sdd-apply
Implement tasks from the change, writing actual code following the specs and design. Trigger: "apply", "implement", "implementar", "code it", "build it", "sdd apply", "ejecutar tareas", "/sdd:apply".
86
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Discovery
82%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 has strong trigger term coverage with both English and Spanish variations, and clearly separates the 'what' from the 'when'. However, the capability description is somewhat vague ('writing actual code following the specs') and could benefit from more specific actions. The mix of SDD-specific and generic triggers creates some conflict risk with general coding skills.
Suggestions
Add more specific concrete actions like 'creates functions, modifies classes, updates tests based on SDD task specifications'
Clarify the relationship to SDD workflow to reduce overlap with general coding skills (e.g., 'Executes implementation tasks defined in SDD change documents')
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (implementing tasks from change specs) and a general action (writing code), but lacks specific concrete actions like 'create functions', 'modify classes', or 'update tests'. | 2 / 3 |
Completeness | Clearly answers both what ('Implement tasks from the change, writing actual code following the specs and design') and when (explicit 'Trigger:' clause with multiple trigger terms). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms including 'apply', 'implement', 'code it', 'build it', plus Spanish variations ('implementar', 'ejecutar tareas') and command-style triggers ('/sdd:apply'). | 3 / 3 |
Distinctiveness Conflict Risk | The SDD-specific triggers ('/sdd:apply', 'sdd apply') help distinguish it, but generic terms like 'implement', 'code it', 'build it' could overlap with general coding skills. | 2 / 3 |
Total | 10 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured implementation skill with excellent workflow clarity and actionability. The TDD workflow is particularly well-defined with explicit validation at each step. Minor verbosity in some sections (detection logic duplication, overlapping error tables) prevents a perfect conciseness score, but the content is largely justified given the complexity of the task.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is comprehensive but includes some redundancy (e.g., conflict resolution and error recovery tables overlap conceptually, TDD detection logic is repeated from sdd-tasks). Some sections could be tightened, though most content is necessary for the complex workflow. | 2 / 3 |
Actionability | Provides concrete, executable guidance throughout: specific file paths, exact markdown syntax for task completion, clear pseudocode workflows for TDD cycles, specific test command patterns, and detailed return summary templates with exact formatting. | 3 / 3 |
Workflow Clarity | Excellent multi-step sequencing with explicit validation checkpoints: pre-implementation checklist with stop condition, TDD RED→GREEN→REFACTOR cycle with verification at each step, clear 'STOP and report back' instructions for blockers, and structured error recovery table. | 3 / 3 |
Progressive Disclosure | Well-organized with clear section hierarchy. References external shared files appropriately (persistence-contract.md, engram-convention.md, openspec-convention.md) at one level deep. Content is logically split into detection, execution, persistence, and reporting phases. | 3 / 3 |
Total | 11 / 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 |
|---|---|---|
metadata_field | 'metadata' should map string keys to string values | Warning |
Total | 10 / 11 Passed | |
- 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.