session-logs

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

1.91x

Quality

59%

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 ./openclaw/skills/session-logs/SKILL.md

Quality

Content

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 with excellent conciseness and fully executable examples covering a wide range of session log queries. Its main weaknesses are the lack of a guided workflow for common multi-step investigation tasks and the fact that all content is in a single file when some queries could be offloaded to a reference document. The trigger and location sections are well-defined and practical.

Suggestions

Add a brief recommended workflow for the most common use case (e.g., 'To investigate a past conversation: 1. List sessions to find the date, 2. Extract user messages to confirm the right session, 3. Search assistant responses for the relevant content').

Consider splitting the extensive 'Common Queries' section into a separate QUERIES.md reference file, keeping only 2-3 essential queries in the main SKILL.md.

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. No unnecessary padding.	3 / 3
Actionability	Every query is a fully executable, copy-paste-ready bash/jq command. The examples cover a comprehensive range of use cases (listing sessions, searching, cost analysis, tool usage) with concrete, runnable code rather than pseudocode or vague descriptions.	3 / 3
Workflow Clarity	The skill is primarily a reference of independent queries rather than a multi-step workflow, so sequencing is less critical. However, there's no guidance on a recommended workflow for common tasks (e.g., 'first find the session, then extract messages, then search'), and no validation steps for confirming results or handling edge cases like missing files or empty sessions.	2 / 3
Progressive Disclosure	The content is well-organized with clear sections (Location, Structure, Common Queries, Tips), but it's a moderately long single file with many query examples that could benefit from being split—e.g., a quick-reference section in SKILL.md with advanced queries in a separate file. No bundle files are provided to offload content.	2 / 3
	Total	10 / 12 Passed

Description

40%

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 and distinctive niche (searching own session logs with jq) but is too terse. It lacks explicit trigger guidance ('Use when...') and doesn't enumerate specific capabilities beyond the generic 'search and analyze'. The distinctiveness is its strongest quality.

Suggestions

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

List more specific concrete actions, e.g., 'Search, filter, and analyze session logs from older/parent conversations using jq — extract timestamps, count messages, find specific topics, or summarize past interactions.'

Include additional natural trigger terms users might say, such as 'past sessions', 'conversation history', 'previous chats', 'log analysis', or 'query logs'.

Dimension	Reasoning	Score
Specificity	Names the domain (session logs / older conversations) and mentions two actions (search and analyze) plus the tool (jq), but doesn't list specific concrete actions like filtering by date, extracting metrics, or querying specific fields.	2 / 3
Completeness	Describes what the skill 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 fairly thin, placing this at 1.	1 / 3
Trigger Term Quality	Includes some relevant terms like 'session logs', 'conversations', and 'jq', but misses natural user phrases like 'past sessions', 'conversation history', 'previous chats', 'log files', or 'query logs'.	2 / 3
Distinctiveness Conflict Risk	The combination of 'session logs', 'parent conversations', and 'jq' creates a very specific niche that is unlikely to conflict with other skills. This is a clearly distinct use case.	3 / 3
	Total	8 / 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: trpc-group/trpc-agent-go
Commit: fc01b4b

Reviewed: 3 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.