CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

pua-offline

PUA offline alias for Codex. Codex subcommand mapping for Claude Code /pua:offline style usage; invoke with $pua-offline.

Quality

75%

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 ./codex/pua-offline/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

80%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 tight, actionable instruction set for a simple config mutation, well-organized and token-efficient. Its main weakness is workflow clarity: a destructive config edit with only an implicit validation directive and no explicit verify checkpoint, which the rubric caps at 3.

Suggestions

Add an explicit validation step in the workflow, e.g., re-read ~/.pua/config.json after editing to confirm offline=true and feedback_frequency=0 are set and other fields are preserved.

Make the edit command copy-paste ready (e.g., a concrete jq/python snippet to patch the JSON while preserving unknown fields) to lift actionability to 5.

State the condition for reporting success explicitly (verify the config change before emitting [PUA OFFLINE]) so the validation loop is unambiguous.

DimensionReasoningScore

Conciseness

The body is lean and efficient — it gives the exact config fields and values (offline=true, feedback_frequency=0), the preservation rule, and the report token, with no padding or explanation of concepts Claude already knows, matching the 'lean and efficient; every token earns its place' anchor.

5 / 5

Actionability

It provides concrete, field-level guidance (specific keys, values, and the [PUA OFFLINE] output token) plus the file-preservation behavior, but lacks a literal copy-paste command, matching the 'mostly executable guidance with minor gaps' anchor rather than a fully copy-paste ready 5.

4 / 5

Workflow Clarity

The sequence (set config -> report) is present and there is a verification directive ('Do not claim completion without command/output evidence'), but there is no explicit validation checkpoint in the workflow, and because this mutates a config file destructively the rubric's feedback-loop cap limits workflow clarity to 3.

3 / 5

Progressive Disclosure

At under 50 lines with no bundle files and a clear heading plus two well-organized instruction paragraphs, this matches the simple-skill exception where progressive disclosure scores 5 with just well-organized sections.

5 / 5

Total

17

/

20

Passed

Description

57%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 clearly communicates a narrow, distinctive Codex-alias niche but lacks a 'Use when...' trigger clause and offers only thin capability coverage. It reads more as a technical alias registration than a user-facing skill description.

Suggestions

Add an explicit 'Use when...' clause stating when Claude should invoke this skill (e.g., when the user requests offline mode for the /pua:offline command).

Broaden the capability description beyond 'alias/mapping' to name the concrete effect (enabling offline mode by editing ~/.pua/config.json) so the 'what' is unambiguous.

Include natural trigger synonyms (e.g., 'pua offline', 'offline mode') alongside the command tokens to improve trigger coverage.

DimensionReasoningScore

Specificity

Names the domain (Codex alias) and a couple concrete actions ('subcommand mapping', 'invoke with $pua-offline'), but the capability coverage is thin and jargon-heavy rather than comprehensive, matching the 'names domain and 1-2 concrete actions' anchor.

3 / 5

Completeness

It gives a clear 'what' (offline alias / subcommand mapping for Codex) but has no 'Use when...' clause or equivalent trigger guidance, which caps completeness at 3 per the rubric guidelines.

3 / 5

Trigger Term Quality

It includes the natural invocation tokens users would type ('/pua:offline', '$pua-offline'), but offers no synonyms or variations beyond a single command alias, matching the 'some relevant keywords but missing common variations' anchor.

3 / 5

Distinctiveness Conflict Risk

It targets a very specific niche (a Codex alias for a particular Claude Code command) with distinct triggers ('/pua:offline', '$pua-offline'), giving it a clear niche with minimal conflict risk.

5 / 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

tanweai/pua

Path

codex/pua-offline/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.