CtrlK
BlogDocsLog inGet started
Tessl Logo

codex-pr-body

Update the title and body of one or more pull requests.

53

Quality

59%

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/skills/codex-pr-body/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

65%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 well-structured, concise, and assumes Claude's competence, but the core editing command is missing and a destructive operation lacks an explicit verification checkpoint.

Suggestions

Provide the concrete editing command, e.g. `gh pr edit <number> --title "..." --body "..."` or `gh pr edit <number> --body-file`, so the central action is copy-paste ready.

Add an explicit verification step after editing, such as re-running `gh pr view` to confirm the title and body updated correctly and no images/content were lost.

Tighten the Sapling `sl sl` output example or trim a few discursive sentences to push conciseness toward a 5.

DimensionReasoningScore

Conciseness

The body is efficient with direct imperative guidance and assumes Claude knows Git/PR basics, with only minor padding (the illustrative `sl sl` output block and a few discursive sentences) keeping it just below a 5.

4 / 5

Actionability

Supporting commands like `gh pr view ... --json number` and `sl log ...` are executable, but the central action (editing the PR) is only described as "use `gh` to edit" without the concrete `gh pr edit` command or flags, a key missing detail.

3 / 5

Workflow Clarity

Sections are logically sequenced (determine PR, edit, contents, stacks, Sapling) with a soft preservation checkpoint, but overwriting a PR body is destructive with no explicit post-edit verification, capping this at 3 per the guidelines.

3 / 5

Progressive Disclosure

A compact, single-file skill with no bundle files and clear section headers (Determining the PR(s), PR Body Contents, Working with Stacks, Sapling); well-organized sections with no need for external references justify a 5.

5 / 5

Total

15

/

20

Passed

Description

53%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 concrete and domain-specific but lacks any trigger/when guidance and has thin keyword coverage, leaving it competent yet incomplete for skill selection.

Suggestions

Add a 'Use when...' clause with concrete triggers, e.g. 'Use when updating a PR title or body, rewriting a PR description, or refreshing PR details.'

Include natural synonyms users say, such as 'PR', 'PR description', and 'edit PR', to broaden trigger-term coverage.

Consider mentioning the scope of fields touched (title and body) alongside the multi-PR capability to sharpen distinctiveness.

DimensionReasoningScore

Specificity

Names the domain (pull requests) and two concrete actions ("Update the title and body") but is not comprehensive, matching the '1-2 concrete actions' anchor rather than the 'several specific actions' anchor above.

3 / 5

Completeness

Gives a clear 'what' (update PR title and body) with no 'when'/trigger clause, which per the guidelines caps completeness at 3.

3 / 5

Trigger Term Quality

Includes 'title', 'body', and 'pull requests' but omits common user phrasings like 'PR', 'edit PR', or 'rewrite PR body', fitting the 'some relevant keywords but missing common variations' anchor.

3 / 5

Distinctiveness Conflict Risk

The PR-editing niche is mostly distinct with only minor overlap risk against closely related PR skills, though the lack of explicit triggers keeps it below a 5.

4 / 5

Total

13

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
openai/codex
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.