strategic-compact

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

Quality

64%

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

75%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 compact, well-structured hook-setup skill: the JSON config is executable, install modes are clearly distinguished, and configuration is concrete. The main weaknesses are the missing verification step for hook registration and the absence of the referenced script/install files from the bundle, which slightly undercut actionability and progressive disclosure.

Suggestions

Add a short verification step after hook setup (e.g., a test edit that confirms the compact suggestion fires) to close the workflow validation gap.

Ship the referenced files (suggest-compact.js, install.sh, hooks/hooks.json) in the skill bundle or link to their actual locations, since the body's instructions currently depend on files that are not present.

Trim the "為什麼需要策略性壓縮？" rationale bullets to one line, since the behavior itself already implies the motivation.

Dimension	Reasoning	Score
Conciseness	The body is lean with well-labeled sections and almost no padding of concepts Claude already knows; the only trimmable part is the "為什麼需要策略性壓縮？" rationale bullets, which keeps it just below the level-5 "every token earns its place" anchor and clearly above level 3's "some unnecessary explanation".	4 / 5
Actionability	Provides a copy-paste-ready hooks JSON block, a concrete env var (COMPACT_THRESHOLD, default 50), and named hook IDs; however, the referenced suggest-compact.js and install.sh files are not present in the skill bundle, leaving minor gaps versus the fully executable level-5 anchor.	4 / 5
Workflow Clarity	The single setup action is unambiguous and the plugin-vs-manual install distinction is handled explicitly (including a warning against duplicate registration), but there is no step verifying the hook actually fires, so it stops short of the level-5 anchor's explicit validation/feedback loop.	4 / 5
Progressive Disclosure	The short body is organized into clear sections with one-level-deep references (script, hooks.json, install.sh, external guide), which is good structure; the referenced bundle files do not exist in the skill directory, a real but contained organization gap that keeps it below level 5.	4 / 5
	Total	16 / 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 states a clear, single-purpose capability in third person without fluff, but it omits any "when to use" trigger clause and lacks the natural keyword variations that would help it fire at the right moments. It is specific enough to avoid most conflicts but under-optimized for discovery.

Suggestions

Add an explicit trigger clause, e.g. "Use when sessions run long, the context window is filling up mid-task, or the user mentions /compact or compaction."

Include natural synonyms and concrete terms users would say, such as "/compact", "context window", and "long-running tasks", to improve trigger-term coverage.

Optionally enumerate the concrete actions (when it suggests compaction: after exploration, after milestones, before context switches) to lift specificity from one action to several.

Dimension	Reasoning	Score
Specificity	Names the domain and one concrete action ("Suggests manual context compaction at logical intervals to preserve context") but does not enumerate several specific actions, so it falls short of the level-4 anchor's "several specific actions" and sits above level 2's generic-domain-only example.	3 / 5
Completeness	The "what" is clear (suggest manual compaction at logical task boundaries), but there is no "Use when..." clause or equivalent trigger guidance; per the judging guidelines a missing explicit trigger clause caps completeness at 3.	3 / 5
Trigger Term Quality	Relevant keywords like "context compaction" and "auto-compaction" are present, but common natural variations users would actually say (/compact, "context window filling up", "long session") are missing, matching the level-3 anchor rather than level 4's "good keyword coverage".	3 / 5
Distinctiveness Conflict Risk	Manual-compaction advice at logical task phases is a narrow niche distinct from most skills, with only minor overlap risk against general session/context-management skills, matching the level-4 anchor; it lacks the fully explicit distinct triggers of level 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: c70874f

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.