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-constructed skill description that clearly communicates its purpose and provides explicit trigger conditions. The trigger terms are natural and varied, and the 'Use when' clause effectively guides skill selection. The main weakness is that the capability descriptions are slightly abstract—terms like 'applies prior patterns' could be more concrete about what that entails mechanically.
| 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, applies prior patterns') and when ('Use when starting a task, saying "what do I know about", "previous mistakes", "lessons learned", or "remind me about"') with explicit trigger guidance. | 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 terms with good coverage of variations. | 3 / 3 |
Distinctiveness Conflict Risk | This skill occupies a clear niche around retrieving and applying past learnings/corrections, which is distinct from general task execution or knowledge retrieval skills. The trigger terms are specific to self-reflection on past mistakes rather than general information lookup. | 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 provides a reasonable framework for replaying learnings with a useful output template and concrete grep examples. Its main weaknesses are vague middle steps (checking session history, ranking relevance) that lack executable specifics, and some unnecessary introductory text. The guardrails section adds good constraints but doesn't compensate for the workflow gaps.
Suggestions
Make step 3 ('check session history') concrete — specify where session history lives and provide an executable command or file path to search.
Define how relevance ranking works in step 4 — e.g., keyword match count, frequency of application, or recency — so Claude has a concrete algorithm to follow.
Remove the flavor text opening line ('Like muscle memory...') and tighten the trigger section to avoid duplicating the skill description.
| 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 without over-explaining concepts Claude already knows. | 2 / 3 |
Actionability | The grep commands in step 2 are concrete and executable, which is good. However, steps 3 ('check session history') and 4 ('surface top learnings ranked by relevance') are vague — there's no concrete mechanism for how to check session history or how to rank relevance. The output template is helpful but is an example format, not executable guidance. | 2 / 3 |
Workflow Clarity | The 5-step workflow is clearly sequenced and includes a fallback (step 5). However, there's no validation checkpoint — what if the grep results are stale or the files don't exist in the expected format? Steps 3-4 lack specificity on how to accomplish them, leaving gaps in the process. | 2 / 3 |
Progressive Disclosure | For a skill under 50 lines with a single-purpose task, the content is well-organized into clear sections (Trigger, Workflow, Output, Guardrails) with no need for external references. The structure is easy to scan and navigate. | 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
1de1554
- 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.