compact

Compact the current chat context into a concise summary. Use when the user invokes /compact, context capacity is running low, or a long session needs a smaller continuation state.

Quality

82%

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

Quality

Content

86%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 a lean, well-organized instruction for a simple single-purpose skill that respects token budget and assumes Claude's competence. It is highly actionable for an instruction-only skill, with only minor underspecification around how the native compaction action is invoked.

Dimension	Reasoning	Score
Conciseness	Two tight paragraphs with no padding and no explanation of concepts Claude already knows; every token earns its place, matching the lean anchor-5 example.	5 / 5
Actionability	"Preserve the objective, constraints, decisions, evidence, current workspace state, unfinished work, and exact next action" plus "Use the native compaction action" gives concrete, specific guidance, but does not specify how to invoke that native action, leaving a minor gap versus a 5.	4 / 5
Workflow Clarity	The single action is largely unambiguous with an explicit preservation guard ("without dropping material blockers or verification results"), but there is no explicit validation checkpoint and the mechanism is slightly underspecified, so 4 rather than 5.	4 / 5
Progressive Disclosure	Under 50 lines with a clear heading and organized paragraphs and no need for external references, qualifying for the simple-skill exception at anchor 5.	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.

The description cleanly states a single concrete action and provides explicit, multi-scenario trigger guidance, making both the what and when unambiguous. It is distinctive and well-voiced, with only minor room to expand action specificity and trigger synonyms.

Dimension	Reasoning	Score
Specificity	"Compact the current chat context into a concise summary" names the domain plus one concrete action, matching anchor 3; it does not list several specific actions needed for a 4.	3 / 5
Completeness	It explicitly answers both what (compact chat context into a concise summary) and when (concrete trigger phrases including /compact and low context), matching the anchor-5 example.	5 / 5
Trigger Term Quality	"Use when the user invokes /compact, context capacity is running low, or a long session needs a smaller continuation state" gives good natural-trigger coverage across multiple scenarios, just short of the comprehensive synonym set of a 5.	4 / 5
Distinctiveness Conflict Risk	The /compact command and "continuation state" framing carve a clear niche with a distinct trigger, but there is minor overlap risk with general summarization skills, so 4 rather than 5.	4 / 5
	Total	16 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: synthetic-sciences/openscience
Path: backend/cli/skills/other/compact/SKILL.md
Commit: 4082a2e

Reviewed: 1 day 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.