reflect-session

Reflect on the current session, extract learnings, and consolidate them into Hindsight for future recall.

Quality

43%

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 ./devflow-plugin/skills/reflect-session/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.

A well-structured reflection skill with a clear multi-step workflow and good validation checkpoint (user approval before retention). Its main weaknesses are slight verbosity in the review prompts (things Claude would naturally consider) and the lack of a concrete example of how to invoke the Hindsight retain tool, which is the core action of the skill.

Suggestions

Add a concrete example of the Hindsight retain tool invocation (e.g., exact parameters, expected format) so the core action is fully executable rather than vaguely referenced.

Trim the sub-bullets under 'Review the session' — Claude naturally considers these questions; a single sentence like 'Review the conversation for notable outcomes, surprises, and corrections' would suffice.

Dimension	Reasoning	Score
Conciseness	Mostly efficient but includes some unnecessary elaboration. The sub-bullets under 'Review the session' are things Claude would naturally consider. The learning categories are useful but could be more compact. The template block is helpful but slightly verbose.	2 / 3
Actionability	Provides a clear process and output template, but the key action—using the Hindsight 'retain' tool—lacks concrete examples of how to call it (what parameters, what format). The guidance is structured but not fully executable since the tool invocation is vague.	2 / 3
Workflow Clarity	The 6-step workflow is clearly sequenced with a logical flow: review → extract → present → get approval → retain → confirm. It includes a human-in-the-loop validation checkpoint (step 4) before the destructive/persistent action (step 5), which is appropriate for this type of operation.	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, Important, template). No bundle files are needed and none are referenced, which is appropriate.	3 / 3
	Total	10 / 12 Passed

Description

17%

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 is too abstract and lacks explicit trigger guidance. While it references a specific system ('Hindsight') which helps with distinctiveness, the actions described are vague and the description provides no 'Use when...' clause to help Claude know when to select this skill. The trigger terms are not aligned with natural user language.

Suggestions

Add an explicit 'Use when...' clause, e.g., 'Use when the session is ending, when the user asks to save learnings, or when Claude should remember insights for future sessions.'

Include natural trigger terms users might say, such as 'remember this', 'save for later', 'session notes', 'what did we learn', 'end of session summary'.

Specify concrete actions more clearly, e.g., 'Summarizes key decisions, mistakes, and patterns from the current session and writes them to Hindsight memory files for future recall.'

Dimension	Reasoning	Score
Specificity	Names some actions ('reflect', 'extract learnings', 'consolidate into Hindsight') but these are somewhat abstract. 'Hindsight' appears to be a specific tool/system name which adds some concreteness, but the actual operations remain vague—what does 'extract learnings' or 'consolidate' mean in practice?	2 / 3
Completeness	The description addresses 'what' at a high level but completely lacks a 'when' clause or explicit trigger guidance. There is no 'Use when...' or equivalent, which per the rubric caps completeness at 2, and the 'what' is also weak enough to warrant a 1.	1 / 3
Trigger Term Quality	The description lacks natural keywords a user would say. Terms like 'reflect', 'learnings', 'consolidate', and 'Hindsight' are not phrases users would naturally use when requesting this functionality. Missing terms like 'save notes', 'remember this', 'session summary', 'what did we learn', etc.	1 / 3
Distinctiveness Conflict Risk	The mention of 'Hindsight' as a specific system/tool name provides some distinctiveness, and the concept of session reflection is somewhat niche. However, it could overlap with general note-taking, memory, or summarization skills due to the vague language.	2 / 3
	Total	6 / 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.