strategic-compact

Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.

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 ./docs/zh-TW/skills/strategic-compact/SKILL.md

Quality

Content

67%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, actionable, and clearly sequenced for a hook-based skill, with a copy-paste installation config and concrete defaults. Its main weaknesses are a rationale section that over-explains familiar concepts and references to a script that is not bundled.

Suggestions

Tighten or trim the '為什麼需要策略性壓縮？' section to assume Claude's knowledge of auto-compaction drawbacks, keeping only the strategic-timing rationale.

Bundle the referenced suggest-compact.js (and hooks.json / install.sh) in ./scripts/ and ./assets/ so the progressive-disclosure references resolve to real files.

Add an explicit validation/verification checkpoint (e.g., confirm the hook fires after the threshold) to lift workflow clarity toward 5.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with clear bullets and a copy-paste JSON block, but the '為什麼需要策略性壓縮？' section restates concepts Claude already knows about auto-compaction drawbacks, keeping it just below an efficient 4.	3 / 5
Actionability	Provides a complete, copy-paste-ready hook JSON config, a concrete env var with default, and a precise description of the script's threshold behavior (50 calls, every 25), with only minor gaps (the referenced script itself is not bundled).	4 / 5
Workflow Clarity	The '運作方式' section lays out a clear 3-step sequence (track → threshold detect → periodic reminder) and the best-practices list gives unambiguous timing guidance; this is a non-destructive suggestion hook so the destructive-operation cap does not apply, but it lacks explicit validation checkpoints that would reach 5.	4 / 5
Progressive Disclosure	Well-organized into clear sections with plainly signaled references (script, hooks.json, install.sh, guide link); the main gap is that the centrally referenced suggest-compact.js is not present in a bundle directory, a minor navigation dead-end rather than a structural problem.	4 / 5
	Total	15 / 20 Passed

Description

53%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 clearly states the skill's purpose and carves a distinct niche, but lacks an explicit "Use when..." trigger clause and relies on a single concrete action, which limits completeness and specificity. Trigger terms are relevant but miss natural user phrasings.

Suggestions

Add an explicit 'Use when...' clause naming concrete triggers (e.g., 'Use when context is filling up mid-task, before starting a new task phase, or after completing a milestone').

Expand from one action to several specific behaviors (e.g., 'tracks tool calls, detects a configurable threshold, and reminds you to compact') to raise specificity.

Include natural user-side phrasings and synonyms like '/compact', 'context window', and 'running low on context' to improve trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain (context compaction) and one concrete action ("Suggests manual context compaction"), but does not list multiple specific actions, matching the anchor for a clear domain with only 1-2 concrete actions.	3 / 5
Completeness	The "what" is clear ("Suggests manual context compaction at logical intervals"), but there is no explicit "Use when..." clause; the "when" is only weakly implied via "logical intervals" and "task phases", so per the guidelines completeness caps at 3.	3 / 5
Trigger Term Quality	Relevant keywords like "context compaction", "auto-compaction", and "task phases" appear, but natural user phrases (e.g., "compact", "context is full", "running low on context") are only weakly represented and synonyms are missing.	3 / 5
Distinctiveness Conflict Risk	The strategic-vs-arbitrary compaction framing carves a fairly distinct niche with minimal overlap risk, though it is not maximally explicit with concrete trigger phrases, placing it just below a 5.	4 / 5
	Total	13 / 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: affaan-m/ECC
Path: docs/zh-TW/skills/strategic-compact/SKILL.md
Commit: d8409a4

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.