he-work

Executes bounded implementation work from approved specs, plans, issues, or small fixes by editing files, running validation, preserving unrelated work, and recording rollback and handoff evidence. Use when asked to implement, execute a plan, apply changes, or build a scoped feature.

Quality

85%

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

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 well-structured, actionable skill body with a strong sequenced workflow and explicit validation/feedback loops. Its main weaknesses are some token-heavy reference-path enumeration and a mismatch between body-cited reference files and the files actually present in the bundle.

Suggestions

Consolidate or shorten the long repeated relative reference paths in the References section to reduce token weight without losing navigation.

Reconcile body-cited reference files (e.g. spec-plan-runtime-boundary-contract.md, codex-native-memory-baseline.md) with the actual bundle contents, or move them into references/ so cited paths resolve.

Inline the one or two most critical boundary checks instead of deferring entirely to external contracts, so the core procedure is self-contained and copy-paste ready.

Dimension	Reasoning	Score
Conciseness	Sections are lean and assume Claude's competence (no basic-concept padding), but long repeated relative reference paths add some token weight that could be trimmed, placing it at 4 rather than the fully lean 5 anchor.	4 / 5
Actionability	It gives executable bash commands (git status, rg, py_compile, pytest, ask skills audit) and a complete YAML output template, but defers some of the "how" to external contract files, leaving minor gaps versus the copy-paste-ready 5 anchor.	4 / 5
Workflow Clarity	An 8-step procedure is clearly sequenced with upfront state checks (step 1), explicit validation (step 6), and a fix-once-and-re-run feedback loop (step 7), matching the 5 anchor's checkpoints-and-recovery criterion; validation is present so no destructive-cap applies.	5 / 5
Progressive Disclosure	Clear sectioned overview with a dedicated, one-level-deep References list signals navigation well, but the body's referenced .md paths do not map to the actual bundle (references/ holds contract.yaml, evals.yaml, task-profile.json; assets/ holds icons), a minor organization gap keeping it below 5.	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, third-person description that crisply states both the capability and the use triggers, with concrete actions and a clear niche. It is held back only by slightly less exhaustive trigger synonyms and minor overlap with generic coding skills.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete actions — "editing files, running validation, preserving unrelated work, and recording rollback and handoff evidence" — giving comprehensive coverage of what the skill does, matching the 5 anchor rather than the 4 anchor's "minor gaps."	5 / 5
Completeness	It explicitly answers both what ("Executes bounded implementation work…") and when ("Use when asked to implement…") with concrete trigger phrases, matching the 5 anchor exactly.	5 / 5
Trigger Term Quality	"Use when asked to implement, execute a plan, apply changes, or build a scoped feature" provides good natural trigger coverage, but a few common synonyms/variations are missing, so it sits above the 3 anchor but below the comprehensive 5 anchor.	4 / 5
Distinctiveness Conflict Risk	The "bounded implementation work from approved specs, plans, issues" framing carves a distinct niche, but broad triggers like "implement" and "build a scoped feature" retain minor overlap with general development skills, placing it at 4 rather than 5.	4 / 5
	Total	18 / 20 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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: jscraik/Agent-Skills
Path: Plugins/harness-engineering/skills/he-work/SKILL.md
Commit: f1f2f21

Reviewed: 1 day 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.