psi
Plan-spec-implement workflow for structured development. Only use when explicitly directed by user or when mentioned in project AGENTS.md file. Generates ephemeral plans in ~/.dot-agent/, applies specs to project docs, then implements test-first.
82
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
85%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 is a well-crafted description that clearly defines a specific workflow with explicit trigger conditions. The description excels at completeness and distinctiveness by requiring explicit activation, which prevents accidental triggering. Minor improvement could be made by including more natural language variations of the technical terms.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Generates ephemeral plans', 'applies specs to project docs', 'implements test-first'. Also specifies the location '~/.dot-agent/' and the workflow structure. | 3 / 3 |
Completeness | Clearly answers both what ('Plan-spec-implement workflow... Generates ephemeral plans, applies specs, implements test-first') AND when ('Only use when explicitly directed by user or when mentioned in project AGENTS.md file'). | 3 / 3 |
Trigger Term Quality | Includes some relevant terms like 'plan', 'spec', 'implement', 'workflow', 'AGENTS.md', but these are somewhat technical. Missing natural variations users might say like 'planning', 'specification', 'TDD', 'test-driven'. | 2 / 3 |
Distinctiveness Conflict Risk | Very distinct niche with specific triggers: requires explicit user direction or AGENTS.md mention. The 'plan-spec-implement' workflow and '~/.dot-agent/' location create a clear, unique identity unlikely to conflict with other skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
72%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill demonstrates excellent organization and token efficiency, providing a clear overview of a complex multi-phase workflow with appropriate references to detailed documentation. However, it lacks concrete executable examples and explicit validation checkpoints between phases, which would strengthen actionability and workflow clarity for a process involving documentation and code changes.
Suggestions
Add a concrete example showing the exact commands or actions for at least one complete phase (e.g., Plan phase with actual file creation)
Include explicit validation checkpoints between phases, such as 'Verify plan file exists and contains required sections before proceeding to Spec'
Add an example of the research detection in action, showing input phrase and expected behavior
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient, using bullet points and minimal prose. It assumes Claude understands concepts like test-first development, CI verification, and documentation patterns without explanation. | 3 / 3 |
Actionability | Provides clear conceptual guidance and file path conventions, but lacks executable code examples or copy-paste ready commands. The workflow steps are described rather than demonstrated with concrete examples. | 2 / 3 |
Workflow Clarity | The three-phase workflow is clearly outlined with good structure, but lacks explicit validation checkpoints or feedback loops. No verification steps between phases or error recovery guidance is provided. | 2 / 3 |
Progressive Disclosure | Excellent structure with a concise overview and clear one-level-deep references to 7 detailed protocol files. Navigation is well-signaled with descriptive link text for each reference. | 3 / 3 |
Total | 10 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- 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.