replay-learnings
Surface past learnings relevant to the current task before starting work. Searches correction history and patterns. Use when starting a task or saying "what do I know about".
Install with Tessl CLI
npx tessl i github:rohitg00/pro-workflow --skill replay-learnings85
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
75%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 functional with good completeness and distinctiveness, clearly stating both purpose and trigger conditions. However, it could benefit from more specific concrete actions and broader trigger term coverage to help users discover it through natural language variations.
Suggestions
Add more natural trigger terms users might say, such as 'previous mistakes', 'lessons learned', 'remember when I', or 'past corrections'
Expand the specific actions beyond 'Surface' and 'Searches' to include what happens with the learnings (e.g., 'applies corrections', 'avoids repeated mistakes', 'recalls preferences')
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (past learnings, correction history) and some actions ('Surface', 'Searches'), but lacks comprehensive concrete actions. Could specify what it does with the learnings once found. | 2 / 3 |
Completeness | Clearly answers both what ('Surface past learnings relevant to the current task', 'Searches correction history and patterns') and when ('Use when starting a task or saying "what do I know about"') with explicit triggers. | 3 / 3 |
Trigger Term Quality | Includes some natural terms like 'what do I know about' and 'starting a task', but missing common variations users might say like 'previous mistakes', 'lessons learned', 'remember when', or 'past errors'. | 2 / 3 |
Distinctiveness Conflict Risk | Has a clear niche focused on correction history and past learnings with distinct triggers. Unlikely to conflict with other skills due to the specific focus on self-reflection and learning patterns. | 3 / 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 skill with excellent output examples and clear workflow sequencing. The main weakness is the abstract nature of the workflow steps—they describe what to do but not how to actually search learnings or extract keywords. The concrete output format partially compensates by showing exactly what the result should look like.
Suggestions
Add concrete examples of how to search learnings/memory (e.g., file paths, grep patterns, or tool commands to use)
Show an example of keyword extraction from a sample task description to make step 1 actionable
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is lean and efficient. No unnecessary explanations of concepts Claude knows. Every section serves a purpose with minimal padding. | 3 / 3 |
Actionability | The workflow provides clear steps but lacks executable code. The output example is excellent and concrete, but the workflow steps (extract keywords, search learnings) are described abstractly without showing how to actually perform these operations. | 2 / 3 |
Workflow Clarity | Clear 5-step sequence with logical flow. Includes a fallback path (suggest scout agent if no learnings). The guardrails section adds validation guidance for ranking and handling edge cases. | 3 / 3 |
Progressive Disclosure | For a skill under 50 lines with no need for external references, this is well-organized with clear sections (Trigger, Workflow, Output, Guardrails). Content is appropriately scoped for a single file. | 3 / 3 |
Total | 11 / 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.