recipe-implement
Orchestrate the complete implementation lifecycle from requirements to deployment
32
27%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/recipe-implement/SKILL.mdQuality
Discovery
0%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This description is extremely vague and reads like a buzzword-laden tagline rather than a functional skill description. It fails to specify any concrete actions, lacks natural trigger terms users would use, provides no 'when to use' guidance, and is so generic it would conflict with nearly any development-related skill.
Suggestions
Replace the abstract phrase 'orchestrate the complete implementation lifecycle' with specific concrete actions (e.g., 'Generates project plans, creates boilerplate code, sets up CI/CD pipelines, writes deployment scripts').
Add an explicit 'Use when...' clause with natural trigger terms (e.g., 'Use when the user asks to build a new feature end-to-end, scaffold a project, or set up a deployment pipeline').
Narrow the scope to a distinct niche to avoid conflicting with other skills—currently it overlaps with any skill related to coding, planning, testing, or deploying.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description uses vague, abstract language like 'orchestrate the complete implementation lifecycle' without listing any concrete actions. Terms like 'requirements' and 'deployment' are broad categories, not specific capabilities. | 1 / 3 |
Completeness | The 'what' is extremely vague (orchestrate a lifecycle) and there is no 'when' clause or explicit trigger guidance at all. Both components are weak or missing. | 1 / 3 |
Trigger Term Quality | The terms used ('implementation lifecycle', 'orchestrate', 'requirements to deployment') are abstract project management jargon, not natural keywords a user would type. Users would say things like 'build a feature', 'deploy my app', or 'implement this', not 'orchestrate the implementation lifecycle'. | 1 / 3 |
Distinctiveness Conflict Risk | This description is so broad ('requirements to deployment') that it could conflict with virtually any coding, project management, CI/CD, or development skill. It has no clear niche or distinct triggers. | 1 / 3 |
Total | 4 / 12 Passed |
Implementation
55%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill defines a comprehensive orchestration workflow with strong workflow clarity—clear decision tables, validation loops, and explicit stopping points. However, it suffers from heavy dependency on external references that aren't provided in the bundle, making it difficult to evaluate or execute in isolation. The content is moderately concise but could be tightened by reducing repetitive references and consolidating overlapping sections.
Suggestions
Provide the referenced bundle files (subagents-orchestration-guide, sub-agents.md) or inline the critical information needed to execute the flows, so the skill is self-contained enough to be actionable.
Split detailed sections (e.g., Post-Implementation Verification, Final Cleanup) into separate reference files and keep SKILL.md as a concise overview with clear navigation links.
Reduce repetitive mentions of 'subagents-orchestration-guide skill' by establishing the reference once at the top and using shorter references thereafter.
Add a concrete end-to-end example showing a small-scale flow execution with actual file paths and subagent invocations to make the orchestration pattern tangible.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is moderately efficient but includes repetitive references to 'subagents-orchestration-guide skill' and some redundant structural elements (e.g., the pre-execution checklist partially overlaps with the execution decision flow). Several sections could be tightened, though most content is non-obvious orchestration logic that Claude wouldn't inherently know. | 2 / 3 |
Actionability | The skill provides structured decision tables, specific subagent types, and clear step sequences, but relies heavily on external references (subagents-orchestration-guide, various sub-agent skills) without providing their content. Key details like actual subagent prompt templates and concrete file path examples are missing, making it not fully executable on its own. | 2 / 3 |
Workflow Clarity | The multi-step workflows are clearly sequenced with explicit validation checkpoints: the 4-step task execution cycle has clear pass/fail branching, the post-implementation verification has a fix-and-rerun loop, the implementation readiness check has a decision table with explicit stop/continue gates, and stopping points are explicitly marked throughout. | 3 / 3 |
Progressive Disclosure | The skill heavily references external files and skills (subagents-orchestration-guide, sub-agents.md, various sub-agent skills, recipe-prepare-implementation) but no bundle files are provided, making it impossible to follow the references. The SKILL.md itself is a monolithic wall of orchestration logic (~150+ lines) with no clear separation into overview vs. detailed reference files. | 1 / 3 |
Total | 8 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- shinpr/claude-code-workflows
- Commit
adf2e4d
- Reviewed
Table of Contents
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.