CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

pr-writer

Create pull requests following Sentry's engineering practices.

Quality

73%

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 ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/pr-writer/SKILL.md

The canonical home for this skill is pr-writer in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

82%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 strong, lean operational guide: concrete executable gh/git commands, a validation checkpoint for uncommitted changes, complete PR description templates with worked examples, and a distinct Sentry-specific conventions table. Its only weaknesses are minor padding in the Guidelines section, no error-recovery steps after PR creation, and an example section that could be tightened.

DimensionReasoningScore

Conciseness

The body is dominated by executable commands, a table, and template examples with almost no explanation of concepts Claude already knows; only minor trimming candidates exist (e.g. 'Smaller PRs get faster, better reviews' in Guidelines and some boilerplate Ensure bullets). Matches 'Efficient; minor instances of over-explanation that could be trimmed', not 5 because the three full example PR bodies and Guidelines section carry a little padding.

4 / 5

Actionability

Commands are fully executable — gh repo view for branch detection, git log/diff for analysis, a complete gh pr create invocation with heredoc body, title format patterns, an issue-reference syntax table, and copy-paste-ready example PR descriptions covering feature, fix, and refactor cases. Placeholders (BASE, PR_NUMBER) are explicitly resolved by preceding detection steps, matching 'Fully executable; copy-paste ready commands; specific examples cover the common cases'.

5 / 5

Workflow Clarity

A clear 4-step sequence (verify branch state → analyze changes → write description → create PR) with pre-flight checks ('git status --porcelain' for uncommitted changes, explicit Ensure bullets for branch state) matches 'Clear sequence with most checkpoints present; minor validation gaps'. Not 5 because there are no error-recovery/feedback steps (e.g. what to do if gh pr create fails or the branch is stale); not capped at 3 since draft PR creation is neither destructive nor batch.

4 / 5

Progressive Disclosure

No bundle files exist and the single-file body is well-organized into clearly headed sections (Prerequisites, Process, Examples, Issue References, Guidelines, Editing, References) with two clearly signaled external links — matching 'Good structure; most content is appropriately placed; references mostly clear; minor organization gaps'. Not 5 because at ~176 lines the three full PR examples and the secondary 'Editing Existing PRs' section could be split or tightened, and the skill is above the under-50-line simple-skill case.

4 / 5

Total

17

/

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 states a clear 'what' in third person with a distinct Sentry-specific niche, but it is a single short sentence with no 'when to use' trigger clause and only one concrete action. It would benefit from an explicit use-when clause and natural trigger variations like 'PR' and 'open a PR'.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user asks to create, open, or draft a pull request, or to write a PR description or title.'

Include natural trigger variations users actually say: 'PR', 'open a PR', 'draft PR', 'pull request description'.

Name 1-2 more concrete capabilities to broaden coverage, e.g. writing PR descriptions/titles following Sentry commit conventions and updating existing PRs via gh api.

DimensionReasoningScore

Specificity

"Create pull requests" names the domain and one concrete action, matching the 'Names domain and 1-2 concrete actions' anchor; 'following Sentry's engineering practices' is a style qualifier, not an additional action, so coverage is not comprehensive (not 4).

3 / 5

Completeness

The 'what' is clear (create PRs per Sentry practices) but there is no 'Use when...' clause or equivalent trigger guidance, capping completeness at 3 per the judging guidelines. Not 4 because 'when' is entirely absent rather than merely imprecise.

3 / 5

Trigger Term Quality

"pull requests" is a natural term users say, but common variations and synonyms are missing — 'PR', 'PRs', 'open a PR', 'draft PR' — matching 'Some relevant keywords but missing common variations or synonyms'. Not 4 because coverage is a single keyword phrase rather than good multi-term coverage.

3 / 5

Distinctiveness Conflict Risk

"following Sentry's engineering practices" gives the skill a clear niche that is mostly distinct from generic PR-creation or git skills, with only minor overlap risk — matching 'Mostly distinct; minor overlap risk with closely related skills'. Not 5 because the trigger phrase 'create pull requests' would still fire on any PR-creation request regardless of repository.

4 / 5

Total

13

/

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

administrakt0r/AI-Agents-Safe-Coding-Skills

Path

plugins/AI-Agents-Safe-Coding-Skills-claude/skills/pr-writer/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.