CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

bin-scripts

Use when performing git operations, running Laravel/Composer commands, managing local dev sites, or killing processes on ports. Custom scripts in your PATH provide shortcuts for common workflows.

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./claude/skills/bin-scripts/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

83%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 an excellent lean reference catalog: token-efficient tables with copy-paste-ready usage for every script, plus genuinely novel details (session naming rules, cpx fallback order, excluded dangerous scripts). Its main weaknesses are the absence of validation guidance around destructive commands like git-abort and mux delete, and missed opportunity to move the lengthy tmux/solo detail into a reference file.

Suggestions

Add pre-flight validation guidance for destructive commands, e.g. "Before git abort, run git status and confirm no uncommitted work is needed" and "Before mux delete, run mux show to review panes that will be lost".

Move the detailed tmux/mux naming and registry rules and the solo configuration description into a references/ file (e.g. references/tmux.md), keeping a short table plus a clearly signaled link in SKILL.md.

For git-sync and git-tidy, note what "cleanup" and "merged/deleted on remote" will actually remove so their effects are verifiable before running.

DimensionReasoningScore

Conciseness

The body is pure reference tables pairing each script with usage syntax and purpose, with no explanations of concepts Claude already knows; even the dense mux paragraph conveys only novel, non-derivable information (session naming scheme, registry behavior, hook-based restore).

5 / 5

Actionability

Every entry gives copy-paste-ready usage examples ("git save file1 file2 \"message\"", "killport 3000", "mux tab <name> [path]") plus a one-line purpose, and supplementary details like cpx's fallback order and git-issue's env-var requirement are exactly the specifics needed to execute.

5 / 5

Workflow Clarity

As a command reference each entry's usage is unambiguous, but destructive operations ("git-abort ... Hard reset + clean untracked files (destructive)", "mux delete", "git-delete") carry only warning labels with no validation or verification guidance, which caps this dimension at 3 per the rubric's destructive-operation rule.

3 / 5

Progressive Disclosure

Sections are clearly organized by category with a useful "Not Documented" exclusion list, but at ~110 lines all content is inline (exceeding the under-50-line simple-skill exception) and self-contained detail blocks like the tmux/mux system and solo configuration could live in a one-level-deep reference file.

4 / 5

Total

17

/

20

Passed

Description

66%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 has an explicit and reasonably specific trigger clause, but its capability statement is generic ("shortcuts for common workflows") and it omits trigger terms for large parts of the skill, notably tmux session management, the solo process runner, and artisan. The broad "git operations" phrasing creates overlap risk with other git skills. It is serviceable but sits clearly below the exemplary anchors.

Suggestions

Replace the generic what-statement with concrete capabilities, e.g. "Provides git shortcut scripts (commit, amend, undo, rebase, history), runs artisan/Composer from any subdirectory, manages tmux sessions and local Caddy dev sites, and kills processes on ports."

Add trigger terms for the undocumented-but-active areas: users asking to "start a tmux session", "run the dev server / queue worker" (solo), or "run artisan migrate" should match this skill.

Narrow the git trigger from "performing git operations" to specific actions (committing, undoing commits, cleaning branches) to reduce conflict with other git-related skills.

DimensionReasoningScore

Specificity

The description names concrete domains ("git operations", "Laravel/Composer commands", "local dev sites") and one concrete action ("killing processes on ports"), but the core capability statement "provide shortcuts for common workflows" is generic and lists no specific script actions like committing, amending, or managing tmux sessions.

3 / 5

Completeness

It explicitly answers "when" with a "Use when..." clause listing four trigger scenarios, and states a "what" ("Custom scripts in your PATH provide shortcuts for common workflows"), but the "what" is vague and lacks concrete capability statements, so it falls short of the level-5 anchor.

4 / 5

Trigger Term Quality

Phrases like "running Laravel/Composer commands" and "killing processes on ports" are natural user triggers, but "performing git operations" is generic compared to what users actually say ("commit this", "rebase"), and major skill areas such as tmux session management (mux), the solo process runner, and artisan have no trigger terms at all.

4 / 5

Distinctiveness Conflict Risk

The Laravel/Caddy dev-site and kill-port niches are distinct, but "performing git operations" is very broad and would overlap with virtually any git-related skill, leaving meaningful conflict risk.

3 / 5

Total

14

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

joshmanders/dotfiles

Path

claude/skills/bin-scripts/SKILL.md

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.