dev-story

Read a story file and implement it. Loads the full context (story, GDD requirement, ADR guidelines, control manifest), routes to the right programmer agent for the system and engine, implements the code and test, and confirms each acceptance criterion. The core implementation skill — run after /story-readiness, before /code-review and /story-done.

Quality

72%

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

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/dev-story/SKILL.md

Quality

Content

77%

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

The body excels at actionability and workflow clarity, with concrete paths, routing tables, validation checkpoints, and error-recovery feedback loops. It is slightly verbose in places and, lacking any bundle files, is monolithic rather than progressively disclosed.

Suggestions

Extract the engine-specialist routing tables and the AskUserQuestion option banks into a reference file under references/, linking to it one level deep to improve progressive disclosure.

Tighten repeated guard phrases ('Do not spawn any programmer agent') into a single stated rule referenced where needed, to reduce token redundancy.

Dimension	Reasoning	Score
Conciseness	The body is mostly dense, actionable procedure rather than concept explanation, but repeats itself ('Do not spawn any programmer agent' appears several times) and includes long AskUserQuestion option enumerations that could be tightened.	2 / 3
Actionability	Highly actionable for an instruction-only orchestrator: exact file paths (docs/architecture/tr-registry.yaml, production/session-state/active.md), concrete routing tables, ready-to-use AskUserQuestion prompts with options, and copy-paste output templates.	3 / 3
Workflow Clarity	Seven clearly sequenced phases with explicit validation checkpoints (STOP/WARN file checks, dependency Status validation, manifest-version mismatch handling) and a feedback-oriented error-recovery protocol, including 'Always produce a partial report'.	3 / 3
Progressive Disclosure	No bundle files exist (references/, scripts/, assets/ absent) and the ~300-line SKILL.md is monolithic; it is well-sectioned but keeps content inline (routing tables, engine-specialist tables, prompt option banks) that could plausibly be split into reference files.	2 / 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 well-niched, naming concrete actions and a distinct pipeline position. It is held back by the absence of an explicit user-facing 'Use when...' trigger and reliance on workflow jargon, which cap trigger-term quality and completeness at 2.

Suggestions

Add an explicit 'Use when ...' clause stating the user situation that triggers this skill (e.g., 'Use when a story is marked Ready and you need to implement it end-to-end').

Pair domain jargon (GDD, ADR, control manifest) with at least one plain-language keyword a user would naturally say, so trigger-term coverage reaches common variations.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions: 'Loads the full context (story, GDD requirement, ADR guidelines, control manifest)', 'routes to the right programmer agent for the system and engine', 'implements the code and test', 'confirms each acceptance criterion'.	3 / 3
Completeness	Clearly answers 'what' the skill does, but offers pipeline placement ('run after /story-readiness, before /code-review and /story-done') rather than an explicit 'when to use it' user trigger, so completeness caps at 2 per the guidelines.	2 / 3
Trigger Term Quality	Contains some natural terms a user might say ('story file', 'implement it') but leans heavily on domain jargon (GDD requirement, ADR guidelines, control manifest) and misses common user variations; no 'Use when...' phrasing.	2 / 3
Distinctiveness Conflict Risk	A clear, narrow niche — implementing a story within a named pipeline (/story-readiness → /dev-story → /code-review → /story-done) — with distinct triggers that make it unlikely to fire for the wrong skill.	3 / 3
	Total	10 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: Donchitos/Claude-Code-Game-Studios
Path: .claude/skills/dev-story/SKILL.md
Commit: 984023d

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.