CtrlK
BlogDocsLog inGet started
Tessl Logo

session-logs

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

79

1.91x
Quality

71%

Does it follow best practices?

Impact

94%

1.91x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./openclaw/skills/session-logs/SKILL.md

The canonical home for this skill is session-logs in Hung-Reo/hungreo-openclaw

SKILL.md
Quality
Evals
Security

Quality

Content

82%Weight 40%Scale 1-5

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

A well-organized, highly actionable reference for querying session JSONL files with copy-paste-ready jq/rg commands and useful edge-case tips. The main improvement opportunities are removing the redundant trailing hint section and slightly tightening placeholder documentation.

DimensionReasoningScore

Conciseness

The body is a lean command cookbook with headers, structure documentation, and ready-to-run snippets and almost no conceptual padding. It is not a 5 because the trailing "Fast text-only hint (low noise)" section largely duplicates the earlier keyword-search query, and not a 3 because there are no unnecessary concept explanations.

4 / 5

Actionability

Every section provides copy-paste-ready bash/jq/rg commands covering the common cases (listing, filtering, searching, cost totals, tool-usage counts), with the `<agentId>` placeholder resolved by pointing to the system prompt Runtime line. It is not a 4 because the examples are executable as written once the documented placeholders are substituted and the common cases are comprehensively covered.

5 / 5

Workflow Clarity

Location → Structure → Common Queries gives a coherent progression for a read-only query skill, and the Tips section covers edge cases (deleted sessions, large files, the sessions.json index). It is not a 5 because there are no explicit checkpoints (e.g. verifying a session file exists or the JSONL parses before running expensive queries) and the `<session>.jsonl` placeholder is not spelled out, and not a 3 because the sequence is clear and no destructive/batch operations require validation.

4 / 5

Progressive Disclosure

No bundle files exist, and the body is well organized into clearly signaled sections (Trigger, Location, Structure, Common Queries, Tips) with no nested references. It is not a 5 because at roughly 106 lines — above the under-50-line simple-skill bar — the nine-query cookbook could be split into a reference file, and not a 3 because what is present is appropriately placed and easy to navigate.

4 / 5

Total

17

/

20

Passed

Description

61%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A lean, fairly specific description that names the domain, tool, and concrete actions with natural trigger phrases in the parenthetical. Its main weaknesses are the missing explicit "Use when..." trigger clause and second-person voice, which cap completeness and specificity respectively.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks about prior chats, parent conversations, or what was said in earlier sessions."

Rewrite in third person to avoid the "your own" penalty, e.g. "Searches and analyzes session logs (older/parent conversations) with jq."

Add one or two natural synonyms such as "chat history" or "past conversations" to broaden trigger-term coverage.

DimensionReasoningScore

Specificity

"Search and analyze your own session logs ... using jq" names the domain, two concrete actions, and the tool, which is a base 4 ("lists several specific actions; minor gaps"), but the second-person phrase "your own session logs" triggers the mandated 1-point voice penalty, landing at 3. It is not a 2 because the actions and tool are specific rather than generic, and not a 4 because the penalty applies and coverage gaps exist (no mention of summarizing, cost analysis, etc.).

3 / 5

Completeness

The "what" is clear (search and analyze session logs with jq) but there is no "Use when..." clause or equivalent explicit trigger guidance in the description, which caps completeness at 3 per the guidelines; "older/parent conversations" only weakly implies the "when". It is not a 4 because the trigger guidance exists only in the body, not the description, and not a 2 because the "what" is concrete rather than vague.

3 / 5

Trigger Term Quality

"session logs", "older/parent conversations" are natural phrases a user would say, giving good keyword coverage. It is not a 5 because common variations like "chat history", "past chats", or "transcripts" are missing, and not a 3 because the parenthetical supplies several genuinely natural trigger phrases rather than just one or two generic keywords.

4 / 5

Distinctiveness Conflict Risk

"your own session logs (older/parent conversations) using jq" carves a clear niche with mostly distinct triggers. It is not a 5 because it could minorly overlap with memory-file or general history-search skills, and not a 3 because the jq/session-logs pairing is specific enough that it would rarely fire for the wrong skill.

4 / 5

Total

14

/

20

Passed

Validation

87%

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

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

Total

14

/

16

Passed

Repository
trpc-group/trpc-agent-go
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.