CtrlK
BlogDocsLog inGet started
Tessl Logo

codex-prompting

Use this skill for any request to trigger, coordinate, or craft prompts for Codex. Use when user says 'send to codex', 'use codex', 'prompt codex', 'ask codex', 'delegate to codex', 'run in codex', or asks for a Codex-first execution handoff.

64

Quality

80%

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/codex-prompting/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.

A concise, well-sectioned instruction skill that assumes Claude's intelligence, but it stays largely at the level of principles and checklists without executable examples or explicit validation checkpoints, and it fails to navigate to the bundled reference guide it ships with.

Suggestions

Add a concrete example Codex handoff prompt (or a minimal `codex exec` command sequence) so the guidance is copy-paste ready, not just abstract direction.

Introduce an explicit validate-then-fix feedback loop in the 'Verification and report' section (e.g., run checks -> if failures, fix and re-run -> only then report) to give the workflow real checkpoints.

Link the bundled reference from the body (e.g., 'For extended prompting patterns, see [codex-prompting-guide.md](references/codex-prompting-guide.md)') so the 33KB guide is discoverable instead of orphaned.

DimensionReasoningScore

Conciseness

Lean and free of padding about what Codex is, but a few sentences are abstract aphorisms ('A clear action request authorizes the necessary work') rather than lean direct instruction, so not every token earns its place.

4 / 5

Actionability

Provides some concrete checklists ('State the outcome, repository and relevant paths, constraints, write authority, and evidence') and a CLI pointer ('Read codex exec --help'), but lacks an example handoff prompt or concrete command sequence, leaving key executable details missing.

3 / 5

Workflow Clarity

Section headers imply a model/harness -> execution -> verification sequence, but there are no explicit numbered steps or validation checkpoints, and verification is described as 'run checks appropriate to the change' without a validate-fix-retry loop.

3 / 5

Progressive Disclosure

The body is well-organized into sections, but a 33KB reference file (references/codex-prompting-guide.md) and assets/ exist and are never referenced or linked from the body, leaving bundle navigation unsignaled.

3 / 5

Total

13

/

20

Passed

Description

95%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, well-targeted description that clearly states capability and trigger conditions with comprehensive natural-language phrases. The only weakness is that the named actions lean slightly abstract ('coordinate', 'trigger') rather than enumerating fully concrete operations.

DimensionReasoningScore

Specificity

Names several concrete actions ('trigger, coordinate, or craft prompts for Codex', 'execution handoff') but terms like 'coordinate' and 'trigger' stay somewhat abstract rather than fully concrete operations, leaving minor coverage gaps.

4 / 5

Completeness

Explicitly answers both 'what' (trigger/coordinate/craft prompts for Codex, execution handoff) and 'when' with concrete trigger phrases in a clear 'Use when...' clause.

5 / 5

Trigger Term Quality

Comprehensive natural-phrase coverage with many synonyms users would actually say ('send to codex', 'use codex', 'prompt codex', 'ask codex', 'delegate to codex', 'run in codex', 'Codex-first execution handoff').

5 / 5

Distinctiveness Conflict Risk

Clear niche (Codex prompting/handoff) tied to a named external tool with distinct triggers, giving minimal conflict risk with other skills.

5 / 5

Total

19

/

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
joelhooks/joelclaw
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.