CtrlK
BlogDocsLog inGet started
Tessl Logo

he-deepen-plan

Deepen an existing implementation plan so sequencing, verification, and risk treatment are strong enough for execution. Use when the user wants Harness Engineering plan hardening before he-work.

56

Quality

65%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

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-deepen-plan/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

63%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 concise, well-structured progressive-disclosure entry with a clear sequence and fail-fast gate, but its actionability is directive-level rather than concrete and several referenced bundle paths are missing or deeply nested.

Suggestions

Add a concrete checklist or gate schema (e.g. per-task fields: owner, gate, rollback, completion criteria) so the Procedure is executable rather than directive.

Fix or remove broken references — ./references, ./assets/icon-small.png, and ./Infrastructure/references/* do not exist in the bundle.

Replace the deeply nested ../../../../../Skills/agent-ops/... link with a one-level-deep, signaled reference to avoid 2+-level nesting the rubric penalizes.

DimensionReasoningScore

Conciseness

Lean, well-sectioned, and free of concept explanations Claude already knows, with only mild redundancy across Philosophy/When-to-use/Anti-patterns that could be trimmed.

4 / 5

Actionability

Procedure gives concrete directives ('Inspect current plan for ambiguity, hidden coupling, and missing checkpoints') but stops at high-level verbs without a concrete checklist template, gate schema, or artifact fields to execute against.

3 / 5

Workflow Clarity

Numbered procedure plus an explicit fail-fast gate ('stop at first failed gate and do not proceed') provides clear sequencing and a checkpoint, but there is no validate→fix→retry feedback loop for a 5.

4 / 5

Progressive Disclosure

Sections are well-organized and clearly signal an archived full guide, but several referenced paths (./references, ./assets, ./Infrastructure/references) do not exist on disk and one link is a deeply nested five-level relative path, harming navigation.

3 / 5

Total

14

/

20

Passed

Description

67%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 clearly communicates purpose and trigger condition with good specificity, but its trigger language leans on internal workflow jargon rather than natural user phrasing, capping trigger-term and completeness scores.

Suggestions

Add natural user-facing trigger phrases (e.g. 'Use when the user asks to tighten, sequence, or stress-test an implementation plan before coding').

Replace or gloss the jargon term 'he-work' so the trigger is intelligible without prior workflow knowledge.

List a couple of discrete concrete actions (e.g. 'sequence tasks, define gates, specify rollback') to lift specificity toward 5.

DimensionReasoningScore

Specificity

Names the domain (implementation plans) and three concrete treatment dimensions — sequencing, verification, and risk treatment — but stops short of listing multiple discrete actions like a 5.

4 / 5

Completeness

Explicitly states both what ('Deepen an existing implementation plan...') and when ('Use when the user wants Harness Engineering plan hardening before he-work'), though the 'when' is niche rather than concrete natural triggers.

4 / 5

Trigger Term Quality

Provides a 'Use when' trigger with 'plan hardening' and 'before he-work', but the terms are workflow-jargon-bound and miss natural synonyms a user would actually say.

3 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (plan hardening as a specific Harness Engineering stage) with distinct triggers, but 'deepen an implementation plan' still risks minor overlap with generic planning/review skills.

4 / 5

Total

15

/

20

Passed

Validation

87%

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

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

relative_links

Relative link issues: 6 missing, 3 deeper-than-1-level, 4 suspicious

Warning

Total

14

/

16

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.