he-phase-work

Runs approved Harness Engineering plans in recurring phases: check live state, confirm continuation authority, 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

73%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

—

The risk profile of this skill

Fix and improve this skill with Tessl

tessl review fix ./Plugins/harness-engineering/skills/he-phase-work/SKILL.md

Quality

Content

62%Scale 1-3

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 clear phase-gated workflow, explicit delegation patterns, and a useful output template. Its main weaknesses are moderate verbosity (some sections overlap or could be consolidated) and partially actionable validation commands that use unresolved placeholders. The progressive disclosure is reasonable but the Stage Arc Boundary section adds inline complexity that could be referenced instead.

Suggestions

Replace placeholder tokens in validation commands (<approved-plan-path>, <touched-skill-path>) with concrete resolution instructions or variable-binding examples so commands are fully executable.

Consolidate overlapping sections (Failure Mode, Constraints, Execution Boundaries) into a single 'Guardrails' section to reduce redundancy and improve token efficiency.

Move the Stage Arc Boundary section to a referenced file since it describes a cross-cutting contract rather than phase-work-specific logic.

Dimension	Reasoning	Score
Conciseness	The skill is moderately efficient but includes some redundancy (e.g., 'Philosophy' section restates what the procedure already conveys, and several sections like 'Failure Mode' and 'Constraints' overlap in intent). Some sections like 'Gotchas' are tight and useful, but overall it could be tightened.	2 / 3
Actionability	The procedure provides a clear sequence and the delegation examples are concrete and copy-paste ready. However, the validation commands mix real commands (git status, rg) with placeholders (<approved-plan-path>, <touched-skill-path>) without explaining how to resolve them, and the core procedure steps are more descriptive than executable.	2 / 3
Workflow Clarity	The multi-step procedure is clearly sequenced with explicit validation checkpoints (step 5 runs validation after he-work, step 7 requires approval before mutations). Fail-fast policy is stated, feedback loops for failed gates are explicit (route to he-work or he-code-review), and the output template provides a structured checkpoint summary.	3 / 3
Progressive Disclosure	References to external contracts and files are present and one-level deep (phase-gate-contract.md, subagent-call-contract.md, stage-arc-boundary-contract.md), but no bundle files were provided to verify these exist. The skill itself is somewhat long and the Stage Arc Boundary section feels like it could be a reference rather than inline content.	2 / 3
	Total	9 / 12 Passed

Description

85%Scale 1-3

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 is strong in specificity and completeness, clearly articulating both what the skill does and when to use it. It defines a distinct niche around Harness Engineering phased execution. The main weakness is trigger term quality—the language is heavily domain-specific jargon ('he-work slice', 'continuation authority') that users may not naturally use when requesting this skill.

Suggestions

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

Clarify or expand the abbreviation 'he-work slice' since it reads as jargon that won't match user queries naturally.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions: check live state, confirm continuation authority, execute active work slice, verify gates, update Linear with approval, and stop before unsafe staging/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' (explicit 'Use when a plan, issue, or PR needs continued phase-by-phase execution').	3 / 3
Trigger Term Quality	Includes some relevant terms like 'plan', 'issue', 'PR', 'phase-by-phase execution', 'Linear', and 'Harness Engineering', but these are fairly domain-specific. Missing common natural language variations a user might say (e.g., 'continue working on', 'next step', 'resume task'). 'he-work slice' is jargon that wouldn't be naturally used.	2 / 3
Distinctiveness Conflict Risk	Highly distinctive with specific references to 'Harness Engineering plans', 'he-work slice', 'Linear', and the particular phased execution workflow. Unlikely to conflict with other skills due to its narrow, well-defined niche.	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
Path: Plugins/harness-engineering/skills/he-phase-work/SKILL.md
Commit: d933d80

Reviewed: 2 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.