recipe-build
Execute decomposed tasks in autonomous execution mode
44
31%
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-build/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 abstract, relying on jargon ('decomposed tasks', 'autonomous execution mode') without specifying any concrete capabilities, domains, or trigger conditions. It would be nearly impossible for Claude to correctly select this skill from a pool of alternatives, as it provides no distinguishing information about what it actually does or when it should be used.
Suggestions
Replace abstract language with concrete actions: specify what types of tasks are executed (e.g., 'Runs multi-step build pipelines, deploys services, processes batch data transformations').
Add an explicit 'Use when...' clause with natural trigger terms that users would actually say (e.g., 'Use when the user asks to run a workflow, execute a pipeline, or automate a sequence of steps').
Clarify the domain or niche to distinguish this skill from other task-execution skills (e.g., specify whether this is for CI/CD, data processing, code generation workflows, etc.).
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description uses vague, abstract language ('decomposed tasks', 'autonomous execution mode') without listing any concrete actions. There is no indication of what specific tasks are performed. | 1 / 3 |
Completeness | The description weakly addresses 'what' with abstract language and completely lacks any 'when' clause or explicit trigger guidance. | 1 / 3 |
Trigger Term Quality | The terms 'decomposed tasks' and 'autonomous execution mode' are technical jargon that users would not naturally say. No common, natural keywords are present. | 1 / 3 |
Distinctiveness Conflict Risk | 'Execute decomposed tasks' is extremely generic and could apply to virtually any skill that performs multi-step work, creating high conflict risk with many other skills. | 1 / 3 |
Total | 4 / 12 Passed |
Implementation
62%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 solid orchestration workflow with clear sequencing, explicit validation gates, and well-defined escalation paths. Its main weaknesses are moderate verbosity in places and incomplete actionability—sub-agent invocations are described but not fully specified with all parameters. The progressive disclosure could be improved with clearer cross-references to dependent skills.
Suggestions
Make sub-agent invocations fully actionable by showing complete Agent tool call examples with all required parameters (not just subagent_type and description).
Add explicit links to referenced skills (e.g., [subagents-orchestration-guide](./subagents-orchestration-guide.md)) rather than just naming them inline.
Tighten the pre-execution section by merging the checklist with the decision flow table to eliminate redundancy.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is moderately efficient but includes some redundancy (e.g., the pre-execution checklist partially duplicates the decision flow table, and some explanatory text could be tightened). The constraint suffix block and some framing language add tokens without proportional value. | 2 / 3 |
Actionability | Provides concrete sub-agent invocation patterns with specific subagent_type values and structured response fields to check, but many steps remain at a descriptive level rather than fully executable. The Agent tool invocations are described but not shown as complete, copy-paste-ready calls with all required parameters. | 2 / 3 |
Workflow Clarity | The 4-step task cycle is clearly sequenced with explicit validation checkpoints (escalation check, quality-fixer approval before commit, security review after all tasks). The decision flow table for pre-execution is well-structured, and feedback loops (needs_revision → return to step 2) are explicitly defined. | 3 / 3 |
Progressive Disclosure | References to other skills (subagents-orchestration-guide, task-decomposer, task-executor, quality-fixer, security-reviewer) are mentioned but not consistently linked as navigable references. The content is reasonably structured with clear sections, but some content (like the decision flow table and the decomposition phase) could be better signaled or split for discoverability. | 2 / 3 |
Total | 9 / 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.