he-ideate
Generate and compare grounded product or engineering directions with tradeoffs. Use when users want possibilities, critique, or direction-setting before a spec.
56
64%
Does it follow best practices?
Impact
—
No eval scenarios have been run
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-ideate/SKILL.mdQuality
Discovery
67%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 has a solid structure with both 'what' and 'when' clauses clearly present, which is its main strength. However, the capabilities described are somewhat abstract—terms like 'grounded directions' and 'direction-setting' lack the concrete specificity that would help Claude confidently select this skill. The trigger terms could be expanded to cover more natural user language patterns.
Suggestions
Add more concrete actions/deliverables, e.g., 'create comparison matrices, enumerate pros and cons, draft decision briefs' to increase specificity.
Expand trigger terms in the 'Use when' clause with natural user phrases like 'brainstorm approaches', 'evaluate options', 'pros and cons', 'technical decision', or 'explore alternatives'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names a domain (product/engineering directions) and some actions (generate, compare, tradeoffs), but the actions remain fairly abstract. It doesn't list concrete deliverables like 'create comparison matrices, enumerate pros/cons, draft decision documents.' | 2 / 3 |
Completeness | The description clearly answers both 'what' (generate and compare grounded product or engineering directions with tradeoffs) and 'when' (when users want possibilities, critique, or direction-setting before a spec), with an explicit 'Use when' clause. | 3 / 3 |
Trigger Term Quality | Terms like 'possibilities', 'critique', 'direction-setting', and 'tradeoffs' are somewhat relevant but miss many natural user phrases like 'brainstorm options', 'evaluate approaches', 'pros and cons', 'technical decision', 'architecture options', or 'RFC'. Coverage of natural variations is incomplete. | 2 / 3 |
Distinctiveness Conflict Risk | The description carves out a niche around pre-spec direction-setting, which helps distinguish it, but terms like 'product directions' and 'engineering directions' could overlap with general product management, spec-writing, or architecture skills. The phrase 'before a spec' adds some distinctiveness but the boundaries remain somewhat fuzzy. | 2 / 3 |
Total | 9 / 12 Passed |
Implementation
62%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides a well-structured ideation workflow with clear sequencing and validation gates, making the process easy to follow. However, it lacks concrete actionability—there are no examples of actual output format, no schema definition despite referencing one, and the steps remain abstract rather than executable. The claimed progressive disclosure architecture is unsupported by actual referenced files.
Suggestions
Add a concrete output example showing what a ranked candidate list with tradeoffs actually looks like, including the referenced schema_version:1 format.
Define what 'shallow codebase scan' means concretely—which files/patterns to look at, what commands to run, what constitutes sufficient grounding.
Either provide the referenced archive/reference files for progressive disclosure or remove the claim about 'archived references' and make the skill self-contained.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is reasonably efficient but includes some unnecessary filler (e.g., 'This entrypoint stays concise and keeps full operational context in archived references' is meta-commentary, not instruction). The 'Full Context' section with icon assets adds no operational value. Some sections like 'When to use' could be tightened. | 2 / 3 |
Actionability | The procedure provides a clear sequence of steps, but they are abstract and lack concrete examples of what 'shallow codebase scan' means, what the output format actually looks like, or executable commands/code. The 'Outputs' section mentions a schema but doesn't show it. The examples section shows user prompts but not expected outputs. | 2 / 3 |
Workflow Clarity | The 6-step procedure is clearly sequenced with logical ordering (clarify → check existing → ground → generate → filter → route). The validation section provides explicit gates with a fail-fast policy. Anti-patterns reinforce the correct ordering (e.g., don't critique before full candidate list exists). This is a non-destructive ideation task, so the validation checkpoints are appropriate. | 3 / 3 |
Progressive Disclosure | The skill claims progressive disclosure ('keeps full operational context in archived references') but no bundle files are provided and no references to detailed docs exist beyond mentioning 'he-brainstorm' and 'he-plan' without links. The 'Full Context' section only references icon assets, not operational documentation. The content is reasonably organized with clear sections but doesn't demonstrate actual progressive disclosure. | 2 / 3 |
Total | 9 / 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.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
metadata_version | 'metadata.version' is missing | Warning |
Total | 10 / 11 Passed | |
- Repository
- jscraik/Agent-Skills
- Commit
4c78f98
- 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.