CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

71

Quality

88%

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

The canonical home for this skill is ce-commit-push-pr in EveryInc/compound-engineering-plugin

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 exemplary orchestration-style skill body: dense, declarative rules with no filler, a checkpointed five-step workflow, and disciplined progressive disclosure into real reference files loaded exactly when needed. The only notable gap is that a handful of mechanics live solely in the references, so the body alone is not fully self-sufficient for execution.

DimensionReasoningScore

Conciseness

The body is lean rule-based orchestration with zero explanation of git/PR concepts Claude already knows; every sentence carries a directive ("Pass the body via `--body-file <path>`, never stdin — `gh` exits 0 with an empty body"). It matches 'assumes Claude's competence; every token earns its place'; the small restatement of two context.md rules is intentional surfacing, not padding.

5 / 5

Actionability

Concrete, executable guidance is frequent: exact command semantics ("`git add -A`", "`--body-file <path>`", "`gh pr edit`", "`-R`" targeting on forks), exit-code-to-control-flow rules, and explicit stop conditions. Score 4 rather than 5 because the body itself contains few complete command sequences — the bulk of mechanics is deliberately deferred to reference files, leaving minor gaps when read alone.

4 / 5

Workflow Clarity

A clear Steps 1-5 sequence with explicit validation checkpoints: "Re-verify branch, remote, and PR state right before each consequential action", the pre-create PR-presence re-check with exit-code handling (exit-0 `[]` creates, non-zero blocks), the project publishing gate before external writes, and error-recovery paths (resolve auth/connectivity, stop on ambiguous match). This matches the anchor with feedback loops and checkpointed risky operations, so the destructive-operation cap does not apply.

5 / 5

Progressive Disclosure

The body is a well-structured overview that defers detail to eight real, clearly signaled one-level-deep references, each loaded at its point of use ("Read `references/context.md` before Step 1", "load `references/stack-submit.md` before Step 3"). The single chained file (`references/gh-stack-cli.md` reached via stack-submit.md) is a clearly signaled, stack-mode-only exception, so the structure still fits the anchor for well-organized one-level-deep references.

5 / 5

Total

19

/

20

Passed

Description

83%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, concise description in third person that pairs a three-action 'what' with an explicit 'Use when' clause covering both the full workflow and description-only flows. Its only weaknesses are minor: trigger vocabulary omits a few common phrasings and it does not hint at the skill's broader capabilities.

Suggestions

Add one or two more natural trigger phrasings to the 'Use when' clause, e.g. 'when the user asks to commit and push' or 'write a PR description for these changes'.

Optionally acknowledge the stack/multi-PR variant (e.g. 'supports multi-PR stacks on request') so stack requests surface this skill at description-matching time.

DimensionReasoningScore

Specificity

"Commit, push, and open a PR" lists three concrete domain-specific actions, matching the 'several specific actions; minor gaps in coverage' anchor. It stays at 4 rather than 5 because coverage is not comprehensive (stack mode, description updates, and babysit follow-on handled by the body are absent from the description) and 3 would understate the action list.

4 / 5

Completeness

The 'what' is explicit ("Commit, push, and open a PR") and the 'when' is explicit with concrete trigger phrases ("Use when asked to ship/open a PR, or for PR-description-only flows like writing, rewriting, or describing a PR body"), matching the anchor that requires both with concrete triggers. Not 4, because the 'when' clause is specific and enumerates user phrasings rather than being generic.

5 / 5

Trigger Term Quality

Natural phrases users would say are present — "asked to ship/open a PR", "writing, rewriting, or describing a PR body" — giving good synonym coverage for the description-only flow. A few common natural terms are missing ("commit message", "pull request" spelled out, "review my PR"), so it fits anchor 4 rather than the comprehensive synonym/extension coverage of anchor 5.

4 / 5

Distinctiveness Conflict Risk

The PR-ship/PR-description niche is well carved out ("open a PR", "PR body") and distinct from generic git helpers. Minor overlap risk remains with closely related skills such as commit-message generators or PR review skills, so anchor 4 fits better than the minimal-conflict anchor 5.

4 / 5

Total

17

/

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
crdant/compound-engineering-plugin
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.