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.
77
72%
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 ./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.
The description effectively communicates when to use the skill with clear temporal triggers and identifies a distinct niche around .agent state file management. However, the specific capabilities could be more concrete (what does 'maintain' actually involve beyond read/update?), and the trigger terms are quite technical, which may not match natural user language patterns.
Suggestions
Expand the concrete actions beyond 'read/update' — specify what maintaining state files actually produces or changes (e.g., 'Creates, reads, and updates .agent state files tracking session constitution, memory, focus areas, open issues, and baseline configurations').
Add more natural trigger terms that a user might say, such as 'save progress', 'session state', 'track context', or 'persist memory between sessions'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (.agent state files) and lists some actions (read/update constitution/memory/focus/issues/baseline), but the actions are somewhat abstract — 'maintain' and 'read/update' are generic verbs, and the listed items (constitution/memory/focus/issues/baseline) are domain-specific concepts without clear explanation of what they entail. | 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, and before concluding). The 'Use at...' clause provides explicit temporal triggers. | 3 / 3 |
Trigger Term Quality | Includes some relevant terms like '.agent state files', 'session start', 'constitution', 'memory', 'focus', 'issues', 'baseline', but these are fairly technical/internal terms. A user is unlikely to naturally say 'maintain .agent state files' — they might say 'save progress', 'update session state', or 'remember context', which are missing. | 2 / 3 |
Distinctiveness Conflict Risk | The '.agent state files' concept is quite specific and niche, with distinct triggers around session lifecycle management. This is unlikely to conflict with other skills since it targets a very particular internal state management pattern. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
70%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 solid operational framework for managing .agent state files with clear workflows and good progressive disclosure. Its main weaknesses are moderate verbosity from dual file-based/CLI presentation and insufficient concrete examples of actual file content (e.g., what a focus.md entry looks like). The workflow clarity is strong with explicit ordering, dependency validation, and clear trigger points.
Suggestions
Add a concrete example of a completed focus.md update showing actual content rather than just describing required fields
Consider consolidating the file-based and CLI tables into a single table with both approaches as columns to reduce redundancy
Remove the git status section — these are basic commands Claude already knows and they consume tokens without adding skill-specific value
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient but includes some redundancy — the file-based operations table and CLI operations table overlap conceptually, and the git status section provides basic commands Claude already knows. The dual presentation (file-based + CLI) adds bulk. | 2 / 3 |
Actionability | Provides concrete file paths, field names, and CLI commands, but lacks executable examples of actual file content or edits. The 'Required Updates' section describes what focus.md must contain but doesn't show a concrete example. Templates are referenced but not shown inline. | 2 / 3 |
Workflow Clarity | Clear sequencing for session start (check staleness → read state → validate dependencies), explicit ordered reads, and a well-defined dependency validation workflow with a feedback loop (check → block if unmet → only proceed when satisfied). The 'When to Use' section provides clear trigger points. | 3 / 3 |
Progressive Disclosure | Well-structured with clear sections, a logical flow from defaults to CLI integration, and appropriate references to templates and the agent-ops-git skill for stale detection. Content is organized for quick scanning with tables and numbered lists, and detailed templates are linked rather than inlined. | 3 / 3 |
Total | 10 / 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-data
- Commit
6770aaa
- 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.