Retain a new learning, discovery, or hard-won insight into Hindsight so it's available in future sessions.
54
60%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/retain-learning/SKILL.mdQuality
Discovery
50%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
The description communicates the core purpose—saving insights to a system called Hindsight for cross-session persistence—but lacks explicit trigger guidance ('Use when...') and comprehensive natural trigger terms. It is moderately specific but would benefit from listing concrete actions and user-facing keywords to improve skill selection accuracy.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user wants to save, remember, or log a lesson learned, discovery, or insight for future reference.'
Include more natural trigger terms users might say, such as 'remember this', 'save this lesson', 'note for later', 'takeaway', or 'log insight'.
List additional concrete actions if applicable, such as categorizing insights, tagging learnings, or updating existing entries in Hindsight.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names a domain (retaining learnings/insights) and a specific action (retain into Hindsight), but it doesn't list multiple concrete actions or detail what kinds of operations are supported beyond 'retain.' | 2 / 3 |
Completeness | The 'what' is reasonably clear (retain a learning/insight into Hindsight for future sessions), but there is no explicit 'Use when...' clause or equivalent trigger guidance telling Claude when to select this skill. | 2 / 3 |
Trigger Term Quality | Includes some relevant terms like 'learning', 'discovery', 'insight', and the product name 'Hindsight', but misses common natural variations users might say such as 'remember this', 'save for later', 'note', 'lesson learned', 'takeaway', or 'future reference.' | 2 / 3 |
Distinctiveness Conflict Risk | The mention of 'Hindsight' as a specific system provides some distinctiveness, but terms like 'learning', 'discovery', and 'insight' are broad enough to potentially overlap with note-taking, journaling, or knowledge management skills. | 2 / 3 |
Total | 8 / 12 Passed |
Implementation
70%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 for retaining learnings into Hindsight with a clear workflow and a good concrete example. Its main weakness is the lack of specificity around the actual tool invocation—showing the exact tool call format/parameters would make it fully actionable. The content could also be slightly more concise by trimming category descriptions.
Suggestions
Show the exact tool call syntax for the Hindsight `retain` tool in step 4 (e.g., the function name, parameter names, and expected payload structure) so Claude can execute it without guessing.
Consider condensing the category list into a compact table or single-line definitions to save tokens while preserving clarity.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is mostly efficient but includes some unnecessary elaboration. The category descriptions and field explanations are slightly verbose—Claude could infer much of this from a more compact specification. However, it's not egregiously padded. | 2 / 3 |
Actionability | The steps are clear and the example is concrete and helpful, but the actual tool invocation (step 4) is vague—it says 'using the Hindsight retain tool' without showing the exact tool call syntax, parameters, or payload format. This leaves a gap in executability. | 2 / 3 |
Workflow Clarity | The 5-step workflow is clearly sequenced and logical, covering parsing, classification, structuring, storing, and confirming. For this type of non-destructive, single-action skill, the workflow is unambiguous and complete, including a confirmation step. | 3 / 3 |
Progressive Disclosure | For a simple, self-contained skill under 50 lines with no need for external references, the content is well-organized with clear sections (Steps, Example) and doesn't need further splitting. The structure is appropriate for the complexity. | 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.
b0b1bb6
Table of Contents
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.