CtrlK
BlogDocsLog inGet started
Tessl Logo

bash-pro

Master of defensive Bash scripting for production automation, CI/CD pipelines, and system utilities. Expert in safe, portable, and testable shell scripts.

46

Quality

49%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/bash-pro/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

50%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 a dense, expert-level catalog of defensive Bash practices with strong concrete code snippets, but it is monolithic and repetitive: the same guidance recurs across four or five overlapping sections, and ~250 lines of tool/version reference material are inlined in SKILL.md rather than split into reference files. The four-step workflow lacks intermediate validation checkpoints and error-recovery loops.

Suggestions

Consolidate the overlapping sections (Focus Areas, Approach, Safety & Security Patterns, Advanced Techniques, Performance Optimization, Common Pitfalls) into one non-redundant set — mapfile, version checks, and safe `rm -rf --` each currently appear 2-4 times.

Move the exhaustive catalogs (Essential Tools, Modern Bash Features 5.x, Dependency Management, Security Scanning & Hardening, References & Further Reading) into a references/ file (e.g., TOOLS.md) and keep a short, signaled pointer in SKILL.md.

Add explicit validation checkpoints and a feedback loop to the Instructions workflow, e.g., '4. Run `shellcheck *.sh` and `bats test/`; fix findings and re-run until clean before delivering.'

Fix the Example section — it contains only a user request quote with no actual example output, which reads as a truncated placeholder.

DimensionReasoningScore

Conciseness

The ~300-line body is noticeably verbose with substantial duplication: 'Focus Areas' restates 'Approach', `rm -rf --` safe-deletion appears in both Approach and Safety & Security Patterns, `mapfile`/`readarray` is covered in Approach, Performance Optimization, Advanced Techniques, and Modern Bash Features, and Bash version checks appear in three sections. This matches 'noticeably verbose; several unnecessary explanations or padded sections'. It is not a 1 because individual bullets are terse and it avoids explaining basic concepts Claude already knows.

2 / 5

Actionability

Most guidance is concrete and copy-paste ready: `set -Eeuo pipefail`, `SCRIPT_DIR="$(cd -- "$(dirname -- "${BASH_SOURCE[0]}")" && pwd -P)"`, `readarray -d '' files < <(find . -print0)`, `timeout 30s curl ...`, `jq -n --arg key "$value" '{key: $key}'`, and a CI workflow `shellcheck *.sh && shfmt -d *.sh && bats test/`. It is not a 5 because a meaningful minority of bullets are abstract directives with no executable form ('Sanitize user input', 'Test scripts on all target platforms', 'Log security-relevant operations').

4 / 5

Workflow Clarity

The Instructions section gives a rough 4-step sequence (define inputs/failure modes → strict mode and argument parsing → core logic → tests and linting), but validation appears only as a terminal step with no checkpoints between steps and no feedback loop (e.g., what to do when ShellCheck or Bats fails). This matches 'steps listed but validation gaps; sequence present but checkpoints missing or implicit'. It is not a 4 because most checkpoints are absent, not minor.

3 / 5

Progressive Disclosure

The body has good section structure but inlines ~250 lines of reference material that belongs in separate files — exhaustive tool catalogs (Essential Tools), per-version Bash 5.x feature notes, Dependency Management, and Security Scanning lists — with no bundle files present to offload them. This matches 'some structure... content that should be separate is inline'. It is not a 2 because section headers make it navigable, and external web links are clearly organized by category.

3 / 5

Total

12

/

20

Passed

Description

48%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 identifies a distinct domain (defensive Bash scripting) with some natural trigger terms, but reads as a persona blurb ('Master of', 'Expert in') rather than a statement of concrete capabilities, and it lacks any 'Use when...' trigger guidance. It is serviceable but below the quality of the good examples, which state specific actions plus explicit usage triggers.

Suggestions

Replace persona phrasing ('Master of', 'Expert in') with concrete third-person actions, e.g., 'Writes, reviews, and hardens Bash scripts for production automation, CI/CD pipelines, and system utilities, with strict-mode error handling, safe argument parsing, and ShellCheck/Bats testing.'

Add an explicit trigger clause: 'Use when writing, reviewing, or debugging Bash/shell scripts, CI/CD pipeline steps, or ops automation — or when the user mentions bash, shell scripting, .sh files, or ShellCheck.'

Include common synonyms and file extensions (bash, sh, shell script, .sh) to improve trigger term coverage from 3 to 5.

DimensionReasoningScore

Specificity

The description names the domain ("defensive Bash scripting for production automation, CI/CD pipelines, and system utilities") but uses persona language ("Master of", "Expert in") with qualities ("safe, portable, and testable") rather than concrete actions — no verbs describing what the skill actually does, matching the 'names the domain but actions are minimal or generic' anchor. It is not a 3 because there are no 1-2 discrete concrete actions (e.g., 'writes', 'reviews', 'hardens') stated at all.

2 / 5

Completeness

The 'what' is reasonably clear (defensive Bash scripting for production automation, CI/CD, and system utilities), but there is no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines. It is not a 4 because the 'when' is entirely absent rather than just imprecise.

3 / 5

Trigger Term Quality

Includes genuinely natural terms users would say — "Bash", "shell scripts", "CI/CD", "automation" — but misses common variations like "bash script", "shell scripting", "sh", or "script". This matches 'some relevant keywords but missing common variations or synonyms'; it is above a 2 (terms are domain-specific, not generic like 'works with files') but below a 4 because everyday phrasings users would actually type are absent.

3 / 5

Distinctiveness Conflict Risk

Bash/shell scripting with CI/CD and system-utility framing is a clear, distinct niche with minimal overlap risk against non-shell skills, matching 'mostly distinct; minor overlap risk'. It is not a 5 because "production automation" and "system utilities" are broad enough to overlap with general automation/DevOps skills, and no explicit trigger phrases sharpen the boundary.

4 / 5

Total

12

/

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.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
sickn33/agentic-awesome-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.