session-logs

Search and analyze your own session logs (older/parent conversations) using jq.

1.91x

Quality

56%

Does it follow best practices?

Impact

94%

1.91x

Average score across 3 eval scenarios

Securityby

Risky

Do not use without reviewing

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/session-logs/SKILL.md

Quality

Discovery

32%

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 identifies a clear domain (session logs / parent conversations) and a specific tool (jq), which helps with distinctiveness. However, it lacks an explicit 'Use when...' clause, provides only two high-level actions without concrete specifics, and misses natural trigger terms users might employ when needing this skill.

Suggestions

Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about previous conversations, past sessions, chat history, or wants to query session log files.'

List more specific concrete actions, e.g., 'Search session logs by date, filter conversations by topic, extract message counts, and analyze conversation patterns using jq queries.'

Include additional natural trigger terms like 'previous conversations', 'chat history', 'past sessions', 'log files', '.jsonl' to improve keyword coverage.

Dimension	Reasoning	Score
Specificity	Names the domain (session logs) and mentions two actions (search and analyze) plus a tool (jq), but doesn't list specific concrete actions like filtering by date, extracting metrics, or querying specific fields.	2 / 3
Completeness	Describes what it does (search and analyze session logs using jq) but has no explicit 'Use when...' clause or equivalent trigger guidance, which per the rubric should cap completeness at 2, and the 'what' is also only moderately detailed, placing this at 1-2. Given the missing 'when' clause entirely, scoring at 1.	1 / 3
Trigger Term Quality	Includes some relevant terms like 'session logs', 'jq', and 'conversations', but misses natural user phrases like 'previous conversations', 'chat history', 'past sessions', 'log files', or 'query logs'.	2 / 3
Distinctiveness Conflict Risk	The combination of 'session logs', 'parent conversations', and 'jq' is fairly specific, but 'search and analyze' is generic enough that it could overlap with general log analysis or jq-related skills.	2 / 3
	Total	7 / 12 Passed

Implementation

79%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This is a strong, actionable skill that provides immediately usable jq/bash commands for searching session logs. Its main strengths are concrete, executable examples and efficient use of tokens with no unnecessary explanation. The main weakness is the lack of a recommended investigation workflow (how to go from 'user asks about a prior conversation' to finding the right session and extracting relevant content).

Suggestions

Add a brief recommended workflow at the top: e.g., '1. Check sessions.json for known session keys → 2. List sessions by date to narrow candidates → 3. Search across sessions with rg → 4. Extract relevant messages from matched session'

Consider noting that <agentId> should be replaced with the actual agent ID from the system prompt Runtime line, perhaps with a one-liner to extract it programmatically

Dimension	Reasoning	Score
Conciseness	The skill is lean and efficient. It doesn't explain what jq is, what JSONL is, or how bash works. Every section provides directly usable information—file locations, data structure, and executable queries. The tips section is brief and adds genuinely useful operational knowledge.	3 / 3
Actionability	Every query is a fully executable bash/jq command that can be copy-pasted with only the agentId and session-id substituted. The examples cover a comprehensive range of real use cases (search, cost, stats, tool usage) with no pseudocode or vague instructions.	3 / 3
Workflow Clarity	This is primarily a reference/lookup skill rather than a multi-step workflow, so the bar is lower. However, there's no guidance on the recommended sequence for investigating prior conversations (e.g., start with sessions.json index → identify candidate sessions → search within them). The queries are presented as independent recipes without a coherent investigative workflow.	2 / 3
Progressive Disclosure	The content is well-organized with clear section headers and a logical progression from structure to queries to tips. However, with ~100 lines of query examples inline, some of the less common queries (daily cost summary, tool usage breakdown) could be split into a reference file. For a standalone skill with no bundle, the organization is reasonable but slightly heavy for a single file.	2 / 3
	Total	10 / 12 Passed

Validation

81%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 9 / 11 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning

	Total	9 / 11 Passed

Repository: deepgram/dglabs-deepclaw
Commit: ec8d4f8

Reviewed: 23 days ago

Table of Contents

Discovery Implementation Validation

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.