CtrlK
BlogDocsLog inGet started
Tessl Logo

he-plan

Create bounded Harness Engineering execution plans from approved specs or issue slices. Use when work needs ordered implementation units, explicit scope boundaries, rollback posture, traceability, and validation gates before code changes.

64

Quality

77%

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

Quality

Content

70%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 provides an executable, well-sequenced workflow with strong validation gates, but is somewhat repetitive and inlines contract material that belongs in referenced files, several of which are missing from the bundle.

Suggestions

Move the BLUF paragraph contract and the exact professional-review output headings out of SKILL.md into the referenced contract files, keeping only the trigger and a one-line pointer inline.

Fix or remove the dead `../../references/...` paths that are not present in the bundle so progressive-disclosure navigation does not dead-end.

Dedupe the professional-confidence-review mode description and the role-stack prompt, which currently recur across When to Use, Procedure step 11, and Output Format.

DimensionReasoningScore

Conciseness

The body is dense and avoids explaining known concepts, but restates the professional-confidence-review mode and role-stack prompt across When-to-Use, Procedure, Validation, and Output Format, and several compound policy clauses could be tightened.

3 / 5

Actionability

It names exact lints, executable commands (e.g. `python3 Plugins/harness-engineering/scripts/check_bluf_structure.py <plan-path> --json`), field lists, and enum values, but a few referenced files are absent from the bundle and one script path is hardcoded, leaving minor gaps.

4 / 5

Workflow Clarity

The 12-step Procedure is clearly sequenced with a dedicated fail-fast Validation section, explicit block-handoff stop conditions, a Failure Mode recovery step, and feedback-loop language for an artifact-writing skill.

5 / 5

Progressive Disclosure

Structure points to reference files one level deep, but substantial contract material is inlined in the body and several referenced paths (professional-confidence-review.md, plan-artifact-contract.md, stage-arc-boundary-contract.md, subagent-call-contract.md, deferred-context-index.md) do not exist in the bundle.

3 / 5

Total

15

/

20

Passed

Description

85%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 is specific, complete, and distinctive with both a clear purpose and an explicit trigger clause. Its only weakness is that the trigger terms lean professional/jargon-heavy rather than matching natural user phrasing.

DimensionReasoningScore

Specificity

"Create bounded Harness Engineering execution plans" plus "ordered implementation units, explicit scope boundaries, rollback posture, traceability, and validation gates" lists multiple concrete, distinct capabilities with comprehensive coverage.

5 / 5

Completeness

It states a clear "what" (create bounded execution plans from approved specs/slices) and an explicit "Use when..." clause with concrete trigger conditions, satisfying both halves.

5 / 5

Trigger Term Quality

Triggers like "approved specs", "issue slices", "rollback posture", "traceability", and "validation gates" are domain-idiomatic rather than the natural phrasing a user would say, with several common variations missing.

3 / 5

Distinctiveness Conflict Risk

The "Harness Engineering execution plans from approved specs or issue slices" niche has distinct, specific triggers and minimal overlap risk with other skills.

5 / 5

Total

18

/

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.