luffy-arm-fullpower-off

Use when the user asks to turn off, disable, close, or disarm luffy-arm full-power mode, including "turn off full power", "disable full-power", 关闭 full power, 退出全功率模式. Removes the dedicated admin key, verifies that credential is off, and reports alternate user-level SSH access separately.

Quality

94%

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 lean, highly operational companion-skill body: all four dispatch paths have concrete commands, the legacy procedure has genuine validation checkpoints and retry loops, and references (sibling skill section, user-sessions.md, the bundled wrapper) are correctly signaled and real. The only notable weakness is that self-contained executability dips slightly because target-selection mechanics and example invocations are deferred to the sibling luffy-arm skill.

Suggestions

Add one concrete example invocation per dispatch path (e.g. `python3 scripts/power.py off web-gateway-01`) so the commands are copy-paste ready without consulting the sibling skill.

Briefly state how a 'registered target' is identified or listed (one line or a pointer to the exact main-skill command), since step 1 of the primary path currently depends entirely on the sibling skill's documentation.

Dimension	Reasoning	Score
Conciseness	Every sentence carries operational content — commands, paths, reporting rules, failure branches — with zero concept explanations or padding. Phrases like "TTL expiry is a fallback, not evidence of immediate shutdown" earn their tokens. Matches the lean-and-efficient 5 anchor.	5 / 5
Actionability	Concrete executable commands are given for every path ("python3 scripts/power.py off TARGET", "python3 scripts/lifecycle.py all off", "python3 scripts/session.py off TARGET", "bash scripts/fullpower-off.sh") and the wrapper script exists in the bundle. Not 5 because no concrete example invocation is shown, and key mechanics (target selection rules, what 'host execution' entails) are deferred to the sibling skill, leaving minor gaps in self-contained executability.	4 / 5
Workflow Clarity	The numbered legacy procedure has explicit validation checkpoints (report "DEDICATED GATE: OFF" only on explicit authentication denial, second-layer "EFFECTIVE USER ACCESS: AVAILABLE" check), feedback loops (retry on UNKNOWN with host execution), and error-recovery branches (remediation relay, ask-when-unclear). Validation is present for this credential-removal operation, so the destructive-operation cap does not apply.	5 / 5
Progressive Disclosure	A ~45-line body with well-organized sections and clearly signaled one-level-deep references: the sibling skill's Full-power mode section, its references/user-sessions.md, and the bundled scripts/fullpower-off.sh, which exists in the bundle and is referenced correctly. Matches the small-skill 5 exception and the well-signaled-reference anchor.	5 / 5
	Total	19 / 20 Passed

Description

95%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 strong description: third-person, concise, with an explicit 'Use when' clause carrying multiple natural trigger phrases in both English and Chinese, followed by three concrete capability statements. The only gap is that the capability sentence covers just the default-key path and not the skill's other dispatch variants.

Dimension	Reasoning	Score
Specificity	Names the domain ("luffy-arm full-power mode") and three concrete actions: "Removes the dedicated admin key, verifies that credential is off, and reports alternate user-level SSH access separately." This matches the several-specific-actions-with-minor-gaps anchor rather than 5, since it omits the operation's other variants (closing all connections, password-session targets) and 'reports alternate user-level SSH access separately' is somewhat opaque.	4 / 5
Completeness	Explicitly answers both: 'when' via "Use when the user asks to turn off, disable, close, or disarm luffy-arm full-power mode, including..." with concrete trigger phrases, and 'what' via the three stated actions. Matches the 5 anchor exactly.	5 / 5
Trigger Term Quality	Comprehensive natural-term coverage with synonyms and translations: "turn off, disable, close, or disarm", literal phrases "turn off full power", "disable full-power", plus 关闭 full power and 退出全功率模式. Not below 5 because no common phrasing a user would say for this request is missing.	5 / 5
Distinctiveness Conflict Risk	Clear niche ("luffy-arm full-power mode") with distinct OFF-side triggers (turn off / disable / disarm). The only overlap is with the companion ON-side luffy-arm skill, which the off-verb triggers cleanly disambiguate — minimal conflict risk.	5 / 5
	Total	19 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
referenced_paths_exist	Referenced path issues: 4 missing	Warning

	Total	15 / 16 Passed

Repository: Ares960826/luffy-arm
Path: skills/luffy-arm-fullpower-off/SKILL.md
Commit: 12473f1

Reviewed: 2 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.