CtrlK
BlogDocsLog inGet started
Tessl Logo

chat-history

Use when details may have been lost after context compaction, or when the Agent needs to inspect earlier compacted messages or previously created sub-agents.

65

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./backend/super-magic/agents/skills/chat-history/SKILL.md
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 tight, highly actionable skill body with executable examples and a clearly sequenced list-search-read workflow. The main gap is the absence of explicit validation/feedback-loop checkpoints, though the read-only nature softens that concern.

DimensionReasoningScore

Conciseness

The body is lean, assumes Claude's competence, and avoids explaining what chat history or ripgrep is; the only mild padding is the enumerated time_range forms, which are reference material rather than fluff.

4 / 5

Actionability

It provides copy-paste-ready, fully executable `tool.call(...)` snippets covering the common cases (list, filtered list, search by type, search by file, read a range), plus concrete parameter examples.

5 / 5

Workflow Clarity

The intro states the normal flow (list → search → read a small range) and the four numbered sections follow it, but there are no explicit validation/retry checkpoints; this is acceptable for a read-only skill yet stops just short of a 5.

4 / 5

Progressive Disclosure

Content is well-organized into clearly headed sections with no nested or buried references, and the self-contained tool guidance is appropriately kept inline; it is just over the simple-skill line so a 5 is not automatic.

4 / 5

Total

17

/

20

Passed

Description

73%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 well-targeted, trigger-rich description for a narrow niche, with an explicit 'Use when...' clause. Its main weakness is that it emphasizes when-to-use over concrete capabilities, leaving the 'what' slightly under-specified.

Suggestions

Add 1-2 concrete capability verbs (e.g., 'list, search, and read compacted chat history') so the 'what' is as explicit as the 'when'.

Consider naming the file types or scopes (e.g., 'compacted history files') to sharpen the trigger terms further.

DimensionReasoningScore

Specificity

The description names the domain (compacted chat history) and 1-2 concrete actions ('inspect earlier compacted messages or previously created sub-agents'), but is trigger-focused rather than listing concrete capabilities like list/search/read.

3 / 5

Completeness

It has an explicit 'Use when...' clause answering when, and a what ('inspect earlier compacted messages or previously created sub-agents'), but the 'what' side is somewhat implied rather than enumerating concrete operations.

4 / 5

Trigger Term Quality

Natural trigger phrases like 'details may have been lost after context compaction' and 'compacted messages' / 'sub-agents' align well with what a user would say for this niche, with only minor synonym gaps.

4 / 5

Distinctiveness Conflict Risk

It targets a clear niche (post-compaction chat history and sub-agent inspection) with distinct triggers and minimal overlap risk against other skills.

5 / 5

Total

16

/

20

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
dtyq/magic
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.