CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

write-pr

Use when writing or editing a pull-request title and body in this repository — at prep-pr Step 8, when a later commit or a review makes the body untrue, or for any pull request that closes public issues or private tracker findings. Covers the title, the six sections and what each holds — the change's impact first — the Closes and Part of lines and what a public body may say about a tracker issue, owner and deploy actions, an honest test plan, the faults agent-written bodies fall into, and the command that opens or edits it.

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

81%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.

An exceptionally actionable, well-sequenced workflow skill: every step has concrete commands, worked examples, and executable verification with feedback loops. Its weakness is token weight — the ~330-line body restates several rules (notably the tracker-fix rules) across sections and inlines material that could be consolidated or moved to a reference.

Suggestions

State the tracker-fix rules once (e.g., in Step 4) and cross-reference them from Step 3, Summary, the faults table and the checklist, instead of restating "say what the code now does, never the defect" in each place.

Move the faults table or the extended Issues rules 1–8 into a reference file (like references/examples.md) so SKILL.md carries only the rules needed on every pass.

Trim duplicated phrasing such as "never build or test the base just for this section", which appears in both the Step 2 facts table and Step 4's Impact guidance.

DimensionReasoningScore

Conciseness

Nearly every line carries non-inferable repository policy (no explanations of concepts Claude already knows), but at ~330 lines it could be tightened: the tracker-fix rules are restated across Step 3, Impact, Summary, the faults table and the checklist, and "never build or test the base just for this section" appears in both the Step 2 table and Step 4's Impact.

3 / 5

Actionability

Fully executable throughout: the exact six-heading skeleton, copy-paste `gh api` commands for opening, PATCHing and state-checking the pull request, executable grep/awk validation checks, a complete GraphQL closing-issues query, and worked markdown examples for every section.

5 / 5

Workflow Clarity

Steps 1–6 are clearly sequenced with explicit validation checkpoints: a pre-send checklist of runnable checks, a post-open closingIssuesReferences verification with a fix-PATCH-recheck loop, and a merged/closed guard that halts edits to a merged pull request.

5 / 5

Progressive Disclosure

Good structure with clearly headed steps and one well-signaled, one-level-deep reference (`references/examples.md`, verified to exist and to be the promised before/after worked body). The bulk of the material — Issues rules 1–8, Decisions rules, the faults table — is inlined in SKILL.md rather than split out, which is defensible for an always-needed policy but leaves minor organization gaps.

4 / 5

Total

17

/

20

Passed

Description

87%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: it explicitly answers both what the skill covers and when to use it, with multiple concrete trigger scenarios and a specific inventory of the skill's scope. The only weakness is phrasing that lists topics rather than actions and omits common synonyms like "PR".

DimensionReasoningScore

Specificity

Enumerates several specific, concrete items — "the six sections and what each holds", "the Closes and Part of lines", "owner and deploy actions, an honest test plan", "the command that opens or edits it" — but it is a coverage inventory ("Covers…") with some abstract entries ("the faults agent-written bodies fall into") rather than a list of parallel concrete actions, leaving minor gaps.

4 / 5

Completeness

Both halves are explicit: the "what" is the full "Covers the title, the six sections… the faults… and the command that opens or edits it" inventory, and the "when" gives three concrete trigger scenarios (prep-pr Step 8, a later commit or review making the body untrue, any PR closing public issues or tracker findings).

5 / 5

Trigger Term Quality

Natural trigger phrases are present — "Use when writing or editing a pull-request title and body", "when a later commit or a review makes the body untrue", "for any pull request that closes public issues" — but common synonyms such as "PR" or "open a pull request" as a user phrase are missing.

4 / 5

Distinctiveness Conflict Risk

The niche is distinct — scoped to "a pull-request title and body in this repository" and anchored to repo-specific triggers ("prep-pr Step 8", "private tracker findings"), with issue-writing explicitly owned by a sibling skill — so conflict risk with other skills is minimal.

5 / 5

Total

18

/

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

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

15

/

16

Passed

Repository

englishstreetventures/osn

Path

.claude/skills/write-pr/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.