strategic-compact
Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.
65
56%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./docs/zh-TW/skills/strategic-compact/SKILL.mdQuality
Discovery
40%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 identifies a specific niche (manual context compaction) and distinguishes itself well from other potential skills, but it lacks explicit trigger guidance ('Use when...') and misses common user-facing keywords. It reads more like a feature summary than a skill selection guide.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about managing context window limits, preserving conversation history, or avoiding auto-compaction during long tasks.'
Include natural trigger terms users would actually say, such as 'context window', 'running out of context', 'long conversation', 'memory', or 'conversation history'.
List additional concrete actions beyond just 'suggests compaction', e.g., 'Identifies logical breakpoints in tasks, recommends when to compact, and provides strategies for preserving key context across phases.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names a specific domain (context compaction) and describes the core action (suggests manual context compaction at logical intervals), but it doesn't list multiple concrete actions—it's essentially one action with a rationale. | 2 / 3 |
Completeness | The description explains what the skill does (suggests manual context compaction) but lacks any explicit 'Use when...' clause or trigger guidance. Per the rubric, a missing 'Use when' clause caps completeness at 2, and since the 'when' is entirely absent, this scores a 1. | 1 / 3 |
Trigger Term Quality | Includes relevant terms like 'context compaction', 'auto-compaction', and 'task phases', but misses common user-facing variations like 'context window', 'running out of context', 'memory management', or 'conversation length'. Users may not naturally say 'compaction'. | 2 / 3 |
Distinctiveness Conflict Risk | Context compaction is a fairly niche topic, and the description's focus on manual compaction at logical intervals vs. auto-compaction creates a clear, distinct niche that is unlikely to conflict with other skills. | 3 / 3 |
Total | 8 / 12 Passed |
Implementation
72%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is well-structured and provides actionable hook configuration with clear best practices for when to use strategic compaction. The main weaknesses are some unnecessary explanatory content about why auto-compaction is problematic (which Claude can infer) and a lack of validation/verification steps for confirming the hook is properly installed and functioning. The best practices section is a genuine strength, providing clear decision guidance.
Suggestions
Trim the 'Why strategic compaction?' section to 1-2 lines — Claude doesn't need a detailed comparison of auto vs manual compaction to follow the instructions.
Add a verification step after hook setup, e.g., 'Verify: run `cat ~/.claude/skills/strategic-compact/suggest-compact.sh` to confirm script exists and is executable.'
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The 'Why strategic compaction?' section explaining auto-compaction drawbacks is somewhat unnecessary context — Claude can understand the motivation from the skill's purpose. The comparison bullets add some value but could be tighter. The rest is reasonably efficient. | 2 / 3 |
Actionability | Provides a concrete, copy-paste ready JSON configuration for hooks, specifies the exact script path, explains the environment variable for configuration, and gives clear behavioral rules (when to compact, when not to). The guidance is specific and directly executable. | 3 / 3 |
Workflow Clarity | The workflow of how the hook operates (track calls → threshold → suggest) is listed but lacks validation steps. There's no guidance on verifying the hook is working correctly, no error handling if the script fails, and no feedback loop for confirming compaction was beneficial. For a hook-based skill that modifies workflow behavior, this is a gap. | 2 / 3 |
Progressive Disclosure | For a skill of this size (~50 lines), the content is well-organized into logical sections (why, how, setup, config, best practices, related). External references are one level deep and clearly signaled. The structure supports easy scanning and discovery. | 3 / 3 |
Total | 10 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- haniakrim21/everything-claude-code
- Commit
ae2cadd
- Reviewed
Table of Contents
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.