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.

37

Quality

35%

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

Quality

Content

35%

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

This skill reads more like an abstract policy document than an actionable guide. While it correctly identifies the domain (plan hardening before implementation) and has reasonable structure with external references, it critically lacks concrete examples of what a 'deepened plan' looks like, specific transformation patterns, or any executable artifacts. The irony is that a skill about improving execution clarity is itself vague about execution.

Suggestions

Add a concrete before/after example showing a thin plan entry transformed into a deepened one with sequencing, gates, and rollback — this is essential for actionability.

Replace the abstract procedure steps with specific analysis patterns, e.g., 'For each task, verify it has: (1) observable completion criteria, (2) named owner, (3) rollback command or procedure, (4) dependency list with availability checks.'

Add a template or schema for the deepened plan output so Claude knows the exact structure to produce, rather than just 'deepened plan with explicit sequencing.'

Clarify what 'load the archived full guide' means — specify the exact file path or remove the reference if no bundle file exists.

DimensionReasoningScore

Conciseness

The content is reasonably structured but includes some unnecessary sections (e.g., 'Philosophy' restates obvious points, 'Progressive Disclosure Entry' header is meta-noise). The subagent routing section is verbose and could be trimmed. However, it avoids explaining basic concepts Claude already knows.

2 / 3

Actionability

The procedure is entirely abstract ('Inspect current plan for ambiguity', 'Deepen task sequencing') with no concrete examples of what a deepened plan looks like, no specific commands or templates, and no executable guidance. The examples section only shows user prompts, not input/output pairs demonstrating the transformation.

1 / 3

Workflow Clarity

There is a 3-step procedure and a validation section with a 'fail fast' gate, but the steps are vague and lack explicit checkpoints between them. For a skill focused on 'sequencing and verification,' the workflow itself ironically lacks the concrete validation steps and feedback loops it advocates for.

2 / 3

Progressive Disclosure

References to external files (contract.yaml, evals.yaml, task-profile.json, subagent-routing.md) are clearly listed and one level deep, which is good. However, no bundle files were provided to verify these references exist, the body mentions 'load the archived full guide' without specifying what file that is, and the subagent routing section inlines content that could remain in the referenced file.

2 / 3

Total

7

/

12

Passed

Description

35%

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 attempts to define a specific planning-related skill but relies heavily on internal jargon ('Harness Engineering plan hardening', 'he-work') that would not help Claude match user requests naturally. The 'what' is moderately clear but the 'when' clause is undermined by opaque terminology, and the description lacks concrete, enumerated actions.

Suggestions

Replace jargon like 'Harness Engineering plan hardening' and 'he-work' with natural language users would actually say, e.g., 'Use when the user wants to refine, strengthen, or review an implementation plan before execution.'

List specific concrete actions the skill performs, e.g., 'Adds task sequencing and dependencies, defines verification checkpoints, identifies risks and mitigation steps.'

Include natural trigger terms users might use, such as 'refine plan', 'plan review', 'execution readiness', 'strengthen plan', 'pre-execution check'.

DimensionReasoningScore

Specificity

The description names a domain ('implementation plan') and a general action ('deepen...so sequencing, verification, and risk treatment are strong enough for execution'), but it doesn't list multiple concrete actions—it's more of a high-level summary of what 'deepening' entails rather than specific discrete operations.

2 / 3

Completeness

It answers 'what' (deepen an implementation plan for sequencing, verification, risk treatment) and has a 'Use when' clause, but the 'when' is filled with opaque jargon ('Harness Engineering plan hardening', 'he-work') that doesn't provide clear, actionable trigger guidance.

2 / 3

Trigger Term Quality

The trigger terms are weak and unnatural. 'Harness Engineering plan hardening' and 'he-work' are jargon/internal terminology that users would not naturally say. Common terms like 'refine plan', 'improve plan', 'plan review', or 'execution readiness' are missing.

1 / 3

Distinctiveness Conflict Risk

The niche of 'plan hardening' is somewhat specific, but the vague language around 'implementation plan' and 'execution' could overlap with general planning or project management skills. The jargon makes it distinctive in a narrow sense but not in a way that aids correct selection.

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.