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 identifies a specific niche (worktree-based development workflow) but is too terse and lacks explicit trigger guidance. It reads more like a tagline than a functional description, missing concrete actions and a 'Use when...' clause that would help Claude reliably select it from a pool of skills.
Suggestions
Add a 'Use when...' clause specifying triggers like 'when the user wants to work on an issue in a new worktree', 'set up a development environment for a PR', or 'manage tmux sessions for parallel development'.
List concrete actions such as 'Creates git worktrees for issues/PRs, sets up tmux sessions per worktree, switches between feature branches in isolated directories'.
Include natural keyword variations like 'git worktree', 'pull request', 'branch', 'workspace', 'parallel development' to improve trigger term coverage.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (dev environment management) and mentions specific concepts (worktrees, issues, PRs, features, tmux sessions), but doesn't list concrete actions like 'create worktree', 'open PR', or 'switch sessions'. | 2 / 3 |
Completeness | It partially answers 'what' (manages dev environment with worktrees, issues, PRs, tmux) but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. | 1 / 3 |
Trigger Term Quality | Includes relevant keywords like 'worktree', 'issues', 'PRs', 'features', and 'tmux', which users might naturally mention. However, it misses common variations like 'git worktree', 'pull request', 'branch', or 'workspace' and doesn't cover the full range of natural language triggers. | 2 / 3 |
Distinctiveness Conflict Risk | The 'worktree-first' framing and tmux mention provide some distinctiveness, but terms like 'issues', 'PRs', and 'features' are very broad and could overlap with general git workflow skills, PR review skills, or issue 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.
This skill is highly actionable with complete executable commands but suffers severely from verbosity and poor progressive disclosure. The entire implementation protocol for 8 subcommands, multiple provider configurations, and a separate teleport command are all crammed into a single file with no supporting bundle files. Repeated patterns across subcommands (tmux launch, claude startup, registry updates) inflate the token cost significantly without adding proportional value.
Suggestions
Extract the detailed implementation protocol for each subcommand into a separate IMPLEMENTATION.md or per-subcommand files, keeping only a concise summary table and key patterns in SKILL.md
Deduplicate the repeated tmux/claude launch pattern (appears in review, fix, and feature) into a single 'Common Session Setup' section referenced by each subcommand
Move Jira provider configuration and teleport command documentation into separate bundle files (PROVIDERS.md, TELEPORT.md) with one-line references from the main skill
Add explicit validation checkpoints to destructive operations: confirm before 'git worktree remove --force', verify worktree state before cleanup, validate session registry consistency
| 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 or scripts. Repeats patterns across subcommands (review/fix/feature all show nearly identical tmux/claude launch steps). Much of this is implementation code that Claude could generate from a concise spec. | 1 / 3 |
Actionability | Highly actionable with complete, executable bash commands and code blocks for every operation. Specific CLI invocations, JSON schemas, directory structures, and exact tmux commands are provided. Copy-paste ready throughout. | 3 / 3 |
Workflow Clarity | Steps are clearly numbered and sequenced for each subcommand, but validation checkpoints are largely missing. The 'kill' subcommand removes worktrees with --force but has no confirmation step. The cleanup command checks PR/issue state but doesn't validate worktree integrity before removal. Error handling is listed in a table but not integrated into the workflows as explicit checkpoints. | 2 / 3 |
Progressive Disclosure | Monolithic wall of text with no bundle files to offload content to. The entire implementation protocol for all 8 subcommands is inline, along with configuration examples, provider details, Jira setup, teleport command docs, and initialization scripts. This content desperately needs splitting into separate reference files (e.g., PROVIDERS.md, TELEPORT.md, implementation details per subcommand). | 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
3e94567
- 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.