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.
83
78%
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/psi/SKILL.mdQuality
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 strong skill description that clearly defines a specific workflow with concrete actions and explicit activation conditions. The description excels at completeness and distinctiveness by specifying exact trigger conditions and unique workflow characteristics. The main weakness is trigger term quality, which uses somewhat technical terminology that users might not naturally say.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Generates ephemeral plans', 'applies specs to project docs', 'implements test-first'. Also specifies the workflow structure and file location (~/.dot-agent/). | 3 / 3 |
Completeness | Clearly answers both what ('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') with explicit trigger conditions. | 3 / 3 |
Trigger Term Quality | Includes some relevant terms like 'plan', 'spec', 'implement', 'workflow', 'structured development', and 'test-first', but these are somewhat technical. Missing common user variations like 'planning', 'specification', 'TDD', or 'design document'. | 2 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with specific workflow name 'Plan-spec-implement', unique file path reference (~/.dot-agent/), and explicit activation conditions (user direction or AGENTS.md mention). 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 strong organization and token efficiency with a clear overview structure and appropriate delegation to reference files. However, it lacks concrete executable examples and explicit validation checkpoints that would make the workflow more actionable. The content describes the workflow conceptually but would benefit from specific commands or code snippets showing how to execute each phase.
Suggestions
Add concrete examples of plan/spec file content or commands to execute each phase (e.g., show a sample plan.md structure or the exact steps to generate one)
Include explicit validation checkpoints in the workflow, such as 'Verify plan completeness by checking X criteria before proceeding to Spec phase'
Add a minimal executable example showing the complete workflow for a simple change, demonstrating the Plan → Spec → Implement cycle
| 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 phases describe what to do conceptually but not how to execute specific steps. | 2 / 3 |
Workflow Clarity | The three-phase workflow is clearly sequenced with Plan → Spec → Implement, but validation checkpoints are implicit rather than explicit. Missing concrete verification steps like 'run X command to validate' or feedback loops for error recovery. | 2 / 3 |
Progressive Disclosure | Excellent structure with a concise overview and well-signaled one-level-deep references to detailed protocols. The References section clearly points to specific files for each aspect of the workflow. | 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.
- Repository
- siviter-xyz/dot-agent
- Commit
3376255
- 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.