CtrlK
BlogDocsLog inGet started
Tessl Logo

he-work

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

46

Quality

48%

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./Plugins/harness-engineering/fixtures/budget-archive/2026-04-21/deferred-store/skills/team_automation/he-work/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

57%

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

This skill is well-organized as an overview document with good progressive disclosure to reference materials. Its main weaknesses are redundancy across sections (Constraints, Gotchas, Anti-patterns, and Core Contract overlap significantly) and a lack of concrete, executable examples — most guidance is procedural prose rather than actionable commands or artifact templates. The single validation script command is a bright spot, but the workflow would benefit from more specific, executable steps.

Suggestions

Consolidate overlapping sections (Gotchas, Constraints, Anti-patterns, parts of Core Contract) to eliminate repeated points about scope expansion, validation evidence, and traceability — this would improve conciseness significantly.

Add a concrete example of a handoff artifact or validation evidence output so Claude knows exactly what the deliverable looks like, not just the abstract requirements.

Expand the Procedure section with sub-steps or a worked example showing the actual commands/actions for at least one execution lane (e.g., plan-led), including the feedback loop when a validation gate fails.

DimensionReasoningScore

Conciseness

The content is mostly efficient but has some redundancy — 'Gotchas' repeats points from 'Constraints' and 'Anti-patterns', and several sections (Deliverables, Core Contract, Procedure, Validation) overlap in their coverage of traceability and validation requirements. The philosophy and structure are lean, but the repetition across sections inflates token count without adding new information.

2 / 3

Actionability

The skill provides one concrete executable command (the linting script), but most guidance is procedural/conceptual rather than copy-paste ready. Terms like 'resolve Linear', 'implement one verified slice', and 'update handoff evidence' are domain-specific instructions without concrete examples of what those artifacts look like or specific commands to run. The examples section only shows trigger phrases, not input/output examples.

2 / 3

Workflow Clarity

The Procedure section provides a clear 4-step sequence, and the Validation section includes explicit stop-on-failure gates and a concrete validation command. However, the procedure steps are high-level abstractions ('Resolve Linear, branch, PR, IDs, and validation gates') without detailed sub-steps or explicit feedback loops for error recovery. The failure mode section helps but the workflow lacks the granularity needed for a multi-step process involving code, Linear, PRs, and artifact state synchronization.

2 / 3

Progressive Disclosure

The skill is well-structured as an overview with clear, well-signaled one-level-deep references to detailed materials (full guide, handoff-and-shipping, execution-modes, approval-flow, etc.). The main body stays concise while pointing to specific reference files for deeper content. Navigation is straightforward.

3 / 3

Total

9

/

12

Passed

Description

40%

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 too vague about what concrete actions the skill performs, relying on abstract phrases like 'implement approved work' and 'traceable delivery and validation.' While it includes a 'Use when' clause and the 'Harness Engineering' domain qualifier adds some distinctiveness, the lack of specific capabilities makes it difficult for Claude to confidently select this skill over others.

Suggestions

Replace 'Implement approved Harness Engineering work' with specific concrete actions, e.g., 'Creates branches, writes code changes, runs tests, and submits PRs for Harness Engineering tasks.'

Expand trigger terms with natural user language variations, e.g., 'Use when a user asks to execute a plan, complete a todo item, build from a spec, or deliver on an approved engineering task in Harness.'

Clarify what 'traceable delivery and validation' means concretely — e.g., 'links commits to plan items, verifies test coverage, and marks tasks complete.'

DimensionReasoningScore

Specificity

The description uses vague language like 'implement approved work' and 'traceable delivery and validation' without listing any concrete actions. It does not specify what kind of work is being implemented or what specific operations are performed.

1 / 3

Completeness

It has a 'Use when...' clause addressing the 'when' question with triggers like 'plan, todo list, or tiny spec needs traceable delivery,' but the 'what' is extremely vague — 'implement approved Harness Engineering work' doesn't explain what concrete actions the skill performs.

2 / 3

Trigger Term Quality

It includes some relevant terms like 'plan', 'todo list', 'tiny spec', and 'Harness Engineering' that could serve as triggers, but these are somewhat niche and miss common variations a user might naturally say. Terms like 'traceable delivery' are not natural user language.

2 / 3

Distinctiveness Conflict Risk

'Harness Engineering' provides some domain specificity, but 'implement approved work' and 'traceable delivery and validation' are generic enough to overlap with other implementation, project management, or CI/CD skills.

2 / 3

Total

7

/

12

Passed

Validation

90%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

Total

10

/

11

Passed

Repository
jscraik/Agent-Skills
Reviewed

Table of Contents

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.