recipe-implement
Orchestrate the complete implementation lifecycle from requirements to deployment
39
25%
Does it follow best practices?
Impact
Pending
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 far too vague and abstract to be useful for skill selection. It reads like a high-level mission statement rather than a functional skill description, using buzzwords like 'orchestrate' and 'implementation lifecycle' without specifying any concrete actions. It lacks trigger terms, a 'Use when' clause, and any distinguishing specificity that would help Claude select it appropriately from a pool of skills.
Suggestions
Replace abstract language with specific concrete actions (e.g., 'Breaks down feature requirements into tasks, generates implementation plans, writes code, creates tests, and prepares deployment configurations').
Add an explicit 'Use when...' clause with natural trigger terms (e.g., 'Use when the user asks to build a feature end-to-end, implement a spec, or scaffold a new project from requirements').
Narrow the scope to a distinct niche to reduce conflict risk — 'requirements to deployment' covers nearly all of software engineering, so specify what kind of implementation (e.g., web apps, APIs, microservices) or what methodology is followed.
| 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 description vaguely addresses 'what' (orchestrate implementation lifecycle) but provides no 'when' clause or explicit trigger guidance. Both the what and when are very weak. | 1 / 3 |
Trigger Term Quality | The keywords used ('implementation lifecycle', 'orchestrate', 'requirements to deployment') are abstract project management jargon, not natural terms a user would type when seeking help. Users would more likely say things like 'build a feature', 'deploy my app', or 'implement this spec'. | 1 / 3 |
Distinctiveness Conflict Risk | This description is extremely generic and could conflict with virtually any coding, project management, DevOps, or software engineering skill. 'Implementation lifecycle from requirements to deployment' encompasses nearly everything in software development. | 1 / 3 |
Total | 4 / 12 Passed |
Implementation
50%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides a structured orchestration framework with clear role definition, decision flows, and a defined task execution cycle. Its main weaknesses are heavy reliance on external references without clear navigation to them, some redundancy in restating compliance requirements, and a lack of fully concrete/executable examples. The workflow is reasonably clear but would benefit from more explicit validation checkpoints and better-signaled cross-references.
Suggestions
Add explicit file path links to all referenced skills and sub-agent definitions (e.g., '[subagents-orchestration-guide](./subagents-orchestration-guide.md)') so navigation is one-click rather than implied.
Consolidate the repeated 'subagents-orchestration-guide compliance' references into a single authoritative section to reduce redundancy and improve conciseness.
Add a concrete end-to-end example showing a small-scale flow from requirement to commit, with actual sub-agent invocation prompts and expected responses, to improve actionability.
Make validation/verification steps more explicit in the 4-step task cycle—e.g., specify what 'quality check' entails and what constitutes a pass/fail before committing.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is moderately efficient but includes some redundancy (e.g., repeatedly referencing 'subagents-orchestration-guide skill' and restating the orchestrator identity). Some sections like the pre-execution checklist and compliance sections overlap in intent. However, it avoids explaining basic concepts Claude would already know. | 2 / 3 |
Actionability | The skill provides structured decision tables, checklists, and named sub-agent invocations with specific subagent_type values, which is concrete. However, it heavily relies on external references (subagents-orchestration-guide, various sub-agents) without providing their actual content, and lacks executable code examples or copy-paste ready commands beyond the constraint suffix template. | 2 / 3 |
Workflow Clarity | The multi-step workflow is outlined with phases and a 4-step task execution cycle, and stopping points are mentioned. However, validation checkpoints are somewhat implicit—the flow between steps relies on understanding external flow definitions, and error recovery paths (e.g., escalation, re-execution) are mentioned but not fully detailed with explicit feedback loops for all failure modes. | 2 / 3 |
Progressive Disclosure | The content references external skills and sub-agents appropriately (subagents-orchestration-guide, various sub-agent types), suggesting a layered architecture. However, the references are not clearly signaled with links or file paths, and the main document itself is somewhat dense with inline detail that could be better organized or split out. | 2 / 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
2e719be
- 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.