compact
Compact current session memory into structured text for session recovery. Supports custom descriptions and tagging.
48
36%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Risky
Do not use without reviewing
Optimize this skill with Tessl
npx tessl skill review --optimize ./.codex/skills/memory-compact/SKILL.mdQuality
Discovery
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—compacting session memory for recovery—but lacks explicit trigger guidance ('Use when...') and natural user-facing keywords. It is moderately specific but would benefit from concrete action listing and clear invocation cues to help Claude reliably select it from a large skill set.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks to save, compress, or checkpoint the current conversation context for later recovery.'
Include natural trigger terms users might say, such as 'save context', 'compress memory', 'checkpoint session', 'persist conversation state'.
List more concrete actions, e.g., 'Summarizes conversation history into structured notes, tags key topics, and outputs a recovery-ready text block.'
| 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, placing it at 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 the description could overlap with general memory management or note-taking skills. More specific triggers would reduce conflict risk. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
39%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill has a well-structured workflow with clear sequencing and validation, but is severely over-engineered for what is essentially 'extract session state into a template and save via MCP tool.' The extensive pseudocode, duplicate explanations (template + field definitions table + code generation), and inlined reference material make this far too verbose. Claude doesn't need 300+ lines to understand how to fill in a structured template.
Suggestions
Reduce to ~80 lines: keep the output template, the MCP save command, the quality checklist, and the plan detection priority order. Remove the field definitions table (duplicates the template), the JavaScript pseudocode for text generation (Claude can fill a template), and the path resolution section (Claude knows how paths work).
Split reference material into separate files: move the field definitions table, path resolution rules, and plan detection priority logic into a REFERENCE.md, keeping SKILL.md as a concise overview with the template and execution steps.
Replace illustrative pseudocode with a single concrete example: show one complete filled-in memory compact output rather than abstract JavaScript generation code with undefined helper functions.
Remove the 'Core Philosophy' section and Notes section — these explain concepts Claude can infer from the template structure itself.
| 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 illustrative pseudocode that Claude doesn't need spelled out in such detail. The 'Core Philosophy' bullets, extensive path resolution rules, and reference file categories table add significant bloat. Much of this could be condensed to the output template + a few key rules. | 1 / 3 |
Actionability | The structured output format is concrete and copy-paste ready, and the MCP tool call is specific. However, the JavaScript code throughout is pseudocode/illustrative rather than executable (e.g., `extractTodosFromConversation()`, `inferPlanFromDiscussion()` are undefined functions). The plan detection section describes what to do conceptually but relies on placeholder functions. | 2 / 3 |
Workflow Clarity | The 4-step execution flow (Analyze → Generate → Import → Report) is clearly sequenced with explicit outputs at each stage. The quality checklist provides validation before saving, and the priority-ordered plan detection gives clear decision logic. The confirmation display format ensures the user gets the recovery ID. | 3 / 3 |
Progressive Disclosure | This is a monolithic wall of text with no references to external files despite being complex enough to warrant splitting. The field definitions table, path resolution rules, plan detection logic, and reference file categories could all be separate reference documents. No bundle files are provided, and no external references are made, resulting in everything being inlined in one massive document. | 1 / 3 |
Total | 7 / 12 Passed |
Validation
90%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
227244f
- Reviewed
Table of Contents
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.