CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

bash

How to use the shell successfully

Quality

57%

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 ./.claude/skills/bash/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

71%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 admirably brief and centers on one executable pattern, but it is undermined by a factually inverted explanation — "This makes sure the shell is polluted by any outside state" says the opposite of the evident intent (isolation from outside state) — and by the absence of a concrete example command. Structure is appropriate for a skill this small.

Suggestions

Fix the inverted explanation: "This makes sure the shell is NOT polluted by any outside state" — as written it instructs the opposite of the skill's purpose and is the single largest correctness issue.

Add one concrete executable example, e.g. `bash -c 'ls -la | wc -l'`, so the placeholder `bash -c 'command'` pattern has a copy-paste-ready instance.

Optionally note why isolation matters (e.g. avoiding inherited environment/variables) or when to prefer this form, so the guidance is complete without adding padding.

DimensionReasoningScore

Conciseness

The body is very lean — a one-line instruction, one three-line code block, and one explanatory sentence — with no padding or concepts Claude already knows, close to anchor 5. It falls to 4 because the final sentence "This makes sure the shell is polluted by any outside state" fails to earn its tokens: it is confusingly worded (apparently missing "not") and does not clearly communicate the rationale.

4 / 5

Actionability

The single pattern `bash -c 'command'` is executable syntax, but no real example command is given, and the accompanying rationale sentence is factually inverted ("makes sure the shell is polluted"), leaving the reader with misleading key details. This matches anchor 3 ("Some concrete guidance but incomplete... missing key details") better than 4, where the guidance would be reliable with only minor gaps.

3 / 5

Workflow Clarity

As a simple single-task skill (well under 50 lines) the single action — wrap commands in `bash -c` — is unambiguous, which per the simple-skill guideline can merit a 5. It drops to 4 because the incorrect closing sentence ("This makes sure the shell is polluted by any outside state") actively muddies what the procedure is meant to achieve, introducing a real gap in understanding rather than a purely stylistic one.

4 / 5

Progressive Disclosure

This is a ~5-line single-purpose skill with no external references needed; per the guideline "For skills under 50 lines with no need for external references, progressive disclosure can score 5 with just well-organized sections." Everything belongs inline and nothing is buried or nested, and no bundle files (references/scripts/assets) exist to misorganize.

5 / 5

Total

16

/

20

Passed

Description

25%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 is a vague title rather than a functional description: it names the shell domain but gives no concrete actions, no trigger terms beyond the single word "shell", and no "when to use" guidance. It closely resembles the bad example pattern ("Helps with documents") and needs both a capability list and an explicit trigger clause.

Suggestions

Add 2–3 concrete actions in third person, e.g. "Runs shell commands in an isolated bash shell, chains multi-step command sequences, and checks exit codes" instead of the generic "How to use the shell successfully".

Append an explicit trigger clause, e.g. "Use when the user asks to run, execute, or debug shell commands, or mentions bash, the terminal, or the command line" — the missing 'Use when...' clause currently caps completeness at 3.

Include natural synonyms users would say (bash, command line, terminal, run a command) so the skill is distinguishable from generic shell/scripting skills and triggers reliably.

DimensionReasoningScore

Specificity

The description only states "How to use the shell successfully" — it names the shell domain but lists zero concrete actions, matching the anchor "Names the domain but actions are minimal or generic" ("Processes PDF files"). Not a 3 because no concrete action is ever named; not a 1 because the domain is at least identified rather than purely abstract.

2 / 5

Completeness

The "what" is vague ("use the shell successfully" — use it to do what?) and there is no "when" clause at all, matching anchor 2 ("Has a vague 'what' and no 'when'"). The missing 'Use when...' guidance also caps this dimension at 3 per the guidelines, and it sits well below that cap.

2 / 5

Trigger Term Quality

"shell" is the single natural keyword; common variations and synonyms users actually say (bash, command line, terminal, run a command) are all missing. This fits anchor 2 ("One or two generic keywords; missing the natural phrases users say") better than anchor 3, which requires several relevant keywords.

2 / 5

Distinctiveness Conflict Risk

"How to use the shell successfully" is very broad and would overlap with any shell, bash, terminal, or scripting skill, matching anchor 2 ("Very broad; high overlap risk with many similar skills"). Not a 1 because it is not entirely generic — it does name the shell domain specifically.

2 / 5

Total

8

/

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

pgdogdev/pgdog

Path

.claude/skills/bash/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.