reflect-session

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

Quality

51%

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

Discovery

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 for when Claude should select this skill. While it hints at a specific workflow (session reflection → Hindsight system), the language is vague and doesn't include natural user-facing keywords. The absence of a 'Use when...' clause is a significant gap for skill selection among many candidates.

Suggestions

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

Include natural trigger terms users would actually say, such as 'save what we learned', 'remember this for next time', 'session notes', 'capture insights'.

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

Dimension	Reasoning	Score
Specificity	Names some actions ('reflect on session', 'extract learnings', 'consolidate into Hindsight') but these are somewhat abstract. 'Learnings' and 'reflect' are vague—it doesn't specify what kinds of learnings or what consolidation entails concretely.	2 / 3
Completeness	The description addresses 'what' at a high level (reflect, extract, consolidate) but completely lacks a 'when' clause. There is no 'Use when...' or equivalent trigger guidance, which per the rubric should cap completeness at 2, and since the 'what' is also vague, this scores a 1.	1 / 3
Trigger Term Quality	The terms 'reflect', 'learnings', 'Hindsight', and 'future recall' are not natural keywords a user would say. A user might say 'save what we learned', 'remember this', or 'take notes' but none of those terms appear. 'Hindsight' appears to be a product-specific term that wouldn't be naturally used.	1 / 3
Distinctiveness Conflict Risk	The mention of 'Hindsight' as a specific system and 'session' reflection gives it some distinctiveness, but 'extract learnings' and 'consolidate' could overlap with note-taking, journaling, or memory skills. Without clearer boundaries, moderate conflict risk remains.	2 / 3
	Total	6 / 12 Passed

Implementation

85%

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 reflection skill with clear, sequential steps and a concrete output template. The workflow includes an appropriate user-approval checkpoint before committing learnings. Minor verbosity in the enumeration of review questions and learning categories slightly reduces token efficiency, but overall the skill is actionable and well-organized.

Dimension	Reasoning	Score
Conciseness	Mostly efficient but includes some unnecessary elaboration. The sub-bullets under 'Review the session' and the classification list in step 2 are somewhat verbose for Claude, who could infer these categories. However, the content isn't egregiously padded.	2 / 3
Actionability	Provides a concrete, step-by-step workflow with a specific output template, clear classification categories, and explicit instructions for user interaction (ask, confirm, retain). The reference to the Hindsight `retain` tool and the exact output format make this copy-paste actionable.	3 / 3
Workflow Clarity	The six steps are clearly sequenced with a logical flow: review → extract → present → get approval → retain → confirm. The user approval checkpoint (step 4) before committing to retention (step 5) serves as a validation gate, and the 'Important' section provides guardrails against over-retention.	3 / 3
Progressive Disclosure	For a simple, self-contained skill with no need for external references, the content is well-organized with clear sections (Steps, Important) and appropriate use of the output template inline. No bundle files are needed and none are referenced, which is appropriate.	3 / 3
	Total	11 / 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: b0b1bb6

Reviewed: 7 days 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.