he-ideate

Generate and compare grounded product or engineering directions with tradeoffs. Use when users want possibilities, critique, or direction-setting before a spec.

Quality

70%

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-ideate/SKILL.md

Quality

Content

71%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, mostly lean instruction skill with a clear sequenced procedure and explicit fail-fast validation. Its main weakness is progressive disclosure: it advertises archived references and asset files that are not present in the bundle.

Suggestions

Remove or fulfill the 'archived references' claim and the ./assets/icon links, since no references/ or assets/ files exist in the bundle.

Interleave the validation gates inline within the Procedure steps (e.g. a checkpoint after grounding, after candidate generation) rather than only in a separate section.

Replace high-level actions like 'shallow codebase scan' with a specific command or tool call to push actionability toward 5.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence (no explanations of what ideation, repos, or tradeoffs are), but the Philosophy section restates ideas later covered in Procedure and the opening 'keeps full operational context in archived references' is filler, so it is not the every-token-earns-its-place 5.	4 / 5
Actionability	The 6-step Procedure and Validation gates give concrete, sequenced, actionable instruction (e.g. 'shallow codebase scan', 'keep explicit rejection reasons', 'route the strongest survivor to he-brainstorm'), with concrete example prompts; steps like 'shallow codebase scan' lack a specific command, leaving minor gaps short of fully copy-paste-ready 5.	4 / 5
Workflow Clarity	A clear numbered Procedure is paired with an explicit Validation section and a fail-fast feedback loop ('stop at first failed gate and do not proceed'), but validation checkpoints live in a separate section rather than interleaved inline at each risky step, the minor gap that keeps it at 4.	4 / 5
Progressive Disclosure	Sections are well-organized, but the body signals references that do not exist: it claims to 'keep full operational context in archived references' and links ./assets/icon-small.png and ./assets/icon-large.png, yet no references/ or assets/ bundle exists on disk, so signaled navigation is broken.	3 / 5
	Total	15 / 20 Passed

Description

70%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 solid description that clearly pairs a concrete capability statement with an explicit 'Use when' trigger clause and a positioning qualifier. It is held back from the top band by abstract trigger phrasing and only two named actions.

Suggestions

Add 1-2 more concrete actions (e.g. 'rank survivors by tradeoff', 'route the strongest option to he-brainstorm') to lift specificity toward 5.

Swap jargon-y triggers ('direction-setting') for natural user phrases ('explore options', 'compare approaches', 'which direction is worth pursuing').

Tighten the 'when' clause with concrete trigger nouns comparable to 'PDFs, forms, document extraction'.

Dimension	Reasoning	Score
Specificity	Names the domain ("product or engineering directions") and two concrete actions ("Generate and compare ... with tradeoffs"), matching the score-3 anchor of domain plus 1-2 actions; it does not list several distinct actions needed for a 4.	3 / 5
Completeness	It answers both what ("Generate and compare grounded ... directions with tradeoffs") and when ("Use when users want possibilities, critique, or direction-setting before a spec"), but the when phrasing is slightly abstract/jargon-heavy rather than the crisp concrete triggers of a 5.	4 / 5
Trigger Term Quality	The "Use when users want possibilities, critique, or direction-setting" clause supplies three natural trigger terms with good coverage, though more colloquial synonyms (e.g. "explore options", "brainstorm directions") are missing, keeping it just below a 5.	4 / 5
Distinctiveness Conflict Risk	The pre-spec ideation/direction-setting niche is mostly distinct, with the "before a spec" qualifier reducing overlap; minor conflict risk remains with closely related brainstorm/plan skills, so it is not the minimal-risk 5.	4 / 5
	Total	15 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
relative_links	Relative link issues: 2 missing	Warning

	Total	14 / 16 Passed

Repository: jscraik/Agent-Skills
Path: Plugins/harness-engineering/fixtures/budget-archive/2026-04-21/deferred-store/skills/team_automation/he-ideate/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.