ac-session-manager

Session lifecycle management for autonomous coding. Use when starting sessions, resuming work, detecting session type (init vs continue), or managing auto-continuation between sessions.

Quality

70%

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 ./skills/ac-session-manager/SKILL.md

Quality

Content

57%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 action-rich with clear lifecycle sequencing, but it suffers from redundant diagrammatic restatements, a missing validation feedback loop for batch auto-continuation, and broken bundle references where 6 of 7 cited files do not exist while their content is inlined in the body.

Suggestions

Remove redundant representations: keep one of the ASCII lifecycle diagram, the Session Types table, or the Detection Logic code, and drop the others to improve conciseness.

Add an explicit validation checkpoint to the auto-continue/multi-session flow (e.g., verify state and feature_list integrity before starting the next session) to lift workflow clarity above the batch-operation cap.

Create the missing referenced files (references/SESSION-LIFECYCLE.md, references/PROMPTS.md, references/MULTI-SESSION.md and scripts/session_detector.py, auto_continue.py, prompts.py) or remove the dead References/Scripts links and move the inlined prompts and config into real bundle files.

Dimension	Reasoning	Score
Conciseness	The body is mostly concrete code, but the same lifecycle is represented three times (30-line ASCII diagram, Session Types table, Detection Logic code) plus a redundant Multi-Session Flow diagram, which is unnecessary duplication; it is not a 4 because tightening these duplicates would meaningfully cut tokens.	3 / 5
Actionability	Provides copy-paste-style Python for detect_type, create, run_initializer, run_continuation, configure_auto_continue, shutdown, and a SessionConfig dataclass, but several examples reference missing scripts (session_detector.py, auto_continue.py, prompts.py), leaving minor gaps that keep it below fully-executable 5.	4 / 5
Workflow Clarity	The four-phase lifecycle (detect, create, run, end) is clearly sequenced, but auto-continuation is a batch operation and the multi-session flow lacks explicit validation/verification checkpoints with fix-and-retry feedback, triggering the destructive/batch cap at 3.	3 / 5
Progressive Disclosure	Section structure is reasonable (Quick Start, Lifecycle, Operations, References, Scripts) and references are signaled, but only 1 of 7 referenced bundle files actually exists (references/ is absent; 3 of 4 scripts missing) and full prompts/config that belong in separate files are inlined, matching the structured-but-could-be-better-organized 3 anchor rather than the 4 anchor.	3 / 5
	Total	13 / 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.

A strong, third-person description that explicitly pairs a clear 'what' with a concrete multi-trigger 'Use when' clause. It is held back from the top tier only by slightly generic action verbs and the inherent breadth of the 'session' term across sibling skills.

Dimension	Reasoning	Score
Specificity	Names the domain ('Session lifecycle management for autonomous coding') and lists several concrete actions ('starting sessions, resuming work, detecting session type (init vs continue)... managing auto-continuation'), though 'managing' is slightly generic, keeping it just below the comprehensive 5 anchor.	4 / 5
Completeness	It explicitly answers both 'what' ('Session lifecycle management for autonomous coding') and 'when' via a concrete 'Use when...' clause enumerating trigger scenarios, matching the clearly-explicit-both anchor; it is not the 4 anchor because the 'when' is specific and multi-triggered rather than merely adequate.	5 / 5
Trigger Term Quality	Natural phrases a user would say ('starting sessions', 'resuming work', 'detecting session type', 'auto-continuation') give good coverage, but it lacks synonyms and shorthand variants a user might actually type, so it sits below the comprehensive 5 anchor.	4 / 5
Distinctiveness Conflict Risk	The 'autonomous coding' qualifier carves a clear niche and the session triggers are distinct, but 'session' is a broad term and this skill sits in a family of sibling ac-* skills, leaving minor overlap risk rather than the minimal-conflict 5 anchor.	4 / 5
	Total	17 / 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: 6 missing	Warning

	Total	14 / 16 Passed

Repository: fernandezbaptiste/Skrillz
Path: skills/ac-session-manager/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.