strategic-compact

Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction. Use when a session is approaching a context limit and a task phase is a natural place to compact.

Quality

67%

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 ./skills/strategic-compact/SKILL.md

Quality

Content

63%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 well-organized, actionable body with concrete hook setup, configuration, and a useful decision guide. It is held back by an off-topic Token Optimization section and the absence of any progressive-disclosure file structure.

Suggestions

Move the 'Token Optimization Patterns' section into a separate reference file or remove it; it concerns general context hygiene and external tools rather than the skill's core compaction-triggering purpose.

Split 'What Survives Compaction' and the detailed configuration reference into one-level-deep reference files so SKILL.md stays a lean overview with clearly signaled links.

Tighten 'Why Strategic Compaction?' and 'When to Activate' which overlap; consolidate the trigger conditions into the decision table to avoid restating the same boundaries twice.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and assumes Claude's competence, but the 'Token Optimization Patterns' section (trigger tables, duplicate detection, external `token-optimizer` MCP / `context-mode` tools) is off-topic padding that could be trimmed.	3 / 5
Actionability	Provides copy-paste-ready hook JSON, concrete env vars with defaults, and executable `/compact` examples; minor gaps only (the suggest-compact.js script itself is not shown, relying on the plugin file).	4 / 5
Workflow Clarity	Clear sequence via the Compaction Decision Guide table, numbered Best Practices, and a concrete 'How It Works' signal explanation; as an advisory (non-destructive) skill it lacks formal validation checkpoints but the decision flow substitutes well.	4 / 5
Progressive Disclosure	No bundle files exist; all content lives inline in one ~155-line file with several sub-topics (Token Optimization Patterns, What Survives Compaction) that could be split into one-level-deep references, though section headers are clear.	3 / 5
	Total	14 / 20 Passed

Description

71%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, third-person description that explicitly covers both what the skill does and when to use it with concrete triggers. Its main weakness is keyword coverage and action breadth, which are limited by the skill's single-purpose nature.

Dimension	Reasoning	Score
Specificity	Names the domain and a concrete action ('Suggests manual context compaction at logical intervals to preserve context through task phases') but offers only 1-2 actions for a single-purpose skill, not comprehensive coverage.	3 / 5
Completeness	Clearly answers both what ('Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction') and when ('Use when a session is approaching a context limit and a task phase is a natural place to compact') with concrete trigger phrases, in third person.	5 / 5
Trigger Term Quality	Includes relevant keywords ('context limit', 'compact', 'session', 'task phase') but misses common variations users naturally say like 'context window', 'running out of context', or '/compact'.	3 / 5
Distinctiveness Conflict Risk	Has a clear niche (strategic manual compaction vs arbitrary auto-compaction) with distinct triggers, with only minor overlap risk against general context-management skills.	4 / 5
	Total	15 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: affaan-m/ECC
Path: skills/strategic-compact/SKILL.md
Commit: e04ea0b

Reviewed: 2 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.