push

User-invoked safe git push. Confirms before setting first-time upstream and before pushing a diverged main/master, and refuses force pushes without explicit authorization. Self-contained — execute the inlined steps directly.

Quality

72%

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/push/SKILL.md

Quality

Content

75%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 safety workflow with concrete commands and real validation checkpoints, but it suffers from rules/instructions duplication, some rationale padding in the CI-await section, and a malformed terminal step. Fixing the structural defect and de-duplicating would lift conciseness and workflow clarity.

Suggestions

Repair the malformed Step 7 ("7. **7. **TOTAL STOP**") and stop inlining Step 7's final-report text inside Step 6's absent-CI branch so the terminal step is unambiguous.

De-duplicate the protected-branch divergence gate between Rule 4 and Step 3 — state the rule once and have Step 3 reference it rather than re-explaining.

Trim rationale asides in the CI-await section (provider-lag observations, ~2x sizing notes) to tighten conciseness.

Dimension	Reasoning	Score
Conciseness	Mostly efficient but noticeably redundant — the protected-branch divergence gate appears both in Rule 4 and Step 3 with near-identical wording, and the CI-await section includes rationale asides (e.g. "sized at ~2x the slowest realistic provider lag, observed ~30 s for GitLab pipelines") that could be trimmed.	3 / 5
Actionability	Fully executable: concrete git commands throughout ("git rev-parse --abbrev-ref HEAD", "git rev-list --left-right --count HEAD...@{u}", "GIT_PAGER=cat git push [--set-upstream origin <CURRENT>]") with specific exit codes and exact user-facing messages covering the common cases.	5 / 5
Workflow Clarity	Clear 7-step sequence with explicit validation (post-push @{u == HEAD check in Step 5, divergence gates in Step 3) and feedback loops (CI red -> investigate handoff, non-fast-forward -> STOP), but Step 7 is malformed ("7. 7. TOTAL STOP**") and Step 6's absent-CI branch confusingly inlines Step 7's content.	4 / 5
Progressive Disclosure	Well-organized into clearly tagged sections (<context>, <rules>, <step_by_step>, <verification>) with no external references needed by design ("Self-contained"), but at ~118 lines it is a long monolithic document that could arguably split the lengthy CI-await detail into a reference file.	4 / 5
	Total	16 / 20 Passed

Description

70%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 specific, distinct description with concrete safety actions and natural trigger terms, but it lacks an explicit 'when to use' clause, leaving the use-case trigger only weakly implied. Tightening completeness with a concrete trigger phrase would raise it.

Suggestions

Add an explicit 'Use when the user asks to push a branch to its remote' clause to satisfy the 'when' half of completeness.

Optionally mention the post-push verification and CI-await behavior so the safety contract reads as fully comprehensive.

Dimension	Reasoning	Score
Specificity	Names concrete actions — "Confirms before setting first-time upstream", "refuses force pushes without explicit authorization", "pushing a diverged main/master" — listing several specific behaviors with minor gaps (no mention of post-push verification or CI await).	4 / 5
Completeness	The 'what' is clear and comprehensive, but there is no explicit 'Use when...' trigger clause — only the weakly implied "User-invoked" — so per the rubric a missing trigger clause caps completeness at 3.	3 / 5
Trigger Term Quality	Uses natural developer terms ("git push", "force push", "upstream", "diverged main/master") that users would actually say, with good coverage though a few natural variants like "publish a branch" are absent.	4 / 5
Distinctiveness Conflict Risk	Carves a clear niche as a safety-contract git push (force refusal, upstream confirmation, protected-branch divergence gate) with minimal overlap risk against other git skills.	5 / 5
	Total	16 / 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: 1 missing	Warning

	Total	14 / 16 Passed

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