harness-contract-change

Modifies the repository's agent contract including AGENTS.md, docs index, manifests, validation scripts, and contributor-facing harness wrappers. Use when updating agent documentation, changing repo manifests, editing validation scripts, modifying CI/workflow classification, or updating contributor-facing guides like README.md, CONTRIBUTING.md, or the PR template.

Quality

86%

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

85%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 concise, well-structured instruction skill with explicit validation checkpoints in its workflow and concrete make commands. The main gap is actionability of the workflow steps themselves, which are prose instructions rather than literal per-step executable commands.

Dimension	Reasoning	Score
Conciseness	Lean and efficient with no padding or explanation of concepts Claude already knows; every section (Trigger, Surfaces, Stop Conditions, Workflow, Gotchas, Standard Commands, Acceptance) earns its place with no time-sensitive clutter.	5 / 5
Actionability	Provides concrete, copy-paste-ready commands ('make agent-validate', 'make agent-ci-gate CHANGED_FILES="..."', 'make agent-report ENV=cpu CHANGED_FILES="..."') and named files, but workflow steps are phrased as instructional prose rather than literal per-step commands.	4 / 5
Workflow Clarity	A clear 5-step sequence with explicit validation checkpoints ('make agent-validate' as the focused iteration check, 'make agent-ci-gate' as the final gate) and a feedback/debt-recording step, appropriate for a harness change that affects batch enforcement.	5 / 5
Progressive Disclosure	Well-organized into labeled sections with a one-level-deep 'Must Read' reference list pointing to real relative paths (tools/agent/docs/README.md, governance.md, plans/README.md) and no nested references; no bundle files exist to split further, so structure is good but not the full multi-file split of a 5.	4 / 5
	Total	18 / 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 pairs a concrete 'what' with an explicit and comprehensive 'Use when...' clause naming specific filenames and triggers. The only weakness is that 'Modifies' is a single verb applied to many surfaces rather than a set of distinct actions, slightly limiting specificity.

Dimension	Reasoning	Score
Specificity	Lists several concrete objects/surfaces (AGENTS.md, docs index, manifests, validation scripts, contributor wrappers) under the action 'Modifies', but the single verb 'Modifies' covers all of them rather than naming distinct actions per surface.	4 / 5
Completeness	Explicitly answers both what ('Modifies the repository's agent contract including...') and when ('Use when updating agent documentation, changing repo manifests...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Comprehensive natural triggers ('updating agent documentation', 'changing repo manifests', 'editing validation scripts', 'modifying CI/workflow classification') plus specific filenames (README.md, CONTRIBUTING.md, PR template) users would name.	5 / 5
Distinctiveness Conflict Risk	Clear niche (agent/harness contract) with named distinct triggers and specific files, with only minor overlap risk against a generic documentation skill.	4 / 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: 3 suspicious	Warning

	Total	14 / 16 Passed

Repository: vllm-project/semantic-router
Path: tools/agent/skills/harness-contract-change/SKILL.md
Commit: adc7455

Reviewed: 5 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.