bridge-proof

This skill should be used when the user invokes the bridge-check command or asks to verify the isolated Devin bridge.

Quality

46%

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 ./tests/fixtures/devin-bridge/e2e-workspace/.claude/skills/bridge-proof/SKILL.md

Quality

Content

43%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 commendably lean but underspecified: it tells Claude to inspect, edit, and test without naming tools, steps, or validation, and the cryptic `SKILL_BRIDGE_ACTIVE` token adds noise without guidance. It needs concrete commands and a verification checkpoint to be actionable.

Suggestions

Name the specific project-local tools and give an executable command or snippet for inspecting/editing the fixture instead of the generic 'use project-local tools'.

Add an explicit validation/test checkpoint (e.g., a command to run and the condition for passing) before declaring the task done, since the edit step can alter state.

Replace or explain the `SKILL_BRIDGE_ACTIVE` token so it earns its place, or remove it if it carries no actionable meaning.

Dimension	Reasoning	Score
Conciseness	The body is two terse lines with no padding or explanation of concepts Claude already knows, fitting the 'efficient; minor instances that could be trimmed' anchor; the cryptic `SKILL_BRIDGE_ACTIVE` token keeps it just below a 5.	4 / 5
Actionability	'Use project-local tools to inspect, edit, and test the fixture' is a high-level hint with no named tools, commands, or code, matching the 'minimal concrete guidance; missing specific steps' anchor.	2 / 5
Workflow Clarity	'inspect, edit, and test' gives only a rough sequence with poorly defined steps and no validation checkpoints despite an edit step that can be destructive, fitting the 'rough sequence, many gaps, validation absent' anchor.	2 / 5
Progressive Disclosure	The body is a flat two-line blob with no section headers and no references, and no bundle files exist; for such a short skill this is borderline, landing at the 'some structure but could be better organized' anchor rather than penalized for monolithic depth.	3 / 5
	Total	11 / 20 Passed

Description

48%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 carves out a clear, distinct niche but is thin on substance: it specifies when to trigger the skill far more concretely than what the skill actually does. Strengthening the 'what' with concrete actions would lift completeness and specificity.

Suggestions

State the concrete actions the skill performs (e.g., 'Inspects, edits, and validates the Devin bridge fixture') before the trigger clause so the 'what' is explicit, not implied.

Add natural trigger synonyms/variations (e.g., 'bridge check', 'Devin bridge verification') to broaden keyword coverage.

Keep the niche-specific 'bridge-check command' trigger but pair it with a plain-language description of the task to reduce reliance on a single command name.

Dimension	Reasoning	Score
Specificity	The description names the niche ('bridge-check command', 'verify the isolated Devin bridge') but states no concrete actions beyond an implied 'verify', matching the anchor for naming a domain with minimal/generic actions.	2 / 5
Completeness	The 'when' is explicit, but the 'what' is only weakly implied (the action 'verify' is entangled with the trigger clause rather than stated as a capability), so it does not reach the both-what-and-when anchor at 4.	3 / 5
Trigger Term Quality	It includes relevant trigger phrases ('invokes the bridge-check command', 'asks to verify') but offers no synonyms or common variations, fitting the 'some relevant keywords but missing variations' anchor.	3 / 5
Distinctiveness Conflict Risk	The triggers are tied to a specific niche command and a named 'isolated Devin bridge', giving mostly distinct triggers with only minor overlap risk, matching the 4 anchor rather than the fully-distinct 5.	4 / 5
	Total	12 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: diegosouzapw/OmniRoute
Path: tests/fixtures/devin-bridge/e2e-workspace/.claude/skills/bridge-proof/SKILL.md
Commit: c3945a7

Reviewed: 3 days 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.