CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

community-prs

Own pull requests from outside contributors to BuilderIO/agent-native: see who is waiting, take one, reply warmly, and land it with their credit intact. Use when triaging community PRs, handling one, or auditing how replies went.

Quality

94%

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

100%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.

This is a model instruction-style skill: dense with project-specific operational knowledge, fully executable commands, explicit validation gates on risky operations, and a clean one-level split between inline policy and the reply-template reference. No dimension showed anchor-level weaknesses.

DimensionReasoningScore

Conciseness

The body assumes Claude's competence (never explains git, gh, or PR mechanics) and every line carries project-specific policy — e.g., "An outside PR is one whose author is not a current BuilderIO org member and whose branch lives in a fork" — with time limits compressed into a table; no padded or trimmable passages found.

5 / 5

Actionability

Fully executable, copy-paste-ready commands throughout: exact pnpm invocations, `gh pr merge <n> --repo BuilderIO/agent-native --squash --match-head-commit <sha>`, `gh run rerun <run-id> --failed`, and the complete reviews-dismissal API call; the six paths each give concrete entry criteria and the reply templates live in references/replies.md.

5 / 5

Workflow Clarity

"Handle one PR" gives the numbered sequence, and validation checkpoints are explicit at every risky step — "A behavior fix needs a test that fails with the fix reverted. Check that it does", "Merge only when every required check passed on that head", "check every trailer has a real address" — with error-recovery loops ("If the push is refused anyway... rebuild"); the destructive-operation cap does not apply since merge and close are both explicitly gated.

5 / 5

Progressive Disclosure

A clearly sectioned overview with the one bundle reference well-signaled ("Drafts for each moment, and what to avoid: references/replies.md"), which exists and is one level deep; the template bulk is appropriately split into the reference file while operational policy stays inline, and navigation via section headers is easy.

5 / 5

Total

20

/

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: it names the domain, lists concrete actions across the full workflow, and gives an explicit "Use when" clause with natural trigger phrases. The only weakness is slightly thin synonym coverage (no "external contributor"/"fork" phrasing).

DimensionReasoningScore

Specificity

"see who is waiting, take one, reply warmly, and land it with their credit intact" plus "auditing how replies went" names multiple concrete actions covering every phase of the workflow (triage, claim, reply, land, audit), matching the comprehensive-coverage anchor; score 4 would require minor gaps, and no phase is missing.

5 / 5

Completeness

It explicitly answers what ("Own pull requests from outside contributors... take one, reply warmly, and land it with their credit intact") and when ("Use when triaging community PRs, handling one, or auditing how replies went") with concrete trigger phrases, matching the top anchor exactly.

5 / 5

Trigger Term Quality

Natural phrases a user would say are present ("triaging community PRs", "handling one", "auditing how replies went", "outside contributors", "pull requests"), but common synonyms like "external contributor" or "fork" are absent, so it fits the good-but-not-comprehensive keyword anchor rather than the 5.

4 / 5

Distinctiveness Conflict Risk

The niche is sharply drawn — outside/community contributor PRs to one named repo — so triggers are distinct even against the related review-prs skill; conflict risk is minimal.

5 / 5

Total

19

/

20

Passed

Validation

75%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 12 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

referenced_paths_exist

Referenced path issues: 2 missing

Warning

Total

12

/

16

Passed

Repository

BuilderIO/agent-native

Path

.agents/skills/community-prs/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.