agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
83
Quality
80%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/core/agent-ops-state/SKILL.mdQuality
Discovery
75%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This description effectively communicates when to use the skill with clear temporal triggers and identifies a distinct domain (.agent state files). However, the capability description uses compressed slash-separated terms rather than clear action verbs, and the trigger terms are technical rather than user-facing language.
Suggestions
Expand the action descriptions to use clear verbs (e.g., 'Reads and updates agent state files including constitution, memory, focus, issues, and baseline files')
Add user-facing trigger terms that users might naturally say, such as 'agent memory', 'session persistence', 'save state', or 'remember context'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (.agent state files) and mentions actions (read/update constitution/memory/focus/issues/baseline), but the actions are listed as slash-separated terms rather than clearly described concrete operations. | 2 / 3 |
Completeness | Clearly answers both what (maintain .agent state files, read/update constitution/memory/focus/issues/baseline) and when (at session start, after meaningful steps, before concluding) with explicit temporal triggers. | 3 / 3 |
Trigger Term Quality | Includes some relevant terms like 'session start', '.agent state files', and specific file types (constitution/memory/focus/issues/baseline), but these are technical terms that users may not naturally say. Missing common variations like 'agent memory', 'session state', or 'persist context'. | 2 / 3 |
Distinctiveness Conflict Risk | Very specific niche targeting .agent state files with distinct file types (constitution/memory/focus/issues/baseline). Unlikely to conflict with other skills due to the unique domain and specific file references. | 3 / 3 |
Total | 10 / 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 workflow clarity. The dependency validation process and session start sequence are particularly well-defined with explicit checkpoints. Minor inefficiency from presenting both file-based and CLI approaches, though the CLI section is appropriately marked as optional.
Suggestions
Consider condensing the CLI section since it's optional and duplicates the file-based approach - a brief note that 'aoc CLI provides shortcuts for these operations when available' would suffice
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Content is reasonably efficient but includes some redundancy (CLI section duplicates file-based operations, git commands are basic knowledge). The tables are well-structured but the dual approach adds bulk. | 2 / 3 |
Actionability | Provides concrete file paths, specific operations, executable git commands, and clear templates. The issue management operations are specific and copy-paste ready with exact field names and file locations. | 3 / 3 |
Workflow Clarity | Clear sequenced workflows for session start, required reads (numbered order), and dependency validation (5-step process with explicit blocking behavior). Includes validation checkpoints before proceeding. | 3 / 3 |
Progressive Disclosure | Well-organized with clear sections, appropriate use of tables for quick reference, and proper delegation to templates and other skills (agent-ops-git). References are one level deep and clearly signaled. | 3 / 3 |
Total | 11 / 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
- majiayu000/claude-skill-registry
- Commit
6213d1a
- 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.