retain-learning

Retain a new learning, discovery, or hard-won insight into Hindsight so it's available in future sessions.

Quality

60%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/retain-learning/SKILL.md

Quality

Content

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 with clear workflow steps and a helpful concrete example. Its main weakness is the lack of specific tool invocation syntax for the Hindsight `retain` tool—without knowing the exact call format, Claude may not execute the storage step correctly. The content is reasonably concise but could trim some filler phrasing.

Suggestions

Add the exact tool invocation syntax or function call format for the Hindsight `retain` tool (e.g., show the actual tool_use block or API call with the structured payload).

Trim filler phrases like 'You need to retain a new learning into long-term memory via Hindsight' and 'from the arguments below' to improve conciseness.

Dimension	Reasoning	Score
Conciseness	The content is mostly efficient but includes some unnecessary elaboration. The category descriptions and structured fields are useful, but phrases like 'from the arguments below' and the general framing could be tighter. The example is helpful but slightly verbose in its explanation.	2 / 3
Actionability	The skill provides a clear structured process and a concrete example, but lacks executable code or specific tool invocation syntax. The instruction to 'use the Hindsight retain tool' is vague—no actual API call, function signature, or tool-use format is shown, leaving Claude to guess the exact invocation.	2 / 3
Workflow Clarity	The five steps are clearly sequenced and logically ordered: parse → classify → structure → store → confirm. For a non-destructive, single-action skill like memory retention, this level of workflow clarity is sufficient. The confirmation step serves as a lightweight validation checkpoint.	3 / 3
Progressive Disclosure	For a simple, single-purpose skill under 50 lines with no need for external references, the content is well-organized with clear sections (Steps, Example) and doesn't require splitting into multiple files. The structure is clean and easy to navigate.	3 / 3
	Total	10 / 12 Passed

Description

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 learnings to a system called Hindsight for cross-session persistence—but lacks explicit trigger guidance ('Use when...') and misses common natural language variations users might employ. It is moderately specific but would benefit from concrete examples of when to activate and more natural trigger terms.

Suggestions

Add an explicit 'Use when...' clause, e.g., 'Use when the user says to remember something, save a lesson learned, or store an insight for future reference.'

Include more natural trigger terms users would say, such as 'remember this', 'save for later', 'note this', 'lesson learned', 'TIL', or 'don't forget'.

List more specific concrete actions beyond just 'retain', such as 'categorize insights, tag learnings by topic, and surface them in relevant future conversations'.

Dimension	Reasoning	Score
Specificity	The description names the domain (retaining learnings/insights) and a specific action (retain into Hindsight), but doesn't list multiple concrete actions or detail what kinds of learnings or how they're stored/retrieved.	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, which caps this at 2 per the rubric guidelines.	2 / 3
Trigger Term Quality	Includes some relevant terms like 'learning', 'discovery', 'insight', and the product name 'Hindsight', but misses common natural phrases users might say like 'remember this', 'save this for later', 'note for next time', 'TIL', or 'lesson learned'.	2 / 3
Distinctiveness Conflict Risk	The mention of 'Hindsight' as a specific system provides some distinctiveness, but 'learning', 'discovery', and 'insight' are broad terms that could overlap with note-taking, journaling, or general memory/knowledge management skills.	2 / 3
	Total	8 / 12 Passed

Validation

100%

Warnings & errors only

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: AndreJorgeLopes/devflow
Commit: 8d872bf

Reviewed: 1 day ago

Table of Contents

Discovery Implementation Validation

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.