CtrlK
BlogDocsLog inGet started
Tessl Logo

claude-code-bash-patterns

Claude Code Bash tool patterns with hooks, automation, git workflows. Use for PreToolUse hooks, command chaining, CLI orchestration, custom commands, or encountering bash permissions, command failures, security guards, hook configurations.

76

1.07x
Quality

73%

Does it follow best practices?

Impact

72%

1.07x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/claude-code-bash-patterns/skills/claude-code-bash-patterns/SKILL.md
SKILL.md
Quality
Evals
Security

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 dense with concrete, executable bash/hook examples and clear reference navigation, but it is weakened by redundancy, basic-concept padding, missing validation checkpoints on destructive workflows, and broken/orphaned bundle references (templates/ paths that don't exist, undocumented scripts/).

Suggestions

Conciseness: remove the 'ls -la' Quick Start example, consolidate the commit/deploy snippets repeated across 'Git Workflows', 'Common Use Cases', and 'Examples', and trim the Always/Never list entries that restate basic bash Claude already knows.

Workflow clarity: add explicit validation checkpoints to destructive/batch workflows — e.g. a force-push or rm -rf step with a verify-then-proceed gate and a fix-and-retry loop — so risky operations have feedback loops.

Progressive disclosure: either create the referenced templates/ files (custom-command-template.md, settings.json, .envrc.example, github-workflow.yml, dangerous-commands.json) or remove the broken references, and add 'Load ... when:' guidance for the three orphaned scripts/ files (bash-audit-logger.sh, dangerous-command-guard.py, package-manager-enforcer.sh).

DimensionReasoningScore

Conciseness

Mostly efficient code but padded in places: the Quick Start 'ls -la', an Always/Never list rehashing basic bash Claude already knows, and the same commit/deploy chain repeated across Git Workflows, Common Use Cases, and Examples.

3 / 5

Actionability

Mostly executable, copy-paste-ready code (full hook scripts, git/gh commands, settings.json), with minor gaps such as the abstract 'Message with multiple Bash tool calls in parallel' and placeholder hosts like api.example.com.

4 / 5

Workflow Clarity

Sequences are present (Five Core Patterns with 'Use when', CI/CD and git pipelines), but destructive/batch operations like rm -rf, force-push, and multi-repo updates lack explicit validate-before-proceed checkpoints, capping this dimension at 3.

3 / 5

Progressive Disclosure

references/ files are real and well-signaled via 'Load ... when:' sections, but the body references a non-existent templates/ directory (and 6 missing template files) and never references the 3 real scripts/ files — broken paths and orphaned bundles go beyond minor organization gaps.

3 / 5

Total

13

/

20

Passed

Description

88%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.

A strong, third-person description that explicitly covers both what the skill does and when to use it, with concrete Claude-Code-specific trigger terms. It is comprehensive on capabilities and largely distinct, with only minor keyword/overlap gaps.

DimensionReasoningScore

Specificity

Lists multiple concrete capabilities — 'hooks, automation, git workflows', 'PreToolUse hooks, command chaining, CLI orchestration, custom commands' — giving comprehensive coverage of the domain rather than 1-2 actions.

5 / 5

Completeness

Explicitly states what ('Claude Code Bash tool patterns with hooks, automation, git workflows') and when via a concrete 'Use for ...' clause listing trigger scenarios, matching the both-what-and-when anchor.

5 / 5

Trigger Term Quality

Good natural-term coverage including Claude-Code-specific phrases ('PreToolUse hooks', 'custom commands', 'bash permissions', 'command failures'); a few natural synonyms (e.g. '&&', 'scripts') and file extensions are absent, keeping it just below comprehensive.

4 / 5

Distinctiveness Conflict Risk

Scoped to a clear Claude Code Bash niche with distinct triggers (PreToolUse hooks, hook configurations), but 'git workflows' and 'command chaining' carry minor overlap with generic bash/git skills.

4 / 5

Total

18

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_field

'metadata' should map string keys to string values

Warning

Total

15

/

16

Passed

Repository
secondsky/claude-skills
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.