project-session-manager
Worktree-first dev environment manager for issues, PRs, and features with optional tmux sessions
38
37%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/project-session-manager/SKILL.mdQuality
Discovery
32%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 conveys the general domain (git worktree-based development environment management) but lacks concrete action verbs and explicit trigger guidance. It reads more like a tagline than a functional description that would help Claude reliably select this skill from a large pool. The absence of a 'Use when...' clause is a significant gap.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user wants to create or manage git worktrees for issues, PRs, or feature branches, or when they mention tmux-based dev sessions.'
List specific concrete actions such as 'Creates git worktrees for GitHub issues, checks out PR branches in isolated worktrees, launches tmux sessions per worktree.'
Include natural trigger term variations like 'git worktree', 'pull request', 'feature branch', 'development environment', 'workspace setup' to improve keyword coverage.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (dev environment management) and mentions some concepts (worktrees, issues, PRs, features, tmux sessions), but doesn't list concrete actions like 'create worktree', 'switch branches', 'open PR', etc. | 2 / 3 |
Completeness | Describes what it does at a high level but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. Per rubric guidelines, missing 'Use when' caps completeness at 2, and the 'what' is also weak, so this scores a 1. | 1 / 3 |
Trigger Term Quality | Includes some relevant keywords like 'worktree', 'issues', 'PRs', 'features', and 'tmux', but misses common natural language variations users might say such as 'branch', 'git worktree', 'pull request', 'new feature branch', or 'development workflow'. | 2 / 3 |
Distinctiveness Conflict Risk | The 'worktree-first' qualifier and tmux mention add some distinctiveness, but 'issues, PRs, and features' is broad enough to overlap with general git workflow or project management skills. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
42%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill is highly actionable with concrete, executable commands for every operation, which is its primary strength. However, it is severely over-long and monolithic — inlining complete implementation details for 8+ subcommands, provider configuration, teleport docs, and initialization scripts all in one file. The lack of validation checkpoints in destructive operations (kill --force, cleanup) and the absence of any bundle files for progressive disclosure significantly weaken the overall quality.
Suggestions
Split implementation protocol details into a separate IMPLEMENTATION.md or per-subcommand reference files, keeping SKILL.md as a concise overview with command table and quick-start examples
Deduplicate repeated patterns (tmux session creation, claude launch, registry update) into a single 'Common Steps' section referenced by each subcommand instead of repeating inline
Add explicit validation/confirmation steps to destructive operations: 'kill' should verify worktree status before --force removal, 'cleanup' should support a --dry-run flag and show what will be removed before executing
Move Jira provider configuration and teleport command documentation into separate bundle files (PROVIDERS.md, TELEPORT.md) with one-level-deep references from the main skill
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~400+ lines. Massive amounts of inline implementation detail (full bash scripts for every subcommand, session metadata JSON templates, registry management) that could be in separate files. Repeats patterns across subcommands (review/fix/feature all show nearly identical tmux/claude launch steps). Much of this is boilerplate Claude could generate from a concise spec. | 1 / 3 |
Actionability | Highly actionable with concrete, executable bash commands and code blocks for every operation. Commands are copy-paste ready with specific CLI invocations, JSON structures, and exact file paths. The implementation protocol provides step-by-step executable guidance. | 3 / 3 |
Workflow Clarity | Steps are clearly sequenced for each subcommand, but validation checkpoints are largely missing. The 'kill' subcommand uses --force without confirming the worktree is clean. The 'cleanup' command performs destructive batch operations (removing worktrees, killing sessions) without explicit verification steps or dry-run options. Error handling is listed in a table but not integrated into the workflows themselves. | 2 / 3 |
Progressive Disclosure | Monolithic wall of text with no bundle files to offload content to. The full implementation protocol for every subcommand (review, fix, feature, list, attach, kill, cleanup, status) is inlined, along with Jira configuration, teleport command docs, and initialization scripts. This content desperately needs splitting into separate reference files (e.g., PROVIDERS.md, TELEPORT.md, IMPLEMENTATION.md). | 1 / 3 |
Total | 7 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 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 | 9 / 11 Passed | |
- Repository
- Yeachan-Heo/oh-my-claudecode
- Commit
679b418
- Reviewed
Table of Contents
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.