replay-learnings
Surface past learnings relevant to the current task before starting work. Searches correction history, recalls past mistakes, and applies prior patterns. Use when starting a task, saying "what do I know about", "previous mistakes", "lessons learned", or "remind me about".
82
73%
Does it follow best practices?
Impact
94%
1.54xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/replay-learnings/SKILL.mdQuality
Discovery
89%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-structured description that clearly communicates both what the skill does and when to use it, with natural trigger phrases. The main weakness is that the capability descriptions are somewhat abstract ('recalls past mistakes', 'applies prior patterns') rather than describing concrete mechanical actions. Overall it is a strong description that would enable effective skill selection.
Suggestions
Make the actions more concrete by specifying the mechanism, e.g., 'Queries a correction log file for past errors' or 'Searches stored feedback entries' instead of the more abstract 'recalls past mistakes'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (past learnings/corrections) and some actions ('searches correction history, recalls past mistakes, applies prior patterns'), but the actions are somewhat abstract rather than concrete operations like 'queries a database' or 'reads log files'. | 2 / 3 |
Completeness | Clearly answers both what ('Surface past learnings relevant to the current task... Searches correction history, recalls past mistakes, and applies prior patterns') and when ('Use when starting a task, saying "what do I know about", "previous mistakes", "lessons learned", or "remind me about"'). | 3 / 3 |
Trigger Term Quality | Includes natural phrases users would actually say: 'what do I know about', 'previous mistakes', 'lessons learned', 'remind me about', and 'starting a task'. These are realistic trigger phrases with good coverage. | 3 / 3 |
Distinctiveness Conflict Risk | This skill occupies a clear niche around recalling past learnings and correction history. The trigger terms are specific to retrospective knowledge retrieval and unlikely to conflict with other skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
57%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill has a solid structure with a clear output example and useful guardrails. Its main weakness is that several workflow steps (checking session history, ranking learnings) are described abstractly without concrete mechanisms, making them more aspirational than actionable. The grep examples are a good start but the skill needs more executable specificity for the non-trivial steps.
Suggestions
Provide concrete commands or methods for step 3 ('check session history') — e.g., how to find and parse session logs to compute correction rates.
Specify how to rank learnings by relevance in step 4 — e.g., keyword match count, frequency of application, or a simple scoring heuristic.
Remove the flavor text opening line ('Like muscle memory...') and the trigger section (which duplicates the skill description) to improve conciseness.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The opening line 'Like muscle memory for your coding sessions' is unnecessary flavor text, and the trigger section partially duplicates the description. However, the workflow and output sections are reasonably tight. Some tightening possible but not egregiously verbose. | 2 / 3 |
Actionability | The grep commands in step 2 are concrete and executable, which is good. However, steps 3-4 ('check session history', 'surface top learnings ranked by relevance') are vague — there's no concrete mechanism for how to check session history or rank learnings. The output example is illustrative but the skill doesn't explain how to generate the correction rate or ranking. | 2 / 3 |
Workflow Clarity | The 5-step workflow is clearly sequenced and the fallback in step 5 is a nice touch. However, steps 3 and 4 lack specificity — there's no concrete method for checking session history or ranking results. There are no validation checkpoints (e.g., what if grep returns too many results, or files don't exist beyond the 2>/dev/null). | 2 / 3 |
Progressive Disclosure | For a skill of this size and scope (under 50 lines, single-purpose), the content is well-organized into clear sections (Trigger, Workflow, Output, Guardrails) with no need for external references. The structure is clean and navigable. | 3 / 3 |
Total | 9 / 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
- rohitg00/pro-workflow
- Commit
9fc35f5
- 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.