cc-skill-strategic-compact

Prepare a verified checkpoint before condensing an agent conversation at a phase boundary. Use during long tasks when context is repetitive; preserves constraints, evidence, decisions and the next action.

Quality

86%

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

Quality

Content

88%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 content is a well-structured, actionable process guide with executable artifacts, a concrete template, explicit validation checkpoints, and lean prose. It scores near the top across all dimensions, with only minor conciseness and disclosure-organization room for improvement.

Suggestions

Trim or move the legacy user-state-counter migration note into a short "Deprecated behavior" aside to improve conciseness.

Consider splitting the worked example and optional reminder into a reference file to strengthen progressive disclosure now that the body is over 50 lines.

Dimension	Reasoning	Score
Conciseness	The body is largely lean and assumes competence, but the legacy counter paragraph ("Earlier versions incremented a shared user-state counter...") and the somewhat elaborate worked example are minor instances that could be tightened, fitting the 4 rather than 5 anchor.	4 / 5
Actionability	It provides a copy-paste checkpoint template, a concrete executable command ("bash skills/cc-skill-strategic-compact/suggest-compact.sh 50") with documented args/env vars, and a specific worked example with real artifacts (source merge SHA, canonical PR number), matching the fully-executable 5 anchor.	5 / 5
Workflow Clarity	The 6-step procedure is clearly sequenced with explicit validation checkpoints (step 4 "Check that the next action is executable", step 6 "verify mutable state before continuing") and feedback loops, satisfying the destructive-operation validation requirement that would otherwise cap at 3.	5 / 5
Progressive Disclosure	The single SKILL.md is well-organized into clearly signaled sections with one one-level-deep external reference (suggest-compact.sh), but the body exceeds the ~50-line simple-skill threshold, so it does not fully match the 5 anchor's clear overview-with-bulk-split-out structure.	4 / 5
	Total	18 / 20 Passed

Description

83%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 answers both what the skill does and when to use it, with concrete actions and natural trigger terms in third-person imperative voice. It is specific and distinguishable, with only minor gaps in synonym coverage and exhaustiveness.

Suggestions

Add common synonyms users say (e.g., "compact", "context window full", "running out of context") to broaden trigger coverage.

List a couple more concrete checkpoint actions explicitly in the description to push specificity toward comprehensive.

Dimension	Reasoning	Score
Specificity	Quotes "Prepare a verified checkpoint before condensing an agent conversation" and "preserves constraints, evidence, decisions and the next action" name the domain plus several concrete actions (checkpointing, preserving specific artifacts), but coverage of the full action set is slightly less exhaustive than the 5 anchor.	4 / 5
Completeness	It explicitly states the what ("Prepare a verified checkpoint before condensing an agent conversation at a phase boundary") and the when ("Use during long tasks when context is repetitive") with concrete trigger phrases, matching the 5 anchor for both.	5 / 5
Trigger Term Quality	Phrases "long tasks", "context is repetitive", "phase boundary", and "condensing an agent conversation" are natural triggers a user would say, but common synonyms like "compact" or "context window full" are absent, leaving it just below comprehensive.	4 / 5
Distinctiveness Conflict Risk	The checkpoint/compaction niche is distinct and unlikely to trigger the wrong skill, but the phrasing is generic enough to allow minor overlap with general context-management skills, so it sits below the 5 anchor.	4 / 5
	Total	17 / 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: sickn33/agentic-awesome-skills
Path: skills/cc-skill-strategic-compact/SKILL.md
Commit: b1aebac

Reviewed: ~18 hours 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.