context-compression

Manage and compress conversation context in long sessions. Detect when context is growing large, summarize completed work phases, archive old findings while preserving key decisions. Prevents context degradation.

Quality

60%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/context-compression/SKILL.md

Quality

Content

61%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.

The body is well-structured and actionable with useful compression templates and a clear protocol, but it is held back by mild over-explanation of known concepts and the absence of a validation checkpoint in an information-discarding workflow.

Suggestions

Trim the Overview's re-explanation of what context degradation is and why long sessions cause it; Claude already knows this.

Add an explicit validation checkpoint after writing a summary (e.g., 'Verify the summary preserves file paths, line numbers, and key decisions before discarding the raw phase') to lift workflow clarity above 3.

Consider moving the three verbose before/after Level examples into a references file and keeping only one inline, to improve progressive disclosure and token efficiency.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with tables and templates, but the Overview re-explains context degradation (a concept Claude already knows) and some before/after prose could be tightened.	3 / 5
Actionability	Provides concrete before/after compression templates, a numbered Compression Protocol, and checklists of what to preserve vs discard — actionable guidance with only minor gaps.	4 / 5
Workflow Clarity	A clear Step 1/2/3 sequence exists, but there is no validate→fix→retry checkpoint; because compression discards information (a destructive-ish operation), workflow clarity is capped at 3.	3 / 5
Progressive Disclosure	The body is well-sectioned (Overview, When to Compress, Compression Levels, Protocol, Best Practices) with no nested references, but at ~140 lines it exceeds the under-50-line simple-skill exception that would allow a 5.	4 / 5
	Total	14 / 20 Passed

Description

58%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.

The description conveys a clear, specific set of capabilities for a distinct niche, but it omits an explicit 'Use when…' trigger clause and leans on the separate when_to_use field for triggering, which caps completeness and trigger-term quality.

Suggestions

Fold a concise 'Use when…' trigger clause into the description itself (e.g., 'Use when a session has 20+ turns or context feels repetitive') so completeness is not capped at 3.

Add the natural user phrases (e.g., 'summarize what we've done', 'losing track of earlier work') to the description to improve trigger-term quality.

Avoid the second-person-ish framing of intent ('Prevents context degradation') by keeping strictly third-person action verbs.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('Detect when context is growing large', 'summarize completed work phases', 'archive old findings while preserving key decisions') with only minor gaps in coverage.	4 / 5
Completeness	The 'what' is clear, but the description field lacks an explicit 'Use when…' clause or equivalent trigger guidance, so completeness is capped at 3 per the rubric guideline.	3 / 5
Trigger Term Quality	Contains some relevant keywords ('long sessions', 'context is growing large', 'summarize') but the natural user-facing trigger phrases live in the separate when_to_use field rather than the description, so common variations are missing.	3 / 5
Distinctiveness Conflict Risk	Context compression is a fairly distinct niche with its own triggers, with only minor overlap risk against general summarization skills.	4 / 5
	Total	14 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: vudovn/ag-kit
Path: .agents/skills/context-compression/SKILL.md
Commit: 549ba3d

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.