ac-state-tracker

State persistence for autonomous coding. Use when saving progress, loading state, tracking features, managing checkpoints, or persisting data across sessions.

Quality

80%

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

65%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 highly actionable with accurate, executable code, but suffers from duplicated Quick Start/Operations sections, missing validation feedback loops around destructive checkpoint restoration, and four non-existent referenced bundle files that break progressive disclosure.

Suggestions

Collapse the duplicated Quick Start and Operations sections into one set of code examples to remove redundant initialize/save/update_feature blocks.

Add an explicit validate→fix→retry step around restore_checkpoint (and save), e.g. verify feature_list.json loads and git state is clean before proceeding.

Create the referenced bundle files (references/STATE-SCHEMA.md, references/FEATURE-LIFECYCLE.md, and scripts/feature_manager.py, checkpoint_store.py, progress_logger.py) or remove the broken references.

Dimension	Reasoning	Score
Conciseness	Content is mostly code and schemas rather than padded prose, but the Quick Start and Operations sections duplicate the same initialize/save/update_feature code, adding noticeable redundancy beyond the minor over-explanation tolerated at score 4.	3 / 5
Actionability	Every operation (update_feature, create_checkpoint, restore_checkpoint, log_activity, save_handoff, get_progress) is shown as copy-paste-ready async code whose signatures match the real state_tracker.py, covering the common cases with concrete examples.	5 / 5
Workflow Clarity	Operations are numbered 1–7 in a clear sequence, but checkpoint restore mutates feature_list.json and git state (destructive) with no validate→fix→retry feedback loop, capping workflow clarity at 3 per the destructive-operations guideline.	3 / 5
Progressive Disclosure	Structure and one-level-deep references are clearly signaled in dedicated References/Scripts sections, but 4 of the 5 referenced files (STATE-SCHEMA.md, FEATURE-LIFECYCLE.md, feature_manager.py, checkpoint_store.py, progress_logger.py) do not exist in the bundle, so the navigation the body promises is broken.	3 / 5
	Total	14 / 20 Passed

Description

96%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, well-formed description that clearly states what the skill does and when to use it with concrete, natural trigger phrases. The only weakness is slight breadth in 'persisting data across sessions' that leaves minor overlap risk with sibling session/config skills.

Dimension	Reasoning	Score
Specificity	Names the domain ('State persistence for autonomous coding') and lists multiple concrete actions — 'saving progress, loading state, tracking features, managing checkpoints, or persisting data across sessions' — giving comprehensive coverage comparable to the score-5 anchor.	5 / 5
Completeness	Explicitly answers both 'what' (state persistence for autonomous coding) and 'when' via a concrete 'Use when...' clause enumerating trigger phrases, matching the score-5 anchor exactly.	5 / 5
Trigger Term Quality	Includes natural phrases a user would actually say ('saving progress', 'loading state', 'tracking features', 'checkpoints') with good synonym coverage; no file-format extension applies to this non-file skill.	5 / 5
Distinctiveness Conflict Risk	The 'state persistence for autonomous coding' niche is mostly distinct with specific triggers, but 'persisting data across sessions' is broad enough to risk minor overlap with related AC session/config skills rather than the minimal-conflict bar of score 5.	4 / 5
	Total	19 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 5 missing	Warning

	Total	14 / 16 Passed

Repository: fernandezbaptiste/Skrillz
Path: skills/ac-state-tracker/SKILL.md
Commit: 93ed392

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.