Tessl • The package manager for agent skills

SkillPublic

verify-gate

Runs project compile, test, and lint commands between implementation and quality review. Gates simplify-and-harden behind machine verification. If checks fail, routes back to implementation with diagnostics for a fix loop. If checks pass, signals ready for the quality pass. Use after any implementation work completes and before simplify-and-harden. Essential for the inner loop's verify step.

Quality

87%

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

The canonical home for this skill is verify-gate in pskoett/pskoett-ai-skills

Quality

Content

81%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 verification workflow with explicit validation checkpoints and a fully specified fix loop. The main costs are localized verbosity in the acceptance-evidence prose and inlined reference-style material in a long single file.

Suggestions

Trim the 'Do not substitute intermediate proof' sentence list in the acceptance-evidence section to one or two illustrative examples, keeping the principle statement.

Move the mcp-scripts example configs and the sibling-skill integration details (skill-pipeline table, self-healing, self-improvement) into a references/ file, linked from a short section in SKILL.md.

Add a concrete example of a Phase 5 acceptance check (e.g., a specific host/workspace/artifact/outcome tuple) to replace the abstract 'capture enough evidence' phrasing.

Dimension	Reasoning	Score
Conciseness	The body is step- and command-focused and assumes Claude's competence, but the 'Define acceptance evidence' prose ('an iframe src is not a rendered app, a successful build is not proof that the host loaded it...') and the three-example mcp-scripts block could be trimmed.	4 / 5
Actionability	Mostly executable: exact per-ecosystem commands, exit-code branches per phase, copy-paste PASSED/BLOCKED templates, and runnable mcp-scripts examples; Phase 5's 'capture enough evidence' guidance is the minor abstract gap.	4 / 5
Workflow Clarity	Steps 1–4 are explicitly sequenced with per-phase exit-code validation gates, a fix loop with explicit retry counting, attempt limits (3/phase), an effort budget (20%), and an exhausted-loop BLOCKED signal — a complete feedback loop.	5 / 5
Progressive Disclosure	Well-sectioned single file with clear headers and navigation, but at ~235 lines the mcp-scripts examples and cross-skill integration details are inlined where a references file could carry them.	4 / 5
	Total	17 / 20 Passed

Description

88%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 that explicitly states what the skill does, when to use it, and how it fits the pipeline, all in concrete third-person terms. It could add a few more natural trigger phrasings to broaden keyword coverage.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete actions — 'Runs project compile, test, and lint commands', 'routes back to implementation with diagnostics for a fix loop', 'signals ready for the quality pass' — covering the skill's behavior comprehensively with no gaps.	5 / 5
Completeness	It explicitly answers both what (runs compile/test/lint, fix loop on failure, gate signal on success) and when ('Use after any implementation work completes and before simplify-and-harden') with concrete trigger guidance.	5 / 5
Trigger Term Quality	Good natural keywords ('compile, test, and lint', 'machine verification', 'fix loop', 'quality review') but misses common user phrasings like 'run the tests', 'check the build passes', or 'make sure it works', so it falls just short of comprehensive coverage.	4 / 5
Distinctiveness Conflict Risk	The pipeline framing ('inner loop's verify step', 'Gates simplify-and-harden') carves a distinct niche, but the generic 'runs compile, test, and lint commands' action set overlaps somewhat with any general test/verify skill.	4 / 5
	Total	18 / 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: 1 missing	Warning

	Total	15 / 16 Passed

Repository: pskoett/pskoett-ai-skills
Path: agent-plugin/skills/verify-gate/SKILL.md
Revision: 47dc16a

Reviewed: 9 days ago

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.

verify-gate

Table of Contents

Is this your skill?