context-log
Maintaining .opencode/context-log.md for session continuity
71
55%
Does it follow best practices?
Impact
100%
1.78xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./dot_config/opencode/skill/context-log/SKILL.mdQuality
Discovery
22%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 is too terse and lacks both concrete actions and explicit trigger guidance. While it references a specific file path which aids distinctiveness, it fails to explain what maintaining the log entails or when Claude should select this skill. It reads more like a task label than a functional skill description.
Suggestions
Add specific concrete actions such as 'Creates, updates, and reads .opencode/context-log.md to track decisions, progress, and open tasks across sessions'.
Add an explicit 'Use when...' clause with natural trigger terms like 'Use when starting or resuming a coding session, saving progress, logging decisions, or when the user mentions session notes or context log'.
Include natural user-facing keywords such as 'resume session', 'save progress', 'session history', 'pick up where I left off' to improve trigger term coverage.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names a specific file (.opencode/context-log.md) and mentions 'session continuity' but does not describe any concrete actions like creating, updating, reading, or formatting the log. It's more of a vague purpose statement than a list of capabilities. | 1 / 3 |
Completeness | The description weakly addresses 'what' (maintaining a context log) but has no explicit 'when' clause or trigger guidance. Per the rubric, a missing 'Use when...' clause caps completeness at 2, and the 'what' is also vague, so this scores a 1. | 1 / 3 |
Trigger Term Quality | Includes some relevant terms like 'context-log.md', 'session continuity', and '.opencode' that could match specific queries, but misses natural user phrases like 'save progress', 'resume session', 'pick up where I left off', or 'session notes'. | 2 / 3 |
Distinctiveness Conflict Risk | The specific file path '.opencode/context-log.md' provides some distinctiveness, but 'session continuity' is broad enough to potentially overlap with other session management or logging skills. | 2 / 3 |
Total | 6 / 12 Passed |
Implementation
87%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-crafted, concise skill that provides clear, actionable templates for maintaining a context log. Its strengths are token efficiency and concrete examples. The only notable gap is the lack of any validation step (e.g., confirming the file exists or was updated correctly after a checkpoint append), which slightly weakens workflow clarity.
Suggestions
Add a brief validation note after checkpoint appending, e.g., 'After appending, confirm the checkpoint renders correctly in the markdown and the commit SHA matches the latest commit.'
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every section is lean and purposeful. No unnecessary explanations of what a context log is conceptually—it jumps straight to purpose, location, triggers, and templates. The table format for 'When to Update' is efficient. | 3 / 3 |
Actionability | Provides concrete, copy-paste-ready templates for both initial creation and checkpoints, with a realistic example. The compaction instruction is specific and actionable ('Don't re-summarize. Just say:...'). | 3 / 3 |
Workflow Clarity | The 'When to Update' table provides a clear sequence of events, but there's no validation or verification step—e.g., checking that the log file is well-formed, that commit SHAs match, or that the file was actually created. For a file-creation/maintenance workflow, a brief check step would strengthen it. | 2 / 3 |
Progressive Disclosure | This is a simple, single-purpose skill under 50 lines. Content is well-organized into logical sections (purpose, location, triggers, templates, example, edge case) with clear headers and no unnecessary nesting or external references needed. | 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
- athal7/dotfiles
- Commit
4ed3a13
- 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.