session-historian
Look up prior Claude Code sessions when context is lost or forgotten. Use when asked "what did we do before?", "what happened in the last session?", "I forgot what we were working on", "find what I told you about X", or any request to recall past conversation history, prior decisions, experiments, or outcomes. Searches raw JSONL transcripts from ~/.claude/projects/ via DuckDB index. Returns verbatim user messages and summarizes AI actions and sub-agent outcomes. Summaries cached at ~/.claude/kaizen/session-summaries/.
72
88%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Risky
Do not use without reviewing
Quality
Discovery
100%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 is an excellent skill description that clearly defines its purpose, provides rich natural-language trigger phrases, and specifies implementation details that make it highly distinctive. It covers both the 'what' and 'when' comprehensively, with concrete examples of user queries that would trigger this skill. The technical details (DuckDB, JSONL, specific file paths) add precision without sacrificing readability.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: looks up prior sessions, searches raw JSONL transcripts via DuckDB index, returns verbatim user messages, summarizes AI actions and sub-agent outcomes, caches summaries. Very concrete and detailed. | 3 / 3 |
Completeness | Clearly answers both 'what' (searches JSONL transcripts via DuckDB, returns verbatim messages, summarizes AI actions) and 'when' (explicit 'Use when...' clause with multiple natural trigger phrases and scenarios). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger phrases users would actually say: 'what did we do before?', 'what happened in the last session?', 'I forgot what we were working on', 'find what I told you about X', plus general terms like 'recall past conversation history', 'prior decisions', 'experiments', 'outcomes'. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche: specifically about recalling prior Claude Code sessions from JSONL transcripts in ~/.claude/projects/. The combination of session history lookup, DuckDB indexing, and specific file paths makes it very unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
77%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 skill with excellent actionability — every command is concrete and executable, the workflow is clearly sequenced, and the summary template provides a complete artifact specification. The main weakness is that the command reference section is quite extensive inline, making the overall document longer than ideal; this content would benefit from being split into a separate reference file. The fidelity rules are a strong addition that serve as implicit validation checkpoints.
Suggestions
Move the detailed Command Reference section (errors, tools, irritation, current-path with their arguments, output formats, and exit codes) into a separate COMMANDS.md file, keeping only a brief table or list of available commands in the main SKILL.md.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient and avoids explaining concepts Claude already knows, but the command reference section is quite lengthy with detailed descriptions of output formats, exit codes, and argument options that could be more tightly organized. The summary template is verbose but justified since it's a concrete artifact template. | 2 / 3 |
Actionability | Every command is fully executable with concrete bash examples, specific flags, and real argument patterns. The workflow steps are copy-paste ready, the summary template is a complete artifact, and the JSONL schema reference provides exact field names and structure. | 3 / 3 |
Workflow Clarity | The 'I forgot what happened' workflow is clearly sequenced with numbered steps progressing from quick lookup to detailed summary generation. The fidelity rules serve as validation checkpoints (read before summarizing, verbatim messages, preserve counts), and the index rebuild note addresses a common failure mode. | 3 / 3 |
Progressive Disclosure | The skill has good section structure (workflow, template, command reference, schema), but the command reference section is quite long and inline — commands like 'errors', 'tools', 'irritation', and 'current-path' with their detailed argument/output/exit-code documentation could be split into a separate REFERENCE.md. No bundle files were provided to offload this content to. | 2 / 3 |
Total | 10 / 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
- Jamie-BitFlight/claude_skills
- Commit
4e61312
- 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.