opencontext
Persistent memory and context management for AI agents using OpenContext. Keep context across sessions/repos/dates, store conclusions, and provide document search workflows.
72
58%
Does it follow best practices?
Impact
96%
2.13xAverage score across 3 eval scenarios
Risky
Do not use without reviewing
Optimize this skill with Tessl
npx tessl skill review --optimize ./.agent-skills/opencontext/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 identifies the core domain (persistent memory via OpenContext) and lists some capabilities, but suffers from missing explicit trigger guidance and relies too heavily on the product name rather than natural user language. The lack of a 'Use when...' clause significantly weakens its utility for skill selection among many options.
Suggestions
Add a 'Use when...' clause with explicit triggers like 'Use when the user wants to remember information across sessions, recall previous conclusions, or search stored documents'
Include natural trigger terms users would say: 'remember this', 'recall', 'what did we discuss', 'save for later', 'persistent notes'
Make actions more concrete: instead of 'provide document search workflows', specify 'search and retrieve previously stored documents and notes'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (memory/context management) and some actions ('store conclusions', 'document search workflows'), but lacks comprehensive concrete actions. 'Keep context' and 'provide document search workflows' are somewhat vague. | 2 / 3 |
Completeness | Describes what it does but completely lacks a 'Use when...' clause or any explicit trigger guidance. Per rubric guidelines, missing explicit trigger guidance caps completeness at 2, and this has no trigger guidance at all. | 1 / 3 |
Trigger Term Quality | Includes some relevant terms ('memory', 'context', 'sessions', 'repos', 'document search') but relies heavily on the product name 'OpenContext' which users may not naturally say. Missing common variations like 'remember', 'recall', 'persist', 'save state'. | 2 / 3 |
Distinctiveness Conflict Risk | The OpenContext product name provides some distinctiveness, but 'memory', 'context management', and 'document search' are generic terms that could overlap with other memory or search skills. | 2 / 3 |
Total | 7 / 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 skill with strong actionability and clear workflows. The content provides executable commands and practical examples throughout. Minor verbosity in the introductory sections and some marketing-style language slightly reduce token efficiency, but overall the skill effectively teaches OpenContext usage.
Suggestions
Remove or condense the 'Problem/Solution' section - Claude understands context loss without explanation; jump directly to the solution commands
Remove the marketing tagline ('Give your AI assistant persistent memory. Stop repeating explanations, and build smarter.') as it adds no actionable value
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient but includes some unnecessary explanatory content (e.g., 'Problem/Solution' section explaining context loss, marketing-style tagline). Some tables and sections could be tightened, though most content is actionable. | 2 / 3 |
Actionability | Provides fully executable CLI commands, clear command tables, and copy-paste ready examples throughout. Commands like 'oc init', 'oc folder create', and 'oc search' are concrete and immediately usable. | 3 / 3 |
Workflow Clarity | Clear multi-step workflows with explicit sequencing (Before/During/After work pattern, numbered orchestration steps). The daily workflow section provides unambiguous checkpoints and the multi-agent integration shows clear handoff patterns. | 3 / 3 |
Progressive Disclosure | Well-structured with clear sections progressing from core concepts to advanced features. Quick Reference at the end provides summary, and external references are one-level deep with clear signaling to documentation and downloads. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
100%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
- supercent-io/skills-template
- Commit
c033769
- 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.