strategic-compact

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

Quality

58%

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 ./.kiro/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.

The body is well-structured and largely actionable with concrete hook setup and decision guidance, but it carries a tangential token-optimization section and references bundle files that do not exist in the package. Progressive disclosure and conciseness are the weakest areas.

Suggestions

Move the 'Token Optimization Patterns' section into a separate reference file (or remove it) since it is tangential to the core compaction-suggestion purpose.

Either include the referenced suggest-compact.js, hooks/hooks.json, and install.sh in a scripts/hooks bundle, or remove references to files that are not shipped.

Tighten 'What Survives Compaction' and 'Context Composition Awareness' into shorter bullets so every token earns its place.

Dimension	Reasoning	Score
Conciseness	The core sections are efficient, but the 'Token Optimization Patterns' section (trigger-table lazy loading, context composition awareness, duplicate instruction detection, MCP tools) is tangential to the skill's purpose and reads as padding Claude largely already knows.	3 / 5
Actionability	Provides copy-paste-ready hook-setup JSON, a concrete env var (COMPACT_THRESHOLD), a decision table, and numbered best practices; the only gap is that suggest-compact.js itself is described rather than shown.	4 / 5
Workflow Clarity	A clear 3-step 'How It Works' sequence plus a phase-transition decision table and explicit safety guidance ('Don't compact mid-implementation', 'Write before compacting') give clear checkpoints; this is a suggestion skill rather than a destructive batch op, so no validate-retry loop is required.	4 / 5
Progressive Disclosure	No bundle files exist (references/, scripts/, assets/ absent), yet the body references suggest-compact.js, hooks/hooks.json, and install.sh that are not present, and tangential material like Token Optimization Patterns is inlined rather than split into a reference file.	3 / 5
	Total	14 / 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 what the skill does and carves a distinct niche, but it lacks an explicit 'Use when...' trigger clause and the natural keyword variations a user would actually say. It sits at a solid mid-range score with trigger guidance as the main gap.

Suggestions

Add an explicit trigger clause, e.g. 'Use when running long sessions approaching context limits, switching between unrelated tasks, or before a major phase transition.'

Include natural user-facing phrases like 'long session', 'running out of context', or 'context window full' alongside the technical 'compaction' terms.

Name a second concrete action (e.g. 'reminds periodically after a threshold') to lift specificity beyond a single action.

Dimension	Reasoning	Score
Specificity	Names the domain ('context compaction') and one concrete action ('Suggests manual context compaction at logical intervals'), but offers only a single action and is not comprehensive, matching the anchor for 1-2 concrete actions.	3 / 5
Completeness	The 'what' is clear (suggests manual compaction at logical intervals) but there is no explicit 'Use when...' trigger clause — the 'when' is only weakly implied by 'at logical intervals ... through task phases', which caps completeness at 3 per the judging guidelines.	3 / 5
Trigger Term Quality	Includes relevant terms ('context compaction', 'auto-compaction', 'task phases') but misses the natural phrases users actually say ('long session', 'running out of context', 'context full'), so keyword coverage is only partial.	3 / 5
Distinctiveness Conflict Risk	It carves a clear niche (strategic timing of compaction vs auto-compaction) with minimal overlap risk against unrelated skills, though it could still brush against general context-management skills, fitting 'mostly distinct; minor overlap'.	4 / 5
	Total	13 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: affaan-m/ECC
Path: .kiro/skills/strategic-compact/SKILL.md
Commit: d8409a4

Reviewed: 5 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.