harness-init

One-time, guided setup of the local agent-first coding harness — the polling loop, the deterministic dispatcher, its config, the AGENTS.md contract, and the worktree provisioning that makes per-feature worktrees runnable. Use when a developer wants to set up, bootstrap, install, or initialize the coding harness for the first time in a project.

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

71%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 well-structured, actionable guided setup with strong progressive disclosure and a clear validated workflow. Its main weakness is length and some redundancy that could be tightened for token efficiency.

Suggestions

Consolidate the memory-loop explanation (currently restated in Steps 2, 9, and 10) into one place and cross-reference it to cut repeated tokens.

Tighten the Step 7 auth/billing walkthrough by moving subscription-vs-metered detail into references/reviewer-options.md and keeping only the decision in the body.

Trim narrative phrasing like "You have rich context in references/ so you never have to guess" where the instruction is already implied by the read-first directives.

Dimension	Reasoning	Score
Conciseness	Mostly dense and harness-specific rather than explaining general concepts, but at ~325 lines it repeats some explanations (the memory-loop description recurs across Steps 2, 9, 10) and the Step 7 auth/billing tangent could be tightened.	3 / 5
Actionability	Gives concrete, executable commands throughout ("git worktree add --detach ../<repo>-harness origin/main", "/loop 5m /poll-and-dispatch", the .gitignore block) plus exact file paths; a few steps defer to references rather than inlining specifics, which is appropriate but leaves minor gaps.	4 / 5
Workflow Clarity	An explicit Step 0–10 sequence with the explain→confirm→do→show→feedback pattern and real validation (Step 8 bootstrap doubles as validation, Step 9 dry-runs the tick); some checkpoints are human-gated rather than automated, leaving minor gaps.	4 / 5
Progressive Disclosure	The body is a well-signaled overview pointing one level deep into references/, assets/, and scripts/ (e.g., "Read references/dispatcher-explained.md"), and every referenced bundle file exists, giving clear navigation with no nesting.	5 / 5
	Total	16 / 20 Passed

Description

92%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: concrete about what gets set up, explicit about when to use it, and clearly distinct from other skills. The only minor gap is trigger-term breadth, which leans on somewhat technical phrasing.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete components/actions being set up — "the polling loop, the deterministic dispatcher, its config, the AGENTS.md contract, and the worktree provisioning" — giving comprehensive coverage of what the skill stands up.	5 / 5
Completeness	Explicitly answers both what (one-time guided setup of the named harness components) and when ("Use when a developer wants to set up, bootstrap, install, or initialize the coding harness for the first time in a project").	5 / 5
Trigger Term Quality	Includes several natural synonyms users would say ("set up, bootstrap, install, or initialize") but the surrounding noun phrase ("agent-first coding harness") is somewhat technical, missing a few plainer variations.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (first-time harness bootstrap) with distinct triggers ("for the first time in a project"), making overlap with other skills minimal.	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: 6 missing, 1 deeper-than-1-level	Warning

	Total	15 / 16 Passed

Repository: tdg-ninja/context-specs-factory-ai
Path: skills/harness/harness-init/SKILL.md
Commit: 3a7a725

Reviewed: about 19 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.