CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

accept-web-renderer-prs

Review and merge eligible web-renderer pull requests from alec-watts.

Quality

68%

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

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/accept-web-renderer-prs/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 admirably token-efficient and its acceptance criteria are unusually specific, but it reads as a flat checklist rather than an executable workflow: no commands for verifying criteria, no re-validation after fixes, and a machine-specific absolute path for the referenced pr-name skill. The limitations.mdx guidance is the strongest part, with a concrete file path and a clear keep/omit rule.

Suggestions

Add concrete verification commands (e.g. gh pr checks, gh pr view --json isDraft,reviewDecision, or git log for the last-hour push check) so each criterion is executable rather than merely stated.

Restructure into an ordered workflow with an explicit fix-then-revalidate loop: check criteria, push fixes if needed, re-run checks, and only merge when green again — the current batch-merge flow caps workflow clarity at 3 without it.

Replace the absolute path to the pr-name skill (/Users/jonathanburger/.codex/...) with a portable relative reference or inline the naming convention, and add a header for the criteria section so the two-part structure is navigable.

DimensionReasoningScore

Conciseness

The body is a lean checklist of criteria plus two tight paragraphs of editing guidance; it assumes Claude's competence, explains nothing it already knows, and every token earns its place.

5 / 5

Actionability

The criteria are individually checkable ("must be green", "must not be draft", "no pushes within last hour") and the limitations.mdx guidance names a concrete file and method, but there are no executable commands for verifying any criterion, and the "$pr-name" requirement points to an absolute path on one user's machine (/Users/jonathanburger/...) that cannot be followed elsewhere — concrete guidance with key details missing.

3 / 5

Workflow Clarity

The instruction "merge PRs which satisfy criteria" implies an evaluate-then-merge sequence and the criteria act as implicit gates, but the flow is loosely sequenced: remediation actions ("you may push fixes", "you may resolve merge conflicts") are interleaved with checks, and there is no re-validation loop (e.g. re-check green after pushing). As a batch/destructive merge workflow without explicit validation checkpoints, it is capped at 3.

3 / 5

Progressive Disclosure

At under 50 lines with no bundle files, the content itself needs no splitting, but structure is loose (a bare "criteria:" list with no header, one ## section) and its one reference to the pr-name skill is an external absolute path rather than a portable bundle-relative link — more than the 'minor organization gaps' of level 4.

3 / 5

Total

14

/

20

Passed

Description

57%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 concise, specific to a clear niche, and nearly conflict-proof, but it omits any explicit trigger guidance ('Use when...') and lacks keyword variations. It states what the skill does in two concrete actions without saying when Claude should reach for it.

Suggestions

Add an explicit trigger clause, e.g. 'Use when asked to review, triage, accept, or merge pull requests in the web-renderer repository from alec-watts.'

Include common user phrasings and variations such as 'PRs', 'PR review', and 'accept PRs' alongside 'pull requests' to broaden natural trigger coverage.

Briefly unpack 'eligible' (e.g. 'green, non-draft PRs with no outstanding reviews') so the scope of action is concrete rather than deferred entirely to the body.

DimensionReasoningScore

Specificity

"Review and merge eligible web-renderer pull requests" names the domain precisely and exactly two concrete actions (review, merge), matching the anchor for 1-2 concrete actions rather than the 'several specific actions' of level 4; the qualifier "eligible" gestures at criteria without stating them.

3 / 5

Completeness

The description clearly answers 'what' (review and merge web-renderer PRs from alec-watts) but has no 'Use when...' clause or equivalent trigger guidance, capping completeness at 3 per the judging guidelines; 'when' is at best weakly implied by the subject matter.

3 / 5

Trigger Term Quality

Natural terms like "review", "merge", and "pull requests" are present, but common variations users actually say ("PRs", "PR review", "accept") are missing, matching the 'some relevant keywords but missing common variations' anchor.

3 / 5

Distinctiveness Conflict Risk

"web-renderer pull requests from alec-watts" carves out an unmistakable niche tied to a specific repository and author, giving it distinct triggers and minimal conflict risk with any generic skill.

5 / 5

Total

14

/

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

relative_links

Relative link issues: 1 suspicious

Warning

Total

15

/

16

Passed

Repository

remotion-dev/remotion

Path

.agents/skills/accept-web-renderer-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.