CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

ce-commit-push-pr

Commit, push, and open a PR. Use when asked to ship/open a PR, or for PR-description-only flows like writing, rewriting, or describing a PR body.

Quality

91%

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

92%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 well-engineered orchestration layer: lean rule-dense prose, explicit validation checkpoints around every external write, and a clean one-level reference structure where each file is read at a defined step. The only room for improvement is that executable command sequences are deferred to references rather than shown inline.

DimensionReasoningScore

Conciseness

The body is dense, rule-bearing prose with zero padding — no explanations of git/PR basics Claude already knows, every sentence carrying a directive (e.g., "Never use `git add -A` or `git add .`. Name files in both add and commit"). It matches 'lean and efficient; every token earns its place'.

5 / 5

Actionability

Concrete guidance throughout — exact flags (`--body-file <path>`, `-R`, `--head <owner>:<branch>`), exact exit-code semantics, exact config keys (`docs_root`, `auto_babysit`) — but the actual executable command sequences live in the reference files rather than the body, leaving minor gaps versus copy-paste-ready.

4 / 5

Workflow Clarity

Steps 1-5 are clearly sequenced with explicit validation checkpoints for the risky external writes: "Re-verify branch, remote, and PR state right before each consequential action", the pre-create PR re-check, the non-zero-exit-blocks rule, and the publishing gate. Error recovery paths are explicit ("If `ce-babysit-pr` cannot be loaded or started, stop and report it blocked"), matching the level-5 anchor with feedback loops.

5 / 5

Progressive Disclosure

All seven referenced files exist and are one level deep from SKILL.md, each loaded at a precise point with its purpose stated ("Read `references/context.md` before Step 1", "You MUST read `references/pr-description-writing.md`"). Orchestration stays in the body and mechanics are appropriately split into references; the single second-hop (`gh-stack-cli.md` via stack mode's `stack-submit.md`) is a well-signaled command appendix, not buried content.

5 / 5

Total

19

/

20

Passed

Description

88%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 crisp, trigger-rich description that states concrete capabilities and explicit use conditions in two sentences. Only minor gaps keep it from full marks: missing 'pull request' synonyms and some overlap risk with description-writing skills.

DimensionReasoningScore

Specificity

"Commit, push, and open a PR" plus "writing, rewriting, or describing a PR body" names multiple concrete actions covering the skill's full domain — shipping and PR-description flows. It is comprehensive for this niche, matching the level-5 anchor rather than 4, whose 'minor gaps in coverage' does not apply.

5 / 5

Completeness

The what ("Commit, push, and open a PR") and the when ("Use when asked to ship/open a PR, or for PR-description-only flows like writing, rewriting, or describing a PR body") are both explicit with concrete trigger phrases, exactly the level-5 anchor.

5 / 5

Trigger Term Quality

Natural triggers include "ship/open a PR", "PR description", "PR body", "writing, rewriting" — good keyword coverage. It falls short of 5 because common variants like the spelled-out "pull request", "submit", or "create a PR" are absent.

4 / 5

Distinctiveness Conflict Risk

The git shipping niche (commit, push, open PR) is distinct, but the explicit PR-description triggers overlap with dedicated PR-body/commit-message writing skills — a minor overlap risk with closely related skills, matching anchor 4 rather than 5's 'minimal conflict risk'.

4 / 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

frontmatter_unknown_keys

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

Warning

Total

15

/

16

Passed

Repository

EveryInc/compound-engineering-plugin

Path

skills/ce-commit-push-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.