CtrlK
BlogDocsLog inGet started
Tessl Logo

he-plan

Plan execution work from specs, brainstorm outputs, bugs, or feature requests into an implementation-ready sequence. Use when the user needs the Harness Engineering planning stage before execution.

65

Quality

79%

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

Quality

Content

75%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 an efficient, well-structured overview with a clear procedure, validation gate, and organized references. It is held back by minor duplication, delegation of artifact detail to references, and references that do not resolve within the provided bundle.

Suggestions

Deduplicate the "Keep GitHub PRs as delivery evidence, not the tracker of record" guidance that appears in both Constraints and Gotchas.

Inline a minimal plan-artifact template or example so the core deliverable is actionable without jumping to a reference file.

Make an explicit "See references/context-preservation.md" link so the bundled reference is connected to the body, and confirm the external reference paths exist in the consuming repo.

DimensionReasoningScore

Conciseness

Lean bullet-based structure that assumes Claude's competence, with minor trim opportunities such as the duplicated "Keep GitHub PRs as delivery evidence, not the tracker of record" appearing in both Constraints and Gotchas.

4 / 5

Actionability

Provides one concrete executable command (he_linear_traceability_lint.py) and specific ID conventions (P/UP, AC/UAC), but most guidance is procedural direction with the plan-artifact format delegated to references.

4 / 5

Workflow Clarity

A numbered Procedure plus a Validation gate with "Stop at the first failed gate" gives a clear sequence with checkpoints, though the fix-and-retry feedback loop is only implicitly described.

4 / 5

Progressive Disclosure

A well-organized, clearly signaled one-level-deep References section structures the overview, but the referenced paths are external to the bundle and the only bundled reference (context-preservation.md) is not linked from the body.

4 / 5

Total

16

/

20

Passed

Description

83%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 states what the skill does and when to use it, with concrete input triggers and a distinct niche. It is slightly held back by a single abstract action verb and minor synonym gaps.

DimensionReasoningScore

Specificity

Enumerates concrete input types (specs, brainstorm outputs, bugs, feature requests) and a concrete output ("implementation-ready sequence"), but the core action remains a single abstract transformation, leaving minor coverage gaps.

4 / 5

Completeness

Explicitly answers both what ("Plan execution work ... into an implementation-ready sequence") and when ("Use when the user needs the Harness Engineering planning stage before execution") with concrete trigger phrases.

5 / 5

Trigger Term Quality

Natural terms users would say ("specs", "brainstorm", "bugs", "feature requests", "planning stage") are present, though a few common synonyms are missing.

4 / 5

Distinctiveness Conflict Risk

Anchored to a distinct niche ("Harness Engineering planning stage", "before execution") with clear triggers, but retains minor overlap risk with broader planning skills.

4 / 5

Total

17

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

Total

15

/

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.