editor-harvest-plan

Turn an editor-test-harvester report into one lane-specific execution plan, e.g. process every Slate v2 candidate from a harvest through slate-plan without executing implementation.

Quality

71%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/editor-harvest-plan/SKILL.md

Quality

Content

85%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 a highly actionable routing playbook: concrete commands, unambiguous report resolution, a gated workflow with real validation checkpoints, and lane-specific policy that clearly earns its tokens. The weak spot is structure — everything lives inline in one long file with no bundle files, so lane-specific detail and scoring rules could be split into references for easier progressive loading.

Suggestions

Move the lane-specific include/exclude lists (Workflow steps 8-9) and the Slate v2 search heuristics into a references file (e.g. references/lanes.md), keeping only the lane registry and policy summary in SKILL.md.

Extract the confidence-score dimension table, caps, and completion threshold into a references/scoring.md referenced one level deep, reducing the main body length.

Trim the restated planning boundary to a single authoritative statement in Hard Policy and shorten cross-references to it elsewhere.

Dimension	Reasoning	Score
Conciseness	The body is dense with project-specific rules Claude could not infer (lane registry, hard policy, confidence caps, action values) and contains almost no generic explanation, but the planning-only boundary is restated in Hard Policy, the Lane Registry note, the Handoff section, and Workflow step 14, and the source-sync verification block is maintenance meta. Anchor 4: efficient with minor instances that could be trimmed.	4 / 5
Actionability	Fully executable, copy-paste-ready guidance throughout: exact commands with flags (`node .agents/skills/autogoal/scripts/create-goal-scratchpad.mjs --template editor-harvest-plan --title "<Lane> <Repo> Harvest Plan"`, `check-complete.mjs <plan>`), precise report-path resolution orders, concrete rg verification patterns, and a ready-to-use no-claim markdown block.	5 / 5
Workflow Clarity	A 14-step sequenced workflow with explicit validation checkpoints and feedback loops: report resolution fallbacks, threshold gating ("If the plan is below threshold, keep `pending` and name the next pass"), confidence-score caps tied to missing evidence, and a completion checklist that ends with check-complete.mjs passing. Anchor 5.	5 / 5
Progressive Disclosure	The skill ships as a single ~340-line SKILL.md with no references/ bundle; sections are clearly headed, but content that plausibly belongs in reference files — the lane include/exclude lists (Workflow steps 8-9), the confidence-score dimension table, and the issue/claim boilerplate — is fully inlined. Anchor 3: some structure, but the inline-heavy split is more than a minor organization gap given the length.	3 / 5
	Total	17 / 20 Passed

Description

57%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 highly distinctive and names a concrete, well-bounded capability, but it reads as a definition rather than a trigger: it has a clear "what" with no "Use when" clause, only partial keyword coverage (no plate-lane or generic synonyms), and only 1-2 concrete actions framed by a single lane example. Adding explicit trigger guidance and lane synonyms would lift the two capped dimensions.

Suggestions

Append a "Use when..." clause to the description, e.g. "Use when an editor-test-harvester report exists and the user wants one lane's rows routed into an execution plan" — the missing explicit trigger guidance currently caps completeness at 3.

Include natural trigger synonyms for both lanes and the generic case, e.g. "slate-v2 or plate", "all Slate tests from this harvest", "turn harvester results into a plan", so trigger_term_quality covers common user phrasings.

State the capability for all lanes rather than only the Slate v2 example, e.g. "for each lane (slate-v2, plate) apply the matching downstream plan skill", to close the coverage gap in specificity.

Dimension	Reasoning	Score
Specificity	Concrete actions are named — "turn ... report into one lane-specific execution plan", "process every Slate v2 candidate ... through slate-plan", "without executing implementation" — but they amount to 1-2 actions illustrated by a single lane example, with the plate lane and other capabilities uncovered. Not 4: the description does not enumerate several distinct actions with only minor coverage gaps.	3 / 5
Completeness	The "what" is clear and specific, but there is no "Use when..." clause or equivalent explicit trigger guidance in the description itself — the triggering context lives only in the body, capping this at 3 per the judging guidelines. Not 2: the "what" is unambiguous, not vague.	3 / 5
Trigger Term Quality	Relevant keywords exist ("editor-test-harvester report", "Slate v2", "slate-plan", "harvest"), but common user variations and synonyms are missing — nothing for the plate lane, or generic phrasings like "route these tests" or "make a test plan". Not 4: keyword coverage is partial rather than good-with-a-few-gaps.	3 / 5
Distinctiveness Conflict Risk	A clear niche with distinct triggers: it names its upstream skill (editor-test-harvester), a downstream skill (slate-plan), a specific artifact (execution plan), and a concrete scope boundary (without executing implementation), so conflict risk with other skills is minimal.	5 / 5
	Total	14 / 20 Passed

Validation

75%

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 — 12 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 2 suspicious	Warning

	Total	12 / 16 Passed

Repository: udecode/plate
Path: .agents/skills/editor-harvest-plan/SKILL.md
Commit: babb3c2

Reviewed: 2 days 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.