CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

bash-hygiene

Review, create, and validate Bash scripts when shell work needs strict mode, quoting safety, portability, or interpreter-compatible behavior.

Quality

74%

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/agent-ops/bash-hygiene/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

63%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.

A well-organized, terse runbook with strong progressive disclosure (all referenced bundle files are real and one level deep) and a sequenced workflow with an explicit fail-fast validation loop. Its main weaknesses are actionability — it names categories and tools but includes no executable patterns or exact commands — and low-signal governance sections that dilute conciseness.

Suggestions

Add copy-paste-ready patterns for the core fixes the skill prescribes, e.g. `set -euo pipefail`, quoted expansions `"$var"`, and array-based invocation `cmd=("$@")`, so the quoting/strict-mode guidance is executable rather than named.

Replace the generic validation bullet with exact commands such as `shellcheck script.sh` and `bash -n script.sh` (plus the repo wrapper invocation) so the fail-fast gate has a concrete executable step.

Trim the Philosophy and Anti-Patterns sections, which largely restate Constraints and Avoid in abstract terms, to remove low-signal governance bullets.

DimensionReasoningScore

Conciseness

Bullets are terse, but the Philosophy and Anti-Patterns sections restate Constraints/Avoid in abstract, low-signal terms ("Keep the skill focused on the decision and workflow the user actually requested", "Hiding uncertainty or missing evidence"), so the body could be meaningfully tightened. Not anchor 4 because the unnecessary text goes beyond minor trimming; not anchor 2 because there is no padded explanation of concepts Claude already knows.

3 / 5

Actionability

Some concrete guidance exists ("Run shellcheck or the nearest repo validation", "Prefer argument arrays and explicit paths over string-built commands", a named checklist of "strict mode, quoting, arrays, traps, paths, and temporary files"), but there are no executable examples or exact commands — key details for a bash-hygiene skill are missing. Not anchor 4 since the guidance is not mostly executable; above anchor 2 because specific tools and patterns are named.

3 / 5

Workflow Clarity

The Workflow section gives a clear sequence (scope, identify shell/wrappers, check, apply patterns, validate, report) and Validation adds an explicit fail-fast feedback loop ("stop at first failed gate; do not proceed until it is fixed and rerun"). Not anchor 5 because steps are generic bullets without specific commands and validation is not a concrete executable step; validation is present, so the destructive-operation cap does not apply.

4 / 5

Progressive Disclosure

The body is a well-sectioned overview with a dedicated Progressive Disclosure section whose referenced bundle files (references/contract.yaml, references/evals.yaml, references/task-profile.json) all exist, are one level deep, and each carry a stated purpose (machine-readable contract, benchmark/quality gates, evaluator thresholds), matching the clear-overview anchor.

5 / 5

Total

15

/

20

Passed

Description

75%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 concise, third-person description that clearly states what the skill does and when to use it, with natural domain keywords. It sits just below top marks on each dimension due to minor gaps: missing synonyms like 'shell scripts'/'shellcheck' and condition-based rather than utterance-based trigger phrasing.

DimensionReasoningScore

Specificity

Lists three concrete actions ("Review, create, and validate Bash scripts") plus four named concern areas ("strict mode, quoting safety, portability, or interpreter-compatible behavior"), matching the 'several specific actions; minor gaps' anchor. It falls short of anchor 5 because coverage is not comprehensive (e.g., no mention of debugging or what validation involves) and is well above anchor 3's 1-2 actions.

4 / 5

Completeness

It answers both questions: the 'what' is "Review, create, and validate Bash scripts" and the 'when' is the explicit clause "when shell work needs strict mode, quoting safety, portability, or interpreter-compatible behavior". Not anchor 5 because the trigger is condition-based rather than concrete user-utterance phrases, but clearly above anchor 3 since explicit trigger guidance is present.

4 / 5

Trigger Term Quality

"Bash scripts", "strict mode", "quoting safety", and "portability" are terms users naturally say when needing this skill, giving good keyword coverage. It misses anchor 5 because common variations like "shell scripts", "shellcheck", or the ".sh" extension are absent.

4 / 5

Distinctiveness Conflict Risk

The bash-hygiene niche (strict mode, quoting, interpreter compatibility) is mostly distinct with domain-specific triggers. Not anchor 5 because "Review... Bash scripts" could overlap a generic code-review skill for ordinary script review requests.

4 / 5

Total

16

/

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

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository

jscraik/Agent-Skills

Path

Skills/agent-ops/bash-hygiene/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.