compact

Compact current session memory into structured text for session recovery. Supports custom descriptions and tagging.

Quality

30%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Risky

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./.codex/skills/memory-compact/SKILL.md

Quality

Content

27%

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 thorough and well-structured template for session memory compaction, with a clear output format and MCP integration. However, it is severely over-engineered for its purpose—much of the content is pseudocode that Claude cannot directly execute, duplicated explanations (field definitions restating what the template already shows), and verbose sections that could be dramatically condensed or split into reference files. The core value (structured output format + MCP save command) is buried under excessive scaffolding.

Suggestions

Reduce content by 60-70%: Remove the field definitions table (duplicates the template), collapse the JavaScript pseudocode into the output template with brief inline comments, and trim the 'Core Philosophy' section to a single line.

Split reference material into bundle files: Move plan detection priorities, path resolution rules, and reference file categories into separate .md files, keeping SKILL.md as a concise overview with the output template and MCP command.

Add error handling/validation: Include what to do if MCP import fails, how to verify the memory was saved correctly, and a feedback loop for incomplete session analysis.

Replace pseudocode with actionable instructions: Instead of JavaScript functions like `extractTodosFromConversation()`, provide direct instructions like 'Scan conversation for TodoWrite tool calls and preserve all todo items with their status markers.'

Dimension	Reasoning	Score
Conciseness	Extremely verbose at ~300+ lines. The field definitions table duplicates information already shown in the structured output format. The JavaScript code examples for session analysis, plan detection, and text generation are largely pseudocode that Claude could infer from the output format alone. The 'Core Philosophy' section, path resolution rules, and reference file categories table add bulk without proportional value.	1 / 3
Actionability	Provides a concrete output format template and MCP tool calls, which is good. However, much of the JavaScript is pseudocode (extractTodosFromConversation(), inferPlanFromDiscussion() are undefined helper functions), and the plan detection code references MCP tools with specific operations that may or may not exist. The structured output format itself is actionable and copy-paste ready.	2 / 3
Workflow Clarity	The 4-step execution flow (Analyze → Generate → Import → Report) is clearly sequenced. However, there are no validation checkpoints or error handling—what happens if the MCP import fails? What if session analysis is incomplete? The quality checklist exists but is presented as a pre-generation check rather than integrated validation steps with feedback loops.	2 / 3
Progressive Disclosure	Monolithic wall of text with no bundle files to reference. The field definitions table, plan detection priority code, path resolution rules, and reference file categories could all be in separate reference files. Everything is inlined into a single massive document with no external references or layered structure.	1 / 3
	Total	6 / 12 Passed

Description

32%

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 conveys the core purpose of compacting session memory but lacks explicit trigger guidance ('Use when...'), which is a significant gap for skill selection. The trigger terms are somewhat relevant but miss common user phrasings. Adding explicit usage triggers and more natural keywords would substantially improve discoverability.

Suggestions

Add an explicit 'Use when...' clause, e.g., 'Use when the user asks to save session state, compress context, checkpoint the conversation, or prepare for session handoff.'

Include more natural trigger terms users might say, such as 'save context', 'compress memory', 'checkpoint', 'persist conversation', or 'context window management'.

Expand the concrete actions listed—e.g., 'Summarizes conversation history into structured notes, preserves key decisions and context, supports custom descriptions and tags for retrieval.'

Dimension	Reasoning	Score
Specificity	Names the domain (session memory) and some actions (compact, session recovery, custom descriptions, tagging), but doesn't list multiple concrete actions in detail—e.g., what 'compact' means specifically or what structured text looks like.	2 / 3
Completeness	Describes what the skill does (compact session memory) but has no explicit 'Use when...' clause or equivalent trigger guidance, which per the rubric caps completeness at 2, and the 'when' is entirely missing, warranting a 1.	1 / 3
Trigger Term Quality	Includes some relevant terms like 'session memory', 'session recovery', and 'tagging', but misses natural user phrases like 'save context', 'remember conversation', 'checkpoint', 'persist memory', or 'compress context'.	2 / 3
Distinctiveness Conflict Risk	The concept of 'session memory compaction' is fairly niche, but terms like 'memory' and 'tagging' could overlap with note-taking or knowledge management skills. More specific triggers would reduce conflict risk.	2 / 3
	Total	7 / 12 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	10 / 11 Passed

Repository: catlog22/Claude-Code-Workflow
Commit: 07491b0

Reviewed: 20 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.