project-session-manager

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

Quality

59%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Medium

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./skills/project-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 body is highly actionable with concrete, mostly copy-paste-ready commands and clear per-subcommand sequences, but it is a long monolith that inlines content (Jira, teleport, implementation protocol) which belongs in separate reference files, and its destructive paths lack validation checkpoints. Duplication between the Configuration, Initialization, Quick Start, and Teleport sections also inflates token cost.

Suggestions

Split provider-specific and auxiliary detail into one-level-deep reference files (e.g. references/jira.md, references/teleport.md) and keep SKILL.md as an overview with clearly signaled links.

Add validation before destructive operations: check for uncommitted/merged work before `git worktree remove --force` in the kill and cleanup paths, and report what would be lost.

Deduplicate the repeated projects.json examples (Configuration vs Initialization) and the overlapping Quick Start / Teleport usage blocks to cut token cost.

Dimension	Reasoning	Score
Conciseness	Mostly concrete commands and config with no concept explanations Claude already knows, but noticeably tightenable: the projects.json config is duplicated (Configuration and Initialization sections), the Teleport section repeats the Quick Start block, and the Jira section repeats near-identical alias JSON twice. Not anchor 4 because the duplication is more than minor trimming.	3 / 5
Actionability	Concrete executable bash, JSON config schemas, tmux commands, and comparison tables cover the common cases well. Minor gaps only: 'Update sessions registry' is just a comment, and fix/feature hand-wave steps as 'similar to review'. Not anchor 5 because a few steps lack copy-paste-ready commands.	4 / 5
Workflow Clarity	Each subcommand has a clear numbered sequence and there is an error-handling table, but `kill` runs `git worktree remove --force` — a destructive operation — with no validation for uncommitted changes, and the rubric caps destructive/batch workflows without validation at 3. Not anchor 4 because the checkpoint gap affects a destructive path.	3 / 5
Progressive Disclosure	The file is well-sectioned with clear headers and an internal anchor link, but it is a ~590-line monolith with no reference files at all — Jira provider docs, teleport docs, and the implementation protocol each clearly belong in separate one-level-deep references. Not anchor 4 because essentially all detail is inlined rather than split.	3 / 5
	Total	13 / 20 Passed

Description

61%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 is concise and names a distinct niche (worktrees, tmux, issues/PRs/features), but it describes what the skill is rather than what it does, and provides no explicit trigger guidance. Adding an action-oriented verb list and a "Use when..." clause would lift specificity and completeness.

Suggestions

Add a 'Use when...' clause with concrete triggers, e.g. 'Use when the user wants to work on an issue, PR, or feature in an isolated worktree, or mentions parallel sessions, tmux, or git worktrees.'

Replace the static noun phrase with explicit actions, e.g. 'Creates git worktrees for issues, PRs, and features, manages tmux sessions, and attaches Claude Code to them.'

Include natural synonyms such as 'git worktree', 'parallel development', and 'session' to widen trigger coverage.

Dimension	Reasoning	Score
Specificity	Names concrete mechanisms ("worktree", "tmux sessions") and scope ("issues, PRs, and features"), but the only action is the generic "manager" — no explicit verbs like create, manage, or review. Not anchor 4 because several specific actions are not listed; not anchor 2 because the domain and artifacts are concrete rather than generic.	3 / 5
Completeness	Has a clear "what" ("worktree-first dev environment manager ... with optional tmux sessions") but no "Use when..." clause or equivalent explicit trigger guidance, which the rubric caps at 3. Not anchor 4 because "when" is only weakly implied via "for issues, PRs, and features".	3 / 5
Trigger Term Quality	Good natural keywords users would say — "worktree", "issues", "PRs", "tmux sessions", "features" — but common variations like "git worktree", "parallel development", or "session management" are missing. Not anchor 5 because synonym coverage is not comprehensive; not anchor 3 because the present terms are natural, not jargon-only.	4 / 5
Distinctiveness Conflict Risk	"Worktree-first dev environment manager ... with optional tmux sessions" carves a fairly distinct niche with low conflict risk against generic skills. Not anchor 5 because "dev environment manager" is broad enough to overlap with general workflow/environment skills.	4 / 5
	Total	14 / 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
skill_md_line_count	SKILL.md is long (593 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
Path: skills/project-session-manager/SKILL.md
Commit: dc7ba1d

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.