ship

Terminal full-cycle workflow: plan → implement → review → commit → push. Self-contained — execute the inlined steps directly, do NOT invoke other skills via the Skill tool.

Quality

68%

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/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.

A well-engineered, highly actionable composite workflow with excellent sequencing, gates, validation, and feedback loops. Its weaknesses are token cost (heavy jargon and length) and the absence of progressive disclosure — everything is inlined by design with no reference files.

Suggestions

Externalize the large Plan/Review phase detail (GODS format, SALP back-pointer rules, JiT subset) into reference files and keep SKILL.md as an overview pointing one level deep, which would lift progressive_disclosure and cut token cost.

Trim project-framework jargon where a shorter phrasing preserves the operational instruction, reducing conciseness load without losing determinism.

Add one concise copy-paste example block for the Plan-phase task-file skeleton so the procedural steps are as executable as the Push-phase commands.

Dimension	Reasoning	Score
Conciseness	The 569-line body is dense and largely operational rather than padded with concepts Claude already knows, but it carries heavy project-specific jargon (GODS, SALP, FR-IDs, JiT, ANC/REF tokens) and elaborate sub-rules that could be tightened or externalized. Not a 2 because sections are not padded fluff; not a 4 because the volume and jargon load exceed the "minor instances of over-explanation" bar.	3 / 5
Actionability	Concrete, executable commands throughout (e.g. `git rev-parse --abbrev-ref HEAD`, `git rev-list --left-right --count HEAD...@{u}`, `GIT_PAGER=cat git push [--set-upstream origin <CURRENT>]`, `export SHA=$(git rev-parse HEAD)`) with specific exit-code semantics for CI polling. Not a 5 because the Plan and Review phases are procedural/instructional and depend on reading AGENTS.md-resolved roles, leaving minor gaps versus copy-paste-ready coverage of all common cases.	4 / 5
Workflow Clarity	Five phases in strict order with four explicit gates, each with hard STOP conditions and validation checkpoints (project check exit 0, non-empty git status, Approve verdict, clean tree), plus feedback loops (RED→GREEN→REFACTOR→CHECK with revert-on-drift, CI poll/retry) and a final Verification checklist — fully matching the anchor for explicit validation, error-recovery loops, and checklists. The destructive/batch cap does not apply because validation is extensive, not missing.	5 / 5
Progressive Disclosure	Section structure is good (per-phase headings, gates, verification block), but the skill is explicitly monolithic ("All five phases are FULLY INLINED below") with no bundle files in references/scripts/assets, so 569 lines of detail that could live in separate files are inlined. Not a 2 because structure is present and intentional; not a 4 because almost nothing is offloaded to one-level-deep reference files.	3 / 5
	Total	15 / 20 Passed

Description

66%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 focused, concrete description of a terminal full-cycle shipping workflow with strong distinctiveness framing. Its main weakness is the missing explicit "Use when..." trigger clause, which caps completeness at 3 despite a clear statement of what the skill does.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user wants to ship a task end-to-end — plan, implement, review, commit, and push — in a single invocation."

Expand natural synonyms in the description (e.g., "deploy", "open a PR", "land changes") to broaden trigger-term coverage.

Tighten the self-containment note so it reads as a trigger signal (when to reach for this vs. a single-phase skill) rather than only a constraint.

Dimension	Reasoning	Score
Specificity	Names five concrete phases ("plan → implement → review → commit → push") plus a self-containment directive, giving several specific actions rather than vague abstraction. Not a 5 because the named items are high-level workflow phases rather than the granular, comprehensive operations the 5 anchor shows.	4 / 5
Completeness	The "what" is clear (terminal full-cycle ship workflow), but there is no explicit "Use when..." clause or equivalent trigger guidance — only an argument-hint, which the rubric caps at 3. Not a 4 because the "when" is only weakly implied rather than explicitly stated with concrete trigger phrases.	3 / 5
Trigger Term Quality	Includes natural developer terms ("ship", "plan", "review", "commit", "push", "full-cycle workflow") and the argument-hint "task description or issue URL"; good keyword coverage. Not a 5 because synonyms like "deploy", "PR", or "merge" and explicit file extensions are absent.	4 / 5
Distinctiveness Conflict Risk	The "Self-contained — do NOT invoke other skills" framing carves a distinct terminal-composite niche and directly addresses conflict risk. Not a 5 because the phase keywords (plan/review/commit/push) overlap with individual single-phase skills a user might otherwise invoke.	4 / 5
	Total	15 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (580 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 4 missing	Warning

	Total	13 / 16 Passed

Repository: korchasa/flowai-plugins
Path: plugins/flowai/skills/ship/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.