he-phase-work

Runs approved Harness Engineering plans in recurring phases: check live state, wake with he-heartbeat, execute only the active he-work slice, verify gates, update Linear only with approval, and stop before unsafe staging or closure. Use when a plan, issue, or PR needs continued phase-by-phase execution.

Quality

81%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This is a well-structured orchestration skill with strong actionability and workflow clarity—concrete commands, delegation examples, validation gates, and a YAML output template make it highly executable. Its main weaknesses are moderate verbosity with some overlapping sections (Constraints/Gotchas/Failure Mode) and the Stage Arc Boundary section inlining policy that could be referenced. Overall it's a solid skill that clearly guides phase-by-phase execution with appropriate safety boundaries.

Suggestions

Consolidate the overlapping 'Constraints', 'Failure Mode', and 'Gotchas' sections into a single 'Constraints & Failure Modes' section to reduce redundancy.

Move the 'Stage Arc Boundary' detailed policy inline content to a reference file and keep only a one-line pointer in the skill body.

Dimension	Reasoning	Score
Conciseness	The skill is moderately efficient but includes some redundancy—e.g., the 'When Not to Use' and 'Failure Mode' sections overlap, and the 'Inputs' section is a long enumeration that could be tightened. Some sections like 'Gotchas' and 'Constraints' partially repeat each other. However, it generally avoids explaining concepts Claude already knows.	2 / 3
Actionability	The skill provides concrete, executable commands (git status, rg, test -f, pytest), specific delegation examples with exact text, and a structured YAML output template. The procedure steps are specific and copy-paste ready, and the delegation examples show exact skill invocations with file paths and commands.	3 / 3
Workflow Clarity	The procedure is clearly sequenced (steps 1-7) with explicit validation checkpoints (step 5), fail-fast policy, feedback loops (route failures to he-work or he-code-review), and explicit gates before destructive operations (step 7 asks before staging/commit/push/closure). The validation section includes concrete commands and the failure mode is well-defined.	3 / 3
Progressive Disclosure	References are provided at the end pointing to phase-gate contracts, subagent contracts, and other files, which is good structure. However, no bundle files were provided to verify these references exist, and the stage-arc-boundary section inlines a fairly complex policy that could potentially be a reference. The skill is somewhat long for what could be a more concise overview with deeper references.	2 / 3
	Total	10 / 12 Passed

Description

85%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This description is strong in specificity and completeness, clearly listing concrete actions and providing an explicit 'Use when' clause. The domain-specific terminology makes it highly distinctive but may reduce discoverability if users don't use those exact terms. The trigger terms could benefit from more natural language variations that users might actually say.

Suggestions

Add more natural trigger terms users might say, such as 'continue working on', 'resume plan', 'next phase', or 'pick up where I left off' to improve discoverability.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions: check live state, wake with he-heartbeat, execute active he-work slice, verify gates, update Linear with approval, and stop before unsafe staging or closure. These are detailed, actionable steps.	3 / 3
Completeness	Clearly answers both what (runs approved Harness Engineering plans through recurring phases with specific steps) and when ('Use when a plan, issue, or PR needs continued phase-by-phase execution'), with an explicit trigger clause.	3 / 3
Trigger Term Quality	Includes some relevant terms like 'plan', 'issue', 'PR', 'phase-by-phase execution', 'Linear', and 'Harness Engineering', but uses domain-specific jargon ('he-heartbeat', 'he-work slice', 'gates') that users may not naturally say. Missing common variations of how users might request this.	2 / 3
Distinctiveness Conflict Risk	Highly distinctive due to the specific 'Harness Engineering' domain, proprietary terms like 'he-heartbeat' and 'he-work slice', and the unique workflow of phase-by-phase plan execution with Linear integration. Unlikely to conflict with other skills.	3 / 3
	Total	11 / 12 Passed

Validation

100%

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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: jscraik/Agent-Skills
Commit: 8e7e19d

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.