he-work

Implement approved Harness Engineering work. Use when a plan, todo list, or tiny spec needs traceable delivery and validation.

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Failed to scan

The risk profile of this skill

Fix and improve this skill with Tessl

tessl review fix ./Plugins/harness-engineering/fixtures/budget-archive/2026-04-21/deferred-store/skills/team_automation/he-work/SKILL.md

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.

The body is a well-structured, lean process skill with strong workflow clarity — explicit validation gates, feedback loops, and stop conditions — and concrete actionable guidance including a specific validation command. Its weak spots are recurring duplicated statements across sections and a references list that does not fully align with the local bundle.

Suggestions

De-duplicate the repeated 'do not expand scope' and 'do not claim completion without validation' statements across Constraints, Gotchas, and Anti-patterns so each idea lives in one place.

Either add the referenced files (SKILL.full.md, handoff-and-shipping.md, execution-modes.md) to the local bundle or note they reside at the listed repo paths, so the disclosed reference structure matches the actual bundle.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence with terse imperatives and no concept over-explanation, but several statements recur across Constraints, Gotchas, and Anti-patterns (e.g., 'do not expand scope', 'do not claim completion without validation evidence'), which is more than minor padding and keeps it off the top anchor.	4 / 5
Actionability	For an instruction/process skill the guidance is concrete and specific — restate IDs/invariants/non-goals, choose a named execution lane, and run an explicit validation command — with only minor gaps in executable detail beyond the single lint command.	4 / 5
Workflow Clarity	The numbered Procedure plus Core Contract gives a clear sequence with explicit validation checkpoints ('run he_linear_traceability_lint.py before claiming completion'), feedback loops ('stop on contract drift, hidden scope, domain drift, or failed gates'), and a stop-at-first-failed-gate rule, matching the top anchor.	5 / 5
Progressive Disclosure	The body is a clear overview with a dedicated References section signaling one-level-deep pointers to full guide, handoff, execution modes, and routing docs; however the local bundle contains only context-preservation.md (not referenced in the body), so the disclosed structure is only partially realized in the actual bundle, fitting the 'good structure, minor gaps' anchor.	4 / 5
	Total	17 / 20 Passed

Description

78%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.

The description is concise and clearly answers both what it does and when to use it, with concrete trigger phrases tied to a specific engineering niche. Its main weakness is specificity — it relies on a single action verb rather than enumerating several concrete capabilities.

Suggestions

Expand the 'what' with 1-2 more concrete actions (e.g., 'implement, validate, and hand off approved work') to lift specificity above the single-verb anchor.

Add a natural synonym or file-type-style trigger (e.g., 'approved plan or spec') to broaden trigger-term coverage toward the top anchor.

Dimension	Reasoning	Score
Specificity	The description names the domain ('Harness Engineering work') and one concrete action ('Implement'), plus outcomes ('traceable delivery and validation'), but does not enumerate several specific actions — matching the 'domain + 1-2 actions' anchor rather than the comprehensive coverage of a 4 or 5.	3 / 5
Completeness	It explicitly answers both what ('Implement approved Harness Engineering work') and when ('Use when a plan, todo list, or tiny spec needs traceable delivery and validation') with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	It surfaces natural trigger phrases users would say ('plan', 'todo list', 'tiny spec') with good keyword coverage, though a few common synonyms or variations are missing — fitting the 'good coverage, a few natural terms missing' anchor.	4 / 5
Distinctiveness Conflict Risk	The 'Harness Engineering' niche and approved-artifact triggers are mostly distinct with minimal conflict risk, but 'implement approved work' still overlaps somewhat with general implementation skills, fitting the 'mostly distinct, minor overlap' anchor rather than a clean 5.	4 / 5
	Total	16 / 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
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: jscraik/Agent-Skills
Path: Plugins/harness-engineering/fixtures/budget-archive/2026-04-21/deferred-store/skills/team_automation/he-work/SKILL.md
Commit: 2f91362

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.