routing or validation guidance. It falls short of lean because task-tracing rules are duplicated between Startup Validation steps 8-9 and the Rules section, and lint usage is repeated between Startup Validation and Rules.	4 / 5
Actionability	Guidance is fully executable: exact commands ("npx ai-devkit@latest skill list", "npx ai-devkit@latest lint --feature <name>", "npx ai-devkit@latest init -a -e claude --built-in --yes"), a concrete phase routing table, and a script invocation with explicit <skill-dir> resolution. Common cases (startup, resume, backward transitions) are each covered with specific steps.	5 / 5
Workflow Clarity	Startup Validation is a numbered sequence with explicit error-recovery loops (install then rerun skill list; lint failure triggers init then rerun lint), a probe-with-fallback for task tracing, an approval gate before execution, and a hard rule "Do not claim completion without fresh verification evidence". Checkpoints and feedback loops are explicit throughout, matching the level-5 anchor.	5 / 5
Progressive Disclosure	Sections are well organized, and the single bundle reference — "Run <skill-dir>/scripts/check-status.sh <feature-name>" — is real, clearly signaled, and one level deep, with phase detail appropriately delegated to the phase skills. It falls short of 5 because at ~105 lines the task-tracing and lint details repeated in Rules could live in a reference file, and the skill ships no references for its own operating details.	4 / 5
	Total	18 / 20 Passed

Description

70%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 has an explicit and concrete 'Use when' trigger with good natural keyword coverage across all six SDLC phases, and a clear distinct niche as the lifecycle orchestrator. Its main weakness is the abstract 'what' — 'Orchestrator for structured SDLC phase skills' says the role but not the concrete capabilities (routing, validation, resume, phase detection).

Suggestions

Make the 'what' concrete: replace 'Orchestrator for structured SDLC phase skills' with specific actions such as 'Routes work across the nine AI DevKit SDLC phases, validates installed phase skills and docs at startup, detects the current phase, and resumes feature work'.

Add natural trigger synonyms users would say, e.g. 'Use when the user wants to run the full SDLC lifecycle, pick or resume the next phase (requirements, design, planning, implementation, testing, or code review), or figure out where a feature left off'.

Lead with the capability summary rather than the 'AI DevKit ·' product prefix so the functional triggers land before brand jargon.

Dimension	Reasoning	Score
Specificity	"Orchestrator for structured SDLC phase skills" and "run the full lifecycle or choose the next phase" name the domain and 1-2 actions, but the actions are generic orchestration verbs rather than several concrete operations, matching the 'domain and 1-2 concrete actions' anchor. It is above a 2 because it does state what it orchestrates and the two routing actions, but below a 4 because no list of specific capabilities is given.	3 / 5
Completeness	Both parts are present: an explicit "Use when the user wants to run the full lifecycle or choose the next phase" trigger clause and a what-statement ("Orchestrator for structured SDLC phase skills"). The 'when' is explicit and concrete, but the 'what' is somewhat abstract, so it does not clearly reach the level-5 anchor of fully concrete answers to both.	4 / 5
Trigger Term Quality	"run the full lifecycle", "choose the next phase", and the six phase names ("requirements, design, planning, implementation, testing, and review") give good natural keyword coverage a user would say. Missing common variations such as "SDLC", "code review", or "resume work", so it falls short of the comprehensive-synonyms anchor at 5.	4 / 5
Distinctiveness Conflict Risk	The lifecycle-orchestration niche ("run the full lifecycle or choose the next phase") is distinct from the individual phase skills it routes to, giving minimal conflict on the primary triggers. Minor overlap risk remains because phase words like "requirements", "design", and "review" also naturally trigger the individual dev-* phase skills.	4 / 5
	Total	15 / 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: 7ef0cd5

Reviewed: 8 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.