CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

ship-it

Take a PR from review to merged — run the repo's code-review skill on it in a loop (review, fix, re-review) until nothing is left to fix, applying ALL fixes on the PR branch, wait for CI green, then squash-merge. Use when asked to "ship it", "ship PR

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

88%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.

A highly actionable, well-sequenced merge workflow: every step carries executable commands, repo-specific gotchas, validation checkpoints, and feedback loops, with real attention to safety (blocker rule, shared-machine hygiene, worktree restoration). The only deductions are minor — a few trimmable restatements and tangential sections, and small organization gaps in an otherwise appropriately single-file structure.

Suggestions

Trim restated framing — e.g. drop 'Goal: the PR merged with every code-review finding fixed and CI green.' (it repeats the frontmatter description) and tighten section 0b's figure instructions to the trigger conditions plus the SHA-pinning rule, moving the how-to detail to the referenced figure skill.

Fold the trailing 'Note on gh pr edit' into the step where the description is actually edited (step 0b), or a short 'Repo quirks' section, so the file ends on the required step-7 report/cleanup checklist.

Reorder so the blocker rule (step 0) precedes the figure guidance (0b), or renumber 0b after step 1 — as written, tangential description-figure guidance interrupts the load-in/check-out/review/fix/CI/merge flow.

DimensionReasoningScore

Conciseness

The body is dense with non-obvious, environment-specific facts (pg0 instance naming, the silent CONFLICTING-PR CI gap, the gh pr edit GraphQL bug, the shared stash stack) with essentially no padding, but a few minor trims exist: the frontmatter goal is restated ('Goal: the PR merged with every code-review finding fixed and CI green') and section 0b spends ~12 lines on a tangential figure nicety. This fits anchor 4 ('efficient; minor instances of over-explanation that could be trimmed') better than 5 ('every token earns its place').

4 / 5

Actionability

Guidance is copy-paste ready throughout — exact gh/git/jq/pg0/lsof commands (e.g. the headSha-gated 'gh run list' snippet, 'git push origin HEAD:ci/pr-<N>-verify', 'pg0 drop --name <name> -f') — and the specific examples cover the common cases: maintainer vs. fork PR, conflicting PR, missing CI run, flaky jobs. Fully executable with placeholders appropriate to the parameterized inputs.

5 / 5

Workflow Clarity

Steps 0–7 are explicitly sequenced with validation checkpoints (gate on the CI run for the pushed head SHA, judge per job, restore the worktree before merging, verify PIDs with 'ps -p' before killing) and genuine feedback loops (fix → push → back to step 5; review → fix → re-review until zero findings; 'gh run rerun --failed' for flakes). Despite being a destructive/batch workflow, validation is thoroughly present, so the workflow-clarity cap does not apply.

5 / 5

Progressive Disclosure

A single-file, well-sectioned workflow with clear headers and no bundle files to reference (its references to the code-review and figure skills are repo-external, not nested bundle paths). Structure is good, but at ~180 lines a few pieces of inline detail — the trailing 'Note on gh pr edit' section and step 0b's placement before the blocker rule — could be better integrated or split, matching anchor 4 ('good structure; minor organization gaps') rather than the fully clean split of anchor 5.

4 / 5

Total

18

/

20

Passed

Description

100%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.

An exemplary description: third-person, concise, and specific, with a complete what/when pairing and trigger phrases quoted as the literal words a user would say. No dimension shows a gap against the top anchors.

DimensionReasoningScore

Specificity

The description enumerates the full pipeline as concrete actions — 'run the repo's code-review skill on it in a loop (review, fix, re-review)', 'applying ALL fixes on the PR branch', 'wait for CI green', 'then squash-merge' — which matches the comprehensive multi-action anchor; the 4 anchor requires minor gaps, and there are none across the workflow's scope.

5 / 5

Completeness

It explicitly answers both questions: 'what' (loop the code-review skill until zero findings, apply all fixes, wait for CI green, squash-merge) and 'when' ('Use when asked to "ship it", "ship PR #N", or "review, fix and merge" a PR') with concrete trigger phrases, matching the top anchor.

5 / 5

Trigger Term Quality

Triggers are literal user utterances — 'ship it', 'ship PR #N', 'review, fix and merge' — exactly what a user would naturally say when they need this skill, alongside domain keywords (PR, merged, CI). Not 4, because no common natural phrasing for invoking this end-to-end task is missing.

5 / 5

Distinctiveness Conflict Risk

It carves a clear niche — taking a PR from review all the way to merge — and explicitly positions itself as wrapping the repo's code-review skill rather than duplicating it; its triggers ('ship it') do not plausibly fire for a plain review or merge request, so conflict risk is minimal.

5 / 5

Total

20

/

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

vectorize-io/hindsight

Path

.claude/skills/ship-it/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.