CtrlK
BlogDocsLog inGet started
Tessl Logo

compact-chat-history

Summarize and compress the current conversation history into a structured context snapshot, then call compact_chat_history to save it. Read this skill only when the user explicitly asks to compact/summarize — system-triggered compaction injects the instructions directly without requiring a skill read.

64

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./backend/super-magic/agents/skills/compact-chat-history/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

68%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 highly actionable, well-structured instruction skill with concrete tool/parameter guidance and a complete output example. Its weaknesses are redundancy in the status-state guidance and the absence of an explicit pre-call validation checkpoint for an irreversible operation.

Suggestions

Add an explicit verification step before the tool call (e.g. 'Confirm the summary is ≥10,000 chars and preserved_user_input_indexes match Section 6 before calling compact_chat_history') to add a validation checkpoint.

Consolidate the repeated complete/incomplete definitions in Section 5 into a single clear rule to remove redundancy and recover token budget.

Consider moving the long Output Format Example block into a reference file to slim the SKILL.md body and improve progressive disclosure.

DimensionReasoningScore

Conciseness

Mostly efficient and genuinely actionable, but Section 5 restates the complete/incomplete distinction across many bullets ('If the task is complete, say it is complete', 'A task is complete only when...', 'If complete, say so...') and the Rules section reiterates index-passing, so it could be tightened.

3 / 5

Actionability

Provides fully concrete, executable guidance: exact tool name (compact_chat_history), exact parameters (summary, preserved_user_input_indexes), a full output-format example, and hard rules (≥10,000 chars, pass empty list if no index), covering the common cases.

5 / 5

Workflow Clarity

The sequence is clear (fill sections 1-6, then call compact_chat_history with summary and indexes), but there is no explicit validation checkpoint before the irreversible compaction call; per the destructive-operation cap this holds at 3 even though the flow is well ordered.

3 / 5

Progressive Disclosure

Self-contained with well-organized section headers (Instructions, Output Format Example, Rules) and no bundle files needed; good structure, though the long inlined example and 150+ line body keep it just short of the lean top anchor.

4 / 5

Total

15

/

20

Passed

Description

83%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 description that clearly pairs a concrete 'what' with an explicit 'when' trigger and names a specific tool, keeping conflict risk low. The main gap is slightly limited trigger synonym coverage and minor overlap risk from the generic term 'summarize'.

Suggestions

Add a couple of natural trigger synonyms (e.g. 'compress', 'shrink the chat') alongside 'compact/summarize' to broaden keyword coverage.

Tighten the 'summarize' trigger to a chat-specific phrase (e.g. 'summarize this conversation') to reduce overlap with general summarization skills.

DimensionReasoningScore

Specificity

Names the domain (conversation history compaction) and several concrete actions — 'Summarize and compress', 'structured context snapshot', 'call compact_chat_history to save it' — with only minor coverage gaps, fitting the 'lists several specific actions' anchor above the 1-2 action midpoint.

4 / 5

Completeness

Explicitly states what ('Summarize and compress the current conversation history into a structured context snapshot, then call compact_chat_history') and when ('Read this skill only when the user explicitly asks to compact/summarize') with concrete trigger phrases, matching the top anchor.

5 / 5

Trigger Term Quality

Includes natural user phrases 'compact' and 'summarize' plus 'conversation history', giving good keyword coverage; a few common synonyms (e.g. 'compress', 'shrink chat') are missing so it does not reach comprehensive coverage.

4 / 5

Distinctiveness Conflict Risk

The compact_chat_history tool name and explicit boundary ('only when the user explicitly asks') give it a clear niche with minimal conflict risk, though the generic trigger 'summarize' creates minor overlap with general summarization skills.

4 / 5

Total

17

/

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.