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 ./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.
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' entail beyond read/update?), and the trigger terms are internal/technical rather than matching natural user language. The description is functional but could benefit from more concrete action verbs and user-facing terminology.
Suggestions
Replace vague 'maintain' with more concrete actions like 'create, read, update, and persist .agent state files' to improve specificity.
Add natural trigger terms users might say, such as 'session state', 'agent memory', 'persist context', or 'track progress' to improve discoverability.
| 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 more like categories than concrete operations. 'Maintain' and 'read/update' are somewhat generic verbs. | 2 / 3 |
Completeness | Clearly answers both what ('Maintain .agent state files' with read/update of constitution/memory/focus/issues/baseline) and when ('at session start, after meaningful steps, and before concluding'). The when clause is explicit with specific timing triggers. | 3 / 3 |
Trigger Term Quality | Includes some relevant terms like '.agent state files', 'constitution', 'memory', 'focus', 'issues', 'baseline', but these are fairly technical/internal terms. Missing natural user-facing trigger terms—users are unlikely to say 'maintain .agent state files' directly. | 2 / 3 |
Distinctiveness Conflict Risk | The '.agent state files' concept with specific sub-components (constitution/memory/focus/issues/baseline) creates a very distinct niche. Unlikely to conflict with other skills due to the highly specific domain. | 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 is a well-structured operational skill with clear workflows and good progressive disclosure. Its main weaknesses are moderate verbosity from presenting both file-based and CLI approaches side by side, and a lack of concrete inline examples showing what actual state file content looks like. The dependency validation workflow and ordered reading sequence are strong points.
Suggestions
Add a brief inline example of what a focus.md update looks like (actual content, not just field names) to improve actionability.
Remove or significantly condense the git status section — Claude knows these commands — and consider merging the file-based and CLI tables into a single table with two columns to reduce redundancy.
| 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 dependency validation steps are clear but the issue format template is referenced rather than shown inline, and there's no example of what a focus.md update actually looks like. | 2 / 3 |
Workflow Clarity | The session start workflow is clearly sequenced with numbered steps, the required reads are explicitly ordered with context optimization guidance, and the dependency validation includes a clear feedback loop (check → block if unmet → only proceed when satisfied). The 'When to Use' section provides clear trigger points. | 3 / 3 |
Progressive Disclosure | Content is well-structured with clear sections, the reading order uses context optimization (read index first, then only relevant priority files), and templates are appropriately referenced as external files rather than inlined. References are one level deep and clearly signaled. | 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
- Commit
632759f
- 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.