ship-task

Continuation of the SDLC from a ready task file: implement → review → commit → push. No planning — the task file must already exist with `## Solution` filled. Self-contained — execute the inlined steps directly, do NOT invoke other skills via the Skill tool.

Quality

64%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/flowai/skills/ship-task/SKILL.md

Quality

Content

70%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 content is a strong, gated, highly actionable workflow with explicit validation checkpoints and feedback loops, but it is monolithic and somewhat repetitive, inlining everything rather than splitting detailed reference material across one-level-deep files.

Suggestions

Extract the large per-phase detail (e.g. the JiT mutant-synthesis and CI-await poll-loop specifications) into a one-level-deep reference file and signpost it from the body to improve progressive disclosure.

De-duplicate the inter-phase gate definitions — state each gate once in the Rules section and reference it, rather than restating it in the Overview and again at each gate heading.

Trim repeated boilerplate (e.g. re-stating the manifest-detection ladder in both Implement and Review phases) to improve conciseness.

Dimension	Reasoning	Score
Conciseness	The body is dense and largely free of basic-concept padding, but at ~480 lines it restates the inter-phase gates three times (Overview, Rules, and the per-gate sections) and could be tightened; it is mostly efficient with some unnecessary repetition.	3 / 5
Actionability	It provides concrete, mostly copy-paste-ready git commands (e.g. `git rev-parse --abbrev-ref --symbolic-full-name @{u}`, `GIT_PAGER=cat git push`) and a precise manifest-detection ladder, with only minor gaps keeping it just below fully executable.	4 / 5
Workflow Clarity	Four phases are strictly ordered with three explicit validation gates, hard STOP conditions, and clear feedback loops (RED→GREEN→REFACTOR→CHECK, validate-then-proceed, poll loop with iteration cap), matching the explicit-checkpoints anchor.	5 / 5
Progressive Disclosure	It is a single monolithic SKILL.md with no bundle files and no external references — all four phases are inlined — so while sections are well-organized, content that could live in separate reference files is inlined and navigation depth is flat rather than signposted.	3 / 5
	Total	15 / 20 Passed

Description

58%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 concrete and well-scoped to a distinct SDLC-continuation niche, but it lacks an explicit "Use when..." trigger clause and natural user-facing trigger phrases, which holds completeness and trigger quality at the mid range.

Suggestions

Add an explicit "Use when..." clause, e.g. "Use when a task file already exists with ## Solution filled and the user wants to ship it through implement → review → commit → push in one go."

Include the natural phrases users actually say (e.g. "ship this task", "commit and push my changes") to improve trigger-term coverage.

Keep the third-person voice but lead with the triggering situation so the "when" is as explicit as the "what".

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions — "implement → review → commit → push" — with only minor gaps in coverage, fitting the "lists several specific actions" anchor.	4 / 5
Completeness	The "what" is clear (continue the SDLC: implement/review/commit/push from a ready task file) but "when" is only weakly implied via "Continuation ... from a ready task file" with no explicit "Use when..." clause, which caps completeness at 3 per the guideline.	3 / 5
Trigger Term Quality	Has relevant keywords (SDLC, commit, push, ready task file) but misses the natural phrasings a user would actually say (e.g. "ship this", "commit and push my changes"), so coverage is partial.	3 / 5
Distinctiveness Conflict Risk	It carves a clear niche (SDLC continuation composite, task file with Solution already filled) that is mostly distinct from sibling skills, with only minor overlap risk against a generic full-cycle ship skill.	4 / 5
	Total	14 / 20 Passed

Validation

87%

Warnings & errors only

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

Validation — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 3 missing	Warning

	Total	14 / 16 Passed

Repository: korchasa/flowai-plugins
Path: plugins/flowai/skills/ship-task/SKILL.md
Commit: b4ba256

Reviewed: ~21 hours ago

Table of Contents

Discovery Implementation Validation

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.