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 actionable for its core purpose, with an excellent compaction decision table and careful caveats about todo-tool persistence. Its weaknesses are the off-topic Token Optimization Patterns section, embedded version-specific detail, and the absence of any bundle reference files to offload detail.

Suggestions

Move the Token Optimization Patterns section (trigger-table lazy loading, context composition, duplicate detection, optimization tools) into a separate reference file, since it is tangential to when-to-compact guidance.

Replace the version-specific detail ("Claude Code 2.1.233 removed the todo/task tools", model lists) with a version-neutral statement of the risk, so the skill does not age.

Add an explicit validation step to the compaction workflow, e.g. "after writing the plan to a file, re-read it once before compacting to confirm it captures the state you need".

Dimension	Reasoning	Score
Conciseness	The core sections (decision table, hook setup, best practices) are tight and efficient, but the tangential "Token Optimization Patterns" section (~30 lines of generic token-management advice) and the version-specific blockquote ("Claude Code 2.1.233 removed the todo/task tools" with named models) add unnecessary and time-sensitive padding outside any 'old patterns' section. This sits between anchor 3 (some unnecessary explanation) and anchor 4 (minor trim needed), but the off-topic section is more than minor.	3 / 5
Actionability	The body provides copy-paste-ready hook JSON, an explicit configuration env var (COMPACT_THRESHOLD), a decision table with Compact?/Why including the "No" case, and a concrete /compact usage example. It is not 5 because it references files not present in this bundle (suggest-compact.js, install.sh, hooks/hooks.json) with no inline fallback, leaving minor gaps.	4 / 5
Workflow Clarity	The sequence is clear (when to activate → why → how it works → setup → decision guide → best practices) and includes checkpoint-like mitigations for a context-losing operation ("Write the plan to a file before compacting", "Don't compact mid-implementation", the what-survives/what-is-lost table). It is not 5 because there is no explicit validate/recover loop (e.g., verify the written plan survives before discarding context).	4 / 5
Progressive Disclosure	The body has good section structure but no bundle reference files exist (references/, scripts/, assets/ are absent), and the Token Optimization Patterns content is inlined where a separate reference file belongs. This matches anchor 3 (content that should be separate is inline) rather than 4 (most content appropriately placed).	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 is concise and clearly states what the skill does, with a distinct niche versus auto-compaction. Its main weakness is the complete absence of a "Use when..." trigger clause and natural user phrasings, which limits both completeness and trigger-term quality.

Suggestions

Add an explicit trigger clause, e.g. "Use when running long multi-phase sessions, when responses slow from context pressure, or before starting a new task in the same session."

Include natural trigger terms users would actually say, such as "compact", "context window", "200K tokens", or "long session".

Name the concrete mechanism once (suggesting the /compact command at phase boundaries) to raise specificity from one action to several.

Dimension	Reasoning	Score
Specificity	"Suggests manual context compaction at logical intervals" names the domain and one concrete action with its purpose ("preserve context through task phases"), but coverage is not comprehensive — no mention of /compact, thresholds, or hook-based triggering. It is below anchor 4, which expects several listed specific actions.	3 / 5
Completeness	The "what" is clear (suggest manual context compaction at logical intervals), but there is no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines. It is not 4 because "when" is entirely absent, not merely imprecise.	3 / 5
Trigger Term Quality	Relevant keywords exist ("context compaction", "logical intervals", "task phases", "auto-compaction") but they are technical phrasings; natural user trigger terms like "compact", "long sessions", "context limits", or "200K tokens" are missing. This matches anchor 3 (some relevant keywords, missing common variations) rather than 4 (good natural-term coverage).	3 / 5
Distinctiveness Conflict Risk	The compaction-timing niche ("rather than arbitrary auto-compaction") is mostly distinct from other skills with minor overlap risk against general context-management or memory skills. It is not 5 because no explicit trigger phrases fully separate it from those adjacent skills.	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: 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.