CtrlK
BlogDocsLog inGet started
Tessl Logo

github-pr-description

Generate and create pull request descriptions automatically using GitHub CLI. Use when the user asks to create a PR, generate a PR description, make a pull request, or submit changes for review. Analyzes git diff and commit history to create comprehensive, meaningful PR descriptions that explain what changed, why it matters, and how to test it.

65

Quality

82%

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

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.

The workflow is well sequenced with concrete commands and a useful description template, but the skill is a monolithic ~350-line file with no progressive disclosure: five full examples and duplicated anti-pattern guidance are inlined. Trimming the redundant lists, moving examples to a references file, and fixing the empty bash block in Step 5 would lift the weakest dimensions.

Suggestions

Move the five full example PR descriptions into a references/examples.md file and keep one or two condensed examples inline in SKILL.md, linking to the rest.

De-duplicate the anti-pattern guidance: 'What to Avoid' in the Description Guidelines and 'Anti-Patterns to Avoid' in Notes repeat the same four items — keep a single list.

Make Step 5 fully executable: replace the comment-only bash block with the actual write action (e.g., a concrete file-creation instruction) and add error handling for a failed `gh pr create`.

DimensionReasoningScore

Conciseness

The workflow and template sections are efficient, but the body carries five full multi-section example PR descriptions (~180 lines) where two or three would convey the pattern, and the anti-pattern list is stated twice — "Empty descriptions or just issue links", "Placeholder text like 'Fixes #(issue)'", "File-by-file breakdowns" appear in both 'What to Avoid' and 'Anti-Patterns to Avoid'. This is noticeably tighter than the verbose anchor but has real padding, fitting 'mostly efficient but could be tightened' rather than 'efficient with only minor trimming'.

3 / 5

Actionability

Guidance is mostly executable: concrete git commands ("git log origin/main..HEAD --stat", "gh pr create --title ... --body-file .forge/FORGE_PR_DESCRIPTION.md"), a concrete description template, and worked examples. It is not a 5 because Step 5 contains a bash block that is only a comment ("# Write the generated description to .forge/FORGE_PR_DESCRIPTION.md") with no actual command, and the write is described only in prose.

4 / 5

Workflow Clarity

The six steps are clearly sequenced with a prerequisite checkpoint (verify branch is not main and has commits ahead, with explicit handling when there is nothing to create a PR for) and a final confirmation step. It misses a 5 because there is no feedback loop if `gh pr create` fails and no verification that the PR was actually created before confirming to the user.

4 / 5

Progressive Disclosure

There are no bundle files (references/, scripts/, assets/ are absent), so everything — including five full example descriptions that clearly belong in an examples reference file — is inlined in a ~350-line SKILL.md. Section structure and headers are good, which keeps it above the 'minimal structure / inlined content' anchor at 2, but substantial content that should be split into separate files is inline, fitting the middle anchor rather than the well-split anchors at 4-5.

3 / 5

Total

14

/

20

Passed

Description

92%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 description that clearly states both capabilities and explicit trigger conditions in third person. Concrete actions (GitHub CLI, git diff, commit history analysis) and natural trigger phrasings are well covered; only minor synonyms like "open a PR" are absent.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions — "Generate and create pull request descriptions automatically using GitHub CLI", "Analyzes git diff and commit history", and descriptions that "explain what changed, why it matters, and how to test it" — giving comprehensive coverage of the skill's capabilities. It is not a 4 because there are no real gaps: generation, analysis inputs, and output qualities are all named specifically.

5 / 5

Completeness

It explicitly answers what ("Generate and create pull request descriptions... Analyzes git diff and commit history") and when ("Use when the user asks to create a PR, generate a PR description, make a pull request, or submit changes for review") with concrete trigger phrases, matching the top anchor exactly. Neither element is vague or merely implied, ruling out a 4.

5 / 5

Trigger Term Quality

Triggers "create a PR", "generate a PR description", "make a pull request", and "submit changes for review" are natural user phrasings with good synonym coverage (PR, pull request). It falls short of a 5 because common variations like "open a PR", "draft a PR", or "PR body" are missing.

4 / 5

Distinctiveness Conflict Risk

PR description generation is a clear niche with distinct triggers (PR/pull request creation and review submission), so conflict risk with other skills is minimal. The only conceivable overlap is with commit-message generation, but the explicit PR/pull-request framing keeps it distinguishable, so it fits the top anchor rather than the 'minor overlap' anchor at 4.

5 / 5

Total

19

/

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
tailcallhq/forgecode
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.