dev-planning

AI DevKit · Planning phase guidance for creating and reconciling feature task plans. Use when the user wants to create an implementation plan, update planning docs, mark task progress, capture blockers or new tasks, or run dev-lifecycle planning work.

Quality

87%

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

86%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.

A tight, well-structured instruction-only workflow with concrete commands and clear phase sequencing. The main improvement is adding an explicit lint-failure feedback loop and a brief note on what the ai-devkit lint actually validates.

Suggestions

Add a feedback loop after the lint step: 'If lint fails, fix the reported issue and re-run lint before proceeding' to reach top workflow_clarity.

Clarify what `npx ai-devkit@latest lint --feature <name>` validates (e.g. doc paths, task traceability) so the actionability gap from relying on external tool behavior closes.

Optionally note where planning doc paths are confirmed by lint output, reducing the chance of assuming a stale `docs/ai` layout.

Dimension	Reasoning	Score
Conciseness	Lean numbered steps with no padding or explanation of concepts Claude already knows; every line carries an instruction or a concrete command. Not below 5 because nothing reads as over-explanation.	5 / 5
Actionability	Concrete commands ('npx ai-devkit@latest lint --feature <name>') and specific per-task fields (outcome, dependencies, validation evidence) give mostly executable guidance. Not a 5 because several steps rely on external ai-devkit behavior and doc structures that are referenced rather than specified, leaving minor gaps.	4 / 5
Workflow Clarity	Phases are clearly sequenced with numbered steps, a lint checkpoint before phase work, an explicit 'wait for user approval' gate, and 'Next:' transitions. Not a 5 because there is no explicit validate->fix->retry feedback loop when lint fails.	4 / 5
Progressive Disclosure	Under 50 lines with no need for external references and well-organized sections (Phase Contract, Create Initial Plan, Update Planning), matching the rubric's simple-skill exception for a 5. No nested or buried references to penalize.	5 / 5
	Total	18 / 20 Passed

Description

88%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.

A well-constructed description with third-person voice, explicit what-and-when, and concrete trigger phrases. It is strong across all dimensions; the only refinements would be adding synonyms/shorthand variants and sharpening separation from sibling dev-lifecycle phases.

Dimension	Reasoning	Score
Specificity	Names the domain ("Planning phase guidance") and lists multiple concrete actions — create and reconcile task plans, update docs, mark progress, capture blockers, add new tasks — giving comprehensive coverage. Not a 4 because coverage spans the full set of planning operations rather than showing minor gaps.	5 / 5
Completeness	It explicitly states what it does ('Planning phase guidance for creating and reconciling feature task plans') and when to use it with a concrete 'Use when' clause enumerating trigger scenarios. Both what and when are explicit and concrete, matching the top anchor.	5 / 5
Trigger Term Quality	The 'Use when' clause surfaces natural phrases users would say ('create an implementation plan', 'update planning docs', 'mark task progress', 'capture blockers'), giving good keyword coverage. Not a 5 because synonyms and shorthand variants (e.g. 'task list', 'roadmap', 'todo') are absent.	4 / 5
Distinctiveness Conflict Risk	Scoped to the AI DevKit planning phase with distinct dev-lifecycle triggers, giving a clear niche. Not a 5 because 'planning' broadly risks minor overlap with sibling phases (dev-implementation, dev-testing) in the same lifecycle family.	4 / 5
	Total	18 / 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-planning/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.