data-loss-gate

Confirmation gate before any bulk delete, cleanup, or destructive operation that could result in data loss — shell-level (rm -rf, git rm, bulk sed) or brain-level (bulk forget, delete sweeps, purge-deleted, source removal, raw-SQL truncation). Presents a recoverability card and requires an explicit "yes" from the user before proceeding. Routing convention, not an operation-boundary enforcement.

Quality

88%

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

Quality

Content

92%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 high-quality, actionable gate skill with a copy-paste card template, explicit validation and feedback loops, and clean routing to sibling skills. Minor trimming of the motivational prose would improve token efficiency.

Suggestions

Tighten the "Why This Exists" anecdote and "No Exception Classes" section to their rule statements to reduce tokens while keeping the behavioral guidance.

Consider moving the full operation enumeration in "When This Fires" into a short reference list, keeping only the gate-critical categories inline.

Dimension	Reasoning	Score
Conciseness	Mostly efficient: every section has a purpose (card template, gate rules, logging, anti-patterns, dedup) with only minor justificational prose (the "Why This Exists" anecdote, "No Exception Classes") that could be trimmed without losing the instruction.	4 / 5
Actionability	Fully executable guidance: an exact copy-paste confirmation card template, an exact post-execution log entry format with concrete path (daily/notes/YYYY-MM-DD.md under ## Data Deletions), and specific commands (gbrain restore, gbrain purge-deleted) covering the common cases.	5 / 5
Workflow Clarity	Clear four-step sequence (STOP/inspect → card → wait for explicit yes → execute with logging) with explicit validation (inspect target before the card), a gate checkpoint (explicit "yes"), and feedback loops ("wait"/question → re-present; "no" → alternatives), plus the card itself as a checklist.	5 / 5
Progressive Disclosure	Well-organized into clear sections with one-level-deep, well-signaled cross-skill references (ask-user, maintain, test-before-bulk, brain-first) collected in a Dedup section; no nested references and the single-procedure content is appropriately self-contained with no bundle files needed.	5 / 5
	Total	19 / 20 Passed

Description

83%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, well-scoped description that clearly conveys both the gate's behavior and its trigger conditions in third person. Adding an explicit "Use when…" clause and surfacing a few more natural-language synonyms would round it out.

Suggestions

Add an explicit "Use when…" clause (e.g., "Use before any bulk delete, cleanup, or destructive operation that could cause data loss") to make the trigger guidance canonical.

Fold in a couple more natural user phrases such as "wipe" and "free up space" that currently live only in the triggers list.

Dimension	Reasoning	Score
Specificity	Names the concrete actions ("Presents a recoverability card", "requires an explicit 'yes' from the user before proceeding") and comprehensively enumerates the gated operations (rm -rf, git rm, bulk sed, bulk forget, purge-deleted, source removal, raw-SQL truncation), giving full coverage of the domain.	5 / 5
Completeness	Clearly states what the skill does (confirmation gate, card, explicit-yes) and gives explicit trigger guidance ("before any bulk delete, cleanup, or destructive operation"), but lacks a canonical "Use when…" clause, so the when could be marginally more explicit.	4 / 5
Trigger Term Quality	Good keyword coverage including natural phrases ("bulk delete", "cleanup", "destructive operation", "data loss") alongside technical jargon (rm -rf, raw-SQL truncation); a few natural synonyms users might say ("wipe", "free up space") appear only in the triggers list, not the description.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear, narrow niche (confirmation gate for bulk destructive/data-loss operations) with distinct triggers and minimal overlap with sibling skills like test-before-bulk or maintain.	5 / 5
	Total	18 / 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
relative_links	Relative link issues: 6 suspicious	Warning

	Total	14 / 16 Passed

Repository: garrytan/gbrain
Path: plugin-variants/gbrain-coding/skills/data-loss-gate/SKILL.md
Commit: 43597b1

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.