ck

Persistent per-project memory for Claude Code. Auto-loads project context on session start, tracks sessions with git activity, and writes to native memory. Commands run deterministic Node.js scripts — behavior is consistent across model versions. Use when a project needs context to survive across Claude Code sessions instead of being re-explained each time.

Quality

91%

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

The canonical home for this skill is tdg-personal/ck

Quality

Content

96%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.

An exemplar of actionable, concise skill content: every command ships with exact commands, JSON schemas, and confirmation checkpoints. The only gap is progressive disclosure — no bundled reference files exist, so navigation is purely by section header.

Suggestions

Consider splitting the per-command JSON schemas or the SessionStart hook registration into a reference file (e.g., references/schemas.md) so SKILL.md stays a lean overview with one-level-deep navigation.

Add a short top-of-file table of contents or command index linking to each /ck:* section to improve discoverability as the command list grows.

Verify the referenced scripts (commands/*.mjs, hooks/session-start.mjs) are bundled in the skill so the documented commands resolve at runtime.

Dimension	Reasoning	Score
Conciseness	Lean and efficient: it assumes Claude's competence, avoids over-explaining concepts, and every line (verbatim node invocations, exact JSON schemas, rules) earns its place.	5 / 5
Actionability	Provides fully executable, copy-paste-ready bash commands and exact JSON schemas for every command, covering the common cases without pseudocode.	5 / 5
Workflow Clarity	Multi-step commands are clearly sequenced with explicit confirmation checkpoints and feedback loops — init (draft → confirm → pipe to save), save (analyze → draft → confirm → pipe), and forget (resolve → confirm → delete), plus error-exit handling rules.	5 / 5
Progressive Disclosure	Content is well-organized into clear per-command sections with consistent headers, but all detail is inlined and there are no separate reference files for navigation; the skill relies on external scripts not bundled here.	4 / 5
	Total	19 / 20 Passed

Description

87%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.

A strong description that concretely states capabilities and gives an explicit, natural 'Use when...' trigger. Its only weakness is modest keyword coverage — a few common synonyms would make the trigger more robust.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — 'Auto-loads project context on session start, tracks sessions with git activity, and writes to native memory' and 'Commands run deterministic Node.js scripts' — with only minor coverage gaps (e.g., which commands exist).	4 / 5
Completeness	Clearly answers 'what' (persistent per-project memory that auto-loads, tracks git activity, writes to native memory) and 'when' via an explicit 'Use when...' clause with a concrete trigger phrase.	5 / 5
Trigger Term Quality	The 'Use when a project needs context to survive across Claude Code sessions instead of being re-explained each time' phrase is a natural trigger, but common synonyms like 'memory', 'remember project', or 'persist context' are missing.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (per-project session memory for Claude Code) with distinct triggers, so overlap with other skills is minimal.	5 / 5
	Total	18 / 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: skills/ck/SKILL.md
Commit: 06c5e11

Reviewed: 3 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.