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/.
90
88%
Does it follow best practices?
Impact
Pending
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 follows the recommended pattern with an explicit 'Use when...' clause containing multiple realistic user queries, and the technical details (DuckDB, JSONL, specific file paths) help disambiguate it from other skills.
| 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 specific tooling (DuckDB index), file paths, and focus on session history make 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 executable and the workflow is clearly sequenced. The main weakness is that the document is quite long due to inline command reference documentation (errors, tools, irritation, current-path) and the full summary template, which could be split into separate reference files for better progressive disclosure. The fidelity rules are a strong addition that serve as quality guardrails.
Suggestions
Move the detailed command reference (errors, tools, irritation, current-path) to a separate COMMANDS.md file and link to it from the main skill, keeping only the core 5 commands (list, messages, search, show, index) inline.
Consider moving the full summary template to a separate SUMMARY_TEMPLATE.md file, referencing it from the workflow step where it's needed.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly efficient but includes some verbose sections, particularly the full command reference for errors/tools/irritation/current-path which could be split into a separate reference file. The summary template is quite long inline. However, most content is actionable rather than explanatory fluff. | 2 / 3 |
Actionability | Every command is shown with exact executable invocations, flags, and expected outputs. The workflow steps are concrete with copy-paste-ready bash commands. The summary template provides a complete, specific format to follow. | 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 ensuring summary quality. The index rebuild note is an important operational checkpoint. | 3 / 3 |
Progressive Disclosure | The skill keeps everything in one file, including a lengthy command reference section and full summary template that could be split into separate reference files. The script path is clearly identified and the index locations are well-documented, but the inline command reference for 5+ subcommands makes this a long monolithic document. | 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
11ec483
- 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.