branch-sync-and-push-safety

Use when changing local branch synchronization, custody recovery, post-review head binding, rebasing, or force-push safety.

Quality

53%

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 ./.agents/skills/branch-sync-and-push-safety/SKILL.md

Quality

Content

50%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 dense, concrete reference of safety invariants for branch sync and force-push, strong on specific internal detail but weak on sequenced workflow and file-level progressive disclosure. It would benefit from extracting the long invariant prose into a reference file and adding an explicit validation-gated workflow.

Suggestions

Extract the long relation-matrix / fail-safe prose into a reference file (e.g. references/recovery-rules.md) and keep SKILL.md as a concise overview pointing to it, improving progressive disclosure and conciseness.

Add an explicit numbered, validation-gated workflow for the destructive paths (verify remote head → recheck worktree/target/ancestry → CAS update-ref + read-tree → confirm) with checkpoints, to lift workflow_clarity above the destructive cap.

Tighten the dense paragraphs into bulletted invariants and trim redundant restatements of the same rules across sections to reduce token cost.

Dimension	Reasoning	Score
Conciseness	The body assumes Claude's competence (no basic git/PDF-concept padding) and packs genuine domain invariants, but the long dense paragraphs with embedded symbol and test names could be tightened considerably, matching 'mostly efficient but could be tightened' (3) rather than the lean anchor 5.	3 / 5
Actionability	Guidance is highly concrete — exact functions, refs (e.g. 'refs/no-mistakes/recover/<run>'), settings ('branch_sync_remote_timeout', 60s) and test names — but it is declarative invariants rather than executable steps or commands, fitting anchor 3 (concrete but incomplete/instructional).	3 / 5
Workflow Clarity	The skill governs destructive operations (force-push, reset, rebase) and describes implicit checks ('rechecks … immediately before apply', 'pins … before the worktree can be removed'), but there is no clean sequenced workflow with explicit validation checkpoints, so the destructive-operation cap holds it at 3.	3 / 5
Progressive Disclosure	Three bold section headers and explicit code-path pointers ('lives in the Recover doc comment in internal/branchsync/sync.go') give some structure, but no bundle files exist and a large dense inlined reference that could be split out remains in the body, matching anchor 3.	3 / 5
	Total	12 / 20 Passed

Description

57%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 has a clear, distinctive trigger niche and explicit 'when' guidance, but it never states what the skill actually does and leans on the generic verb 'changing'. Strengthening the 'what' and adding natural-term synonyms would raise completeness and trigger quality.

Suggestions

Add an explicit 'what' clause stating the action the skill performs (e.g., 'Guard and recover local branch state during pipeline sync, rebases, and force-pushes') before the 'Use when…' trigger.

Replace the generic verb 'changing' with concrete operations the skill governs (sync, reset, rebase, force-push, custody recovery) to improve specificity.

Add common synonyms users might say (e.g., 'force-push', 'rewrite history', 'recover unpublished commits') alongside the internal jargon to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	The description names several concrete domains ('local branch synchronization, custody recovery, post-review head binding, rebasing, or force-push safety') but the only action verb is the generic 'changing', so it falls between naming the domain (2) and listing concrete actions (3), landing at 3.	3 / 5
Completeness	An explicit 'Use when…' clause gives a clear 'when', but the 'what' (what action the skill performs) is only weakly implied by 'changing', never stated; this is above anchor 2 (only 'when', no 'what') but not the explicit what+when of anchor 4.	3 / 5
Trigger Term Quality	It includes natural operator terms like 'rebasing' and 'force-push' alongside internal jargon ('custody recovery', 'post-review head binding'); some relevant keywords are present but common synonyms/variations are missing, matching the anchor 3.	3 / 5
Distinctiveness Conflict Risk	The description carves a narrow, specific niche (guarded branch sync, custody recovery, head binding, force-push safety) with distinct triggers and minimal overlap risk, matching the anchor 5 example of a clear niche.	5 / 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
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning

	Total	14 / 16 Passed

Repository: kunchenguid/no-mistakes
Path: .agents/skills/branch-sync-and-push-safety/SKILL.md
Commit: 9a464c2

Reviewed: 1 day 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.