CtrlK
BlogDocsLog inGet started
Tessl Logo

get-chat-history

Get current chat history including user messages, your replies, and system task notifications. When user says 'check previous messages' or 'what did I just send', use this tool.

67

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

85%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 clean, well-organized, minimal tool skill whose body efficiently documents parameters, returns, and usage triggers. Weaknesses are limited to minor redundancy between the body and the frontmatter description.

DimensionReasoningScore

Conciseness

The body is lean (parameter table, returns, when-to-use, related skills) with every section earning its place, but the Returns list and When-to-Use bullets partly restate content already in the description, a minor redundancy that fits the 4 anchor rather than 5.

4 / 5

Actionability

The parameter table gives concrete, executable details (types, required flags, defaults of 20 and True) and the returns are enumerated; for a registered tool skill this is concrete actionable guidance, matching the 4 anchor with only minor gaps.

4 / 5

Workflow Clarity

A simple single-task skill (retrieve chat history) with an unambiguous single action; per the rubric's simple-skill exception and no destructive/batch operation requiring validation, it qualifies for the 5 anchor.

5 / 5

Progressive Disclosure

Under 50 lines with no need for external references and well-organized sections (Parameters, Returns, When to Use, Related Skills); per the rubric's under-50-lines exception, this fits the 5 anchor.

5 / 5

Total

18

/

20

Passed

Description

78%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 strong, concrete description that clearly states both capability and trigger conditions with natural user phrasing. The main weakness is second-person voice ('your replies', 'use this tool'), which the rubric penalizes.

Suggestions

Rewrite in third person: change 'your replies' to 'your previous replies' phrasing as 'the agent's replies' and 'use this tool' to 'use when...' to avoid the second-person specificity penalty.

Add a couple of trigger synonyms/variants (e.g., 'review the conversation', 'show chat history') to push trigger_term_quality toward comprehensive coverage.

DimensionReasoningScore

Specificity

Names the domain and three concrete retrieved categories ('user messages, your replies, and system task notifications'), which is solidly a 4, but the second-person phrasing ('your replies', 'use this tool') triggers the rubric's -1 specificity penalty, bringing it to 3.

3 / 5

Completeness

Explicitly answers both what ('Get current chat history including...') and when (concrete trigger phrases), matching the 5 anchor for clearly answering both with concrete triggers.

5 / 5

Trigger Term Quality

Includes two natural phrases a user would actually say ('check previous messages' or 'what did I just send'); good coverage, though synonyms/variants are limited, fitting the 4 anchor rather than 5.

4 / 5

Distinctiveness Conflict Risk

Chat-history retrieval is a distinct niche with dedicated trigger phrases ('check previous messages', 'what did I just send'); mostly distinct with only minor overlap risk, matching the 4 anchor.

4 / 5

Total

16

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
openakita/openakita
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.