project-session-manager

Worktree-first dev environment manager for issues, PRs, and features with optional tmux sessions

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Content

65%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is highly actionable with concrete commands and clear step sequencing, but it is long, repeats patterns across subcommands, and keeps everything inline without validation checkpoints on destructive operations.

Suggestions

Factor the shared review/fix/feature step sequence (resolve, worktree, metadata, tmux, launch) into one block and reference it, instead of repeating it three times.

Add validation checkpoints to destructive/batch workflows: verify gh output succeeded before cloning, and confirm a session is merged/closed before removing its worktree in cleanup.

Move the Jira configuration and the full implementation protocol into reference files (e.g. JIRA.md, PROTOCOL.md) and link to them from the overview to improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is mostly actionable rather than explaining concepts Claude knows, but at ~585 lines it repeats near-identical step blocks across review/fix/feature subcommands and duplicates config examples, so it could be tightened.	2 / 3
Actionability	It provides concrete, copy-paste-ready bash commands and JSON snippets throughout (gh/git/tmux invocations, session metadata, config files), giving fully executable guidance.	3 / 3
Workflow Clarity	Subcommand steps are clearly numbered and sequenced, but destructive/batch operations like 'kill' and 'cleanup' lack explicit validation or verification checkpoints, capping workflow clarity at 2.	2 / 3
Progressive Disclosure	Sections are well organized with headers and tables, but the skill is a monolithic single file with no references despite the large implementation protocol and Jira setup that could be split out.	2 / 3
	Total	9 / 12 Passed

Description

57%

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, in third person, and identifies a distinctive niche, but it lacks an explicit 'Use when...' trigger and only implies its concrete actions rather than listing them.

Suggestions

Add an explicit trigger clause, e.g. 'Use when starting parallel work on issues, PRs, or features that needs an isolated git worktree, optionally with a tmux session.'

List the concrete actions (create, review, fix, feature, attach, kill, cleanup) so specificity reaches the top anchor.

Include a few natural user phrasings ('review a PR', 'start a feature in its own worktree') to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	The phrase 'Worktree-first dev environment manager for issues, PRs, and features with optional tmux sessions' names the domain and objects managed but does not enumerate concrete actions (create/attach/kill/cleanup), so it is not comprehensive.	2 / 3
Completeness	The 'what' is clearly stated (worktree-first dev environment manager), but there is no explicit 'Use when...' trigger clause, so per the judging guidelines completeness is capped at 2.	2 / 3
Trigger Term Quality	It surfaces relevant natural terms like 'worktree', 'PRs', 'issues', 'features', and 'tmux sessions', but misses common variations a user might say (e.g. 'review a PR', 'isolate work', 'parallel branches').	2 / 3
Distinctiveness Conflict Risk	'Worktree-first dev environment manager ... with optional tmux sessions' carves out a clear, narrow niche that is unlikely to trigger for unrelated skills.	3 / 3
	Total	9 / 12 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
skill_md_line_count	SKILL.md is long (586 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: Yeachan-Heo/oh-my-claudecode
Commit: 6c59219

Reviewed: about 4 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.